Skill管理员：在对话里管理 Skill 的安装、更新与自定义

Skill管理员（@user_b3e2a00b/skill-manager-plus，v1.0.0）是 SkillHub 社区 ai-agent 类 Skill，用于管理系统级技能的安装、更新、卸载及本地规则补充与自定义。用户在消息中提供 .zip 的 HTTP 链接并要求装/更、要求卸载、或表达修改技能规则等意图时触发，普通编码问答不触发。安装可按官方提示读取 skillhub.md 安装坐标，或用 skillhub install 并 --dir 指向客户端 skills 目录（如 Cursor 为 ~/.cursor/skills/）。requires_api_key=false。

knowledge-teaching：用 Agent Skill 写系统化、可核实的深度教学文

knowledge-teaching 是 SkillHub education 类 Skill，面向「真正学懂」某主题的请求：生成大纲先行、由浅入深的系统化教学 Markdown，强调联网核实、编号引用与存疑标注，并可导出 Word/PDF。本文说明触发边界（教程/科普/系统学习等）、核心能力与 SkillHub CLI 安装坐标，并给出可复现的提示示例；安装细节请以官网技能页为准。

游戏开发Agent技能精选：为游戏开发场景准备的 SkillHub 技能

介绍 SkillHub 社区技能「游戏开发Agent技能精选」（@user_3c6cb52e/router-sh-jrv0ek，v1.0.0，dev-programming，无需 API Key）。说明其定位、公开元数据范围内的能力表述，以及按 skillhub.cn 文档用 CLI 或提示词安装到 Cursor 等客户端 skills 目录的步骤，并提醒以安装后 SKILL.md 为准、注意 --dir 与社区来源等限制。

知识库标签化：为文档批量打标并生成目录树

介绍 SkillHub 社区 Skill「知识库标签化」（@user_70c2f807/knowledge-base-tagging，v1.0.0，knowledge-management，无需 API Key）。面向文档找不到、标签混乱的痛点，在用户提供标题与摘要的前提下，按 SKILL.md 流程设计多层级标签、批量打标、建立文档关联并输出目录树与使用指南，可导入 Notion、Confluence 等系统。说明 skillhub install 安装命令、Cursor 等 skills 目录及典型对话示例与 50 篇分批、不访问内网等限制。

小羊标书智能写作：用 Agent Skill 完成招标解读、成稿与合规审查

本文介绍 SkillHub 社区 Skill「标书智能写作大师」（@user_ba095919/biaoshu-writer-build，v3.1.2），即百炼标书面向投标场景的 Agent 能力：解读招标文件、生成投标文件、审查合规风险。说明通过 skillhub CLI 安装到 Cursor 等客户端 skills 目录的步骤、requires_api_key 配置注意点，以及用自然语言串联解读—撰写—审查的典型用法与适用边界。

大姨妈守护.skill：把经期管理做成 Agent 里的微信式陪伴

大姨妈守护.skill（@user_ae5129cb/dayimashouhu，v1.0.0）是 SkillHub 社区 life-service 类技能，无需 API Key。它将微信式短句对话、月经周期记录与推算、提前 7 天提醒、多男友人设、截图克隆说话风格、转发男友文案及 profiles.json 档案等写入 SKILL.md。文章说明 SkillHub CLI 安装到 Cursor/Claude/Codex 等 skills 目录的命令，典型触发话术与适用场景，并提醒 Cron 与医疗建议等限制。

诗歌鉴赏助手：把古诗赏析流程写进 Agent Skill

诗歌鉴赏助手是 SkillHub 社区 education 类 Skill（v1.0.1，无需 API Key），通过 SKILL.md 约束 Agent 在用户问诗、赏析、意象与格律时做白话翻译、多维拆解与对比推荐，并明确不做代写与标准答案。本文介绍其定位、核心能力、skillhub install 安装路径（含 Cursor skills 目录）及文档中的典型提问示例与使用边界。

运动计划生成：在 Agent 中按目标输出结构化周训练计划

运动计划生成是 SkillHub 社区技能 @user_70c2f807/workout-plan-generator（v1.0.0，life-service，无需 API Key）。它通过 SKILL.md 约定触发词、四步流程与 Markdown 周计划模板，根据减脂/增肌/塑形目标、训练天数、器械与经验生成动作、组次、休息及热身拉伸，并支持按反馈调强度。本文基于 SkillHub 页面与技能文档说明安装命令（skillhub install workout-plan-generator --namespace user_70c2f807 --dir 对应 skills 目录）、典型对话示例，并列出不适用康复/竞技训练等场景与安全限制。

ai日报：在 Agent 里挂载「绿茶视角」社交策略框架

ai日报（@user_f918c47e/daily-ai-news-plus）是 SkillHub 社区 Skill，版本 2.3.111，分类 knowledge-management，无需 API Key。官方定位为绿茶的沟通操作系统：基于 20+ 学术与文化来源提炼 5 个心智模型、7 条决策启发式与表达 DNA，用于社交场景、情感博弈及操控与反操控分析。文章说明名称与坐标 daily-ai-news-plus 的差异，给出 skillhub install 与 Cursor/Claude Code/Codex 目录示例，并列出绿茶模式等触发语与使用注意。

销售商务全能助手：三版话术一键生成

销售商务全能助手（@user_aa0a2d3e/sales-season-master）是 SkillHub 社区 business-ops 类 Skill，无需 API Key。按「场景+客户类型+产品」输入，可生成正式、亲和、精简三版话术，覆盖拓客、报价、议价、催单与售后。本文基于官方页面与技能包 SKILL.md，说明能力边界、skillhub install 命令及 Cursor 等客户端 skills 目录配置。

电影动漫角色模拟：用 Skill 做虚构角色对话

电影动漫角色模拟（@user_af2bf003/character-v2）是 SkillHub 社区 content-creation 类 Skill，v1.0.1，用于在用户聊天、扮演或多角色对谈时模拟动漫、影视、游戏中的经典虚构角色。标签 requires_api_key=false，无需额外 Key。本文基于官方简介说明单角色与多角色能力、触发话术，并给出按 skillhub.md 安装 CLI、用 skillhub install 与 --dir 装入 Cursor 等目录的步骤，以及可复现的对话示例与适用注意。

内容总结小工具：用 Agent Skill 压缩长文、提炼要点

介绍 SkillHub 社区 Skill「内容总结小工具」（@user_0cb2ead3/content-summary-helper1，v1.0.1）：对长文本做精简概括与要点提炼，分类 knowledge-management，无需 API Key。说明 SkillHub 坐标、评分与下载数据，给出 skillhub CLI 与 Cursor/Claude Code/Codex 的 skills 目录安装要点，以及安装后在 Agent 中触发总结的用法边界与注意事项。

思考与决策辅助：用八步批判性思维框架约束 Agent 决策过程

SkillHub 社区 Skill「思考与决策辅助」（@user_aad6add3/critical-thinking，v1.0.0）提供身份确认、核心问题识别、类比联想、应用判断、结果验证、反向推理、知识验证与思维总结八步框架，用于复杂个人、工作与技术决策。本文介绍其定位、核心步骤、SkillHub CLI 与提示词安装方式（含 Cursor 等 skills 目录），以及典型对话用法与使用注意。无需 API Key。

数据报表解读：在 Agent 里把表格数据讲清楚

SkillHub 社区 Skill「数据报表解读」（@user_70c2f807/data-report-interpreter，v1.0.0，data-analysis）通过 SKILL.md 约束 Agent：在用户粘贴 Excel 类表格数据时做统计、趋势与同比环比对比、异常标注、图表类型建议及报告结论，无需 API Key。不读本地文件、不生成图表文件，也不做采集与库表操作。本文介绍定位、能力、skillhub install 安装路径及典型对话用法，数据来自 SkillHub 页面与 Skill 原文。

cloris：身心灵从业者的商业诊断 Skill

cloris（@user_78963a05/cloris）是 SkillHub 上的 business-ops 类社区 Skill，面向塔罗师、占星师、疗愈师等从业者，围绕定位、内容、变现、成交做商业诊断并指向下一步行动。版本 1.0.0，无需 API Key。文章说明其定位与核实功能，并给出通过 SkillHub CLI 或安装文档将 Skill 装入 Cursor、Claude Code、Codex 等客户端 skills 目录的步骤，以及自然语言触发诊断的典型用法与「仅供学习交流」等使用注意。

竞品速览：用 Agent Skill 快速整理竞品核心信息

竞品速览是 SkillHub 社区发布的 data-analysis 类 Skill（@user_70c2f807/competitor-overview，v1.0.0），用于在 Agent 对话中快速获取竞品功能特点、定价策略与用户评价摘要，标签 requires_api_key=false。本文依据 SkillHub 页面与官方安装文档说明其定位、能力与安装方式：通过 skillhub CLI 将 Skill 安装到 Cursor、Claude Code 或 Codex 对应的 skills 目录，并在对话中指定竞品与关注维度使用。适合需要先做竞品速览再深挖的产品与研发场景，并提醒结合一手来源核对结论。

股市分析：在 Agent 里做跨市场金融分析与研报输出

股市分析是 SkillHub 上 @user_70b62916/stock-analyze（v1.0.0）提供的专业类金融技能包，覆盖美股、港股、中概股与 A 股的行情、财务、财报、行业、宏观、选股与深度研报，内置分析师人设与 taste-skill 报告规范，并整合 28 个外部模块。文章说明其定位、触发词、通过 skillhub install 安装到 Cursor 等目录的步骤，以及 requires_api_key 等使用注意。

绘画基础训练：用 Agent Skill 做每日练习规划与反馈

SkillHub 社区 Skill「绘画基础训练」（@user_70c2f807/drawing-foundation-training，v1.0.0，education）面向零基础与初学者，按 SKILL.md 流程做水平评估、分阶段每日任务（线条、透视、光影等）、练习方法与基于文字描述的反馈调整。无需 API Key。可通过 skillhub install drawing-foundation-training --namespace user_70c2f807 安装到 Cursor 等 skills 目录。不生成画作、无法看图点评，不替代面授与商业项目。

经济学原理图解：用供需与图解把经济概念讲清楚

经济学原理图解是 SkillHub 社区 education 类 Skill（@user_70c2f807/economics-principles-illustrated，v1.0.0），无需 API Key。它指导 Agent 用供需、边际、机会成本等概念配合生活案例与文字版图表解读热点，并按四步流程输出结构化分析，明确不提供投资预测与理财建议。文章说明核心能力、skillhub 安装命令与各客户端 skills 目录，并给出官方快速开始示例，便于在 Cursor 等环境中启用。

AI提示词设计服务：把提示词从「能用」做到稳定可控

介绍 SkillHub 社区 Skill「AI提示词设计服务 - 全行业专业提示词优化工程」（@user_9e8820a0/ai-prompt-designer，v1.0.0，ai-agent）。涵盖模板、定制、深度优化、风格调整与拆分改写，无需 API Key。说明通过 skillhub CLI 安装到 Cursor、Claude Code、Codex 等 skills 目录的步骤，以及基于官方简介的典型使用方式与适用注意。

装修预算分配：用 Agent Skill 结构化家装预算

装修预算分配是 SkillHub 社区 Skill @user_70c2f807/renovation-budget-allocation（v1.0.0，life-service），无需 API Key。文章说明其定位、公开可核对的能力边界，以及通过 skillhub CLI 或官方提示词安装到 Cursor 等 Agent skills 目录的步骤；触发条件与输出格式以本地 SKILL.md 为准。

个人效能提升：用 Agent Skill 做六维度效能诊断与行动规划

SkillHub 社区 Skill「个人效能提升」（@user_bfc01702/effect1，v1.0.0）将心智、目标、时间、精力、情感、关系六维度诊断流程写入 SKILL.md，无需 API Key。文章说明其四步标准流程、输出规范，以及通过 skillhub CLI 安装到 Cursor、Claude Code、Codex 等 skills 目录的方法，并给出官方文档中的三类对话示例，便于在 Agent 中复现效能复盘。

摄影构图训练：把经典构图法则与每日练习写进 Agent Skill

摄影构图训练是 SkillHub 社区教育类 Skill（@user_70c2f807/photography-composition-training，v1.0.0），无需 API Key。它用 SKILL.md 定义构图教学、每日拍摄任务与基于文字描述的画面点评流程，覆盖三分法、引导线、框架等经典法则及人像、风景等题材策略，并明确不处理后期与器材选购。文章说明安装命令、Cursor 等客户端 skills 目录及典型对话示例，适合在 Agent 中系统化练构图的摄影爱好者。

合同速查：在 Agent 里做合同条款审查辅助

合同速查是 SkillHub 社区 Skill（@user_70c2f807/contract-quick-check，v1.0.0），面向专业类场景，帮助标出关键条款、识别潜在风险并提示缺失条款，无需 API Key。文章说明其定位与核实功能，给出 skillhub CLI 安装命令及 Cursor 等客户端 skills 目录，并提醒输出仅为辅助、重大合同须法务复核。

SoloBrand 自动起号运营官：把一人公司的内容运营搬进 Agent

SoloBrand 自动起号运营官是 SkillHub 社区 content-creation 类 Skill（v1.0.0，@user_e97ae77c/solo-brand-ops-autopilot），面向个人 IP、起号、选题、日更与数据复盘等场景，标签 requires_api_key=false。文章依据官方简介说明能力范围，并给出 skillhub CLI 安装到 Cursor 等 skills 目录的步骤与注意事项，不编造未公开的 SKILL 细节。

分析文件目录结构：用 Agent Skill 梳理项目目录

介绍 SkillHub 社区技能「分析文件目录结构」（@user_19fd2d55/analysis-project-content，v1.0.1，it-ops-security，无需 API Key）。说明其面向项目目录与内容梳理的定位，给出 skillhub CLI 与提示词两种安装方式及 Cursor 等常见 skills 路径，并提醒公开页未附完整 SKILL.md、安装时若遇下载 404 需先确认包可用。适合接手仓库与运维安全场景下规范 Agent 做目录分析。

英语包过宝典：在 Agent 里挂载英语学习与备考 Skill

英语包过宝典是 SkillHub 社区 education 类技能（@user_c8f87c33/english-pro，v1.0.1），子类为语言学习与考试备考，无需 API Key。文章说明其定位、已公开的元数据与安全信息，并给出按 skillhub.md 安装 CLI、用 skillhub install 装入 Cursor 等 skills 目录的步骤。商店页未提供 overview，具体能力以安装后 SKILL.md 为准。

coderules-skill：按技术栈自动套用代码规范的 Agent Skill

coderules-skill 是 SkillHub 社区技能（@user_3b34947d/coderules-skill，v1.0.0），定位为智能代码规范助手：识别 TypeScript/Python/Go/Rust/Java 及 React、Vue、Next.js 等框架，加载对应规范后用于生成代码、审查、修复与初始化配置。无需 API Key。本文基于官方页面与元数据说明安装方式（skillhub CLI 与 Cursor/Claude Code/Codex 的 skills 目录）、触发词与典型对话用法，并提示社区来源与统计数据的查阅方式。

穿搭小管家：用六维五层框架系统学穿搭

穿搭小管家（@user_aad6add3/style-advisor）是 SkillHub 社区 education 类 Skill，用版型、色彩、材质、风格、层次、配饰六维，结合身材、体态、单品、组合、场景五层，系统拆解穿搭学习。本文基于官方简介与 SkillHub 元数据，说明定位、核心能力、skillhub CLI 与提示词安装方式，以及按框架提问的典型用法与适用注意。无需 API Key，版本 1.0.0。

商务英语速成：在 Agent 里按场景写外企邮件与会议话术

SkillHub 社区 Skill「商务英语速成」（@user_70c2f807/business-english-express，v1.0.0，education，无需 API Key）通过 SKILL.md 约束 Agent：在催款、邀约、会议、谈判等场景提供地道英文模板、正式度分档、中式英语避坑与跨文化提示，而非长文翻译。文章说明能力边界、skillhub 安装命令及 Cursor/Claude Code/Codex 的 skills 目录，并给出官方文档中的可复现对话示例。

DEEPQ-基金分析：在 Agent 里按基金名称拉齐公募信息与持仓

DEEPQ-基金分析是 SkillHub 社区 Skill（@user_e7dd0698/fund-analysis，v1.0.2），对指定公募基金提供基本信息、业绩、区间表现、基金经理观点与底层持仓分析。通过 guessFundCode、fundPerformance、fundUnderAssets 等工具在对话中触发，需配置 API Key。文章说明安装命令、典型问法与使用注意，官方页见 skillhub.cn。

炒股养家20260703：在 AI 助手里做股票分析复盘

炒股养家20260703（@user_7a539d5c/cgyj20260703）是 SkillHub 社区 professional 类 Skill，v1.0.0，简介强调仅作分析复盘、不构成投资建议，且 requires_api_key=false。文章说明其定位、可核实能力边界，以及按 skillhub.cn 安装文档用 skillhub CLI 或提示词安装到 Cursor、Claude Code、Codex 等 skills 目录的步骤，并提醒社区来源与合规使用。官方页面：https://www.skillhub.cn/skills/user_7a539d5c/cgyj20260703

163邮箱 Skill：把失败、纠正与更好做法写进 Agent 的学习记录

SkillHub 社区 Skill「163邮箱」（@user_bf84fce9/163email1，v1.0.0）按官方简介用于捕获命令失败、用户纠正、外部 API 错误、知识过时及更优做法，并在重大任务前回顾 learnings。标签 requires_api_key=false。本文说明其定位、触发场景，以及通过 skillhub.md 与 skillhub install --dir 在 Cursor 等环境安装的方式；并提醒以页面简介核对能力，勿仅凭名称理解为邮箱产品集成。

资治通鉴每日学习：在 Agent 里按日推进经典史学阅读

SkillHub 社区 Skill「资治通鉴每日学习」（@user_25ab92ec/zizhitongjian-study，v1.0.0，education，无需 API Key）通过 SKILL.md 定义每日一篇、原文译文解读、搜索与进度能力，并提供 Python 3.9+ 入口脚本。文章说明 skillhub 安装到 Cursor 等 skills 目录的方法、斜杠命令与 CLI 用法，并注明当前包内仅内置 3 天示例篇目、进度写入 data/progress.json 等实现细节与限制。

文件整理助手：让 Agent 按扩展名归类本地文件夹

文件整理助手（@user_c73fb2fe/file-organizer-skill-v2）是 SkillHub 社区版 knowledge-management 类 Skill，无需 API Key。它通过 SKILL.md 约定五步流程：扫描目标目录、按文档/图片/代码/压缩包/视频等扩展名分类、创建子文件夹、移动文件并输出报告。文章说明 skillhub CLI 安装命令、Cursor 等客户端的 skills 目录，以及典型对话用法与安全注意点。

通用数学建模工作流：把赛题拆成可执行的建模流水线

SkillHub 社区 Skill「通用数学建模工作流」（@user_3937f0b6/math-modeling-solver，v1.0.0）面向华中杯、CUMCM 等多小问数学建模竞赛，用 SKILL.md 规定理解题意、架构设计、Python 求解实现、约束校验与结果分析五阶段，并给出数据结构、代价函数与交付物清单。无需 API Key。本文说明定位、核心能力、skillhub 安装命令及 Cursor 等 skills 路径，并给出可复现的启用方式与适用注意。

Mongodb Wrap：SkillHub 上的 MongoDB 相关 Agent Skill

Mongodb Wrap（@user_922b1001/mongodb-wrap）是 SkillHub 社区 dev-programming 类 Skill，版本 1.0.0，标注 requires_api_key=false。公开 SKILL.md 以 MongoDB NoSQL 相关简短描述与 wrap、github、automation 标签为主，未附详细操作示例。文章说明官方页面入口、skillhub CLI 安装命令（含 --namespace 与 --dir）、Cursor 等常见 skills 路径，并提醒下载统计与内容边界，避免与完整 MongoDB 运维类 Skill 混淆。

旅游拍照万能助手：把旅行出片拆成可复制的 Agent Skill

旅游拍照万能助手是 SkillHub 社区 Skill（@user_aad6add3/travel-photo-assistant，v1.0.0），从构图、层次、光影、角度、动作、减法六维给出可套用的拍照公式，覆盖景区建议、时间点、动作、道具及单人/多人模式。本文介绍其定位、包内执行流程与《旅游拍照指南》输出结构，并说明通过 SkillHub CLI 或官方提示词安装到 Cursor 等 Agent skills 目录的方法，附乌镇示例输入。无需 API Key。

段永平语录：在 Agent 里固定「长期 + 企业本质」的投资对话方式

段永平语录是 SkillHub 社区 Skill（@user_9628b542/duan-yongping-investing，v1.0.2），模拟段永平雪球风格的投资思考：拆解用户逻辑、强调长期与企业本质、以警醒语录收尾。无需 API Key。文章说明其定位与能力边界，并给出按 skillhub.md 安装、Cursor 等客户端 skills 目录与 CLI 示例，以及估值、恐慌、逻辑复盘等可复现问法。

风水命理大师：在 Agent 里统一做八字分析与六爻起卦

风水命理大师（遇事不决一键起卦）是 SkillHub 社区 professional 类 Skill（@user_62ac3c58/fengshui-master，v1.0.0），覆盖八字分析、流年运势与六爻占卜；首次收集生辰建档，后续复用。无需 API Key。文章说明触发关键词、skillhub 安装命令与各客户端 skills 目录，并给出可复现的对话示例与使用注意。

agent+obsidian=长期记忆：用 Obsidian 给 Agent 做跨会话记忆

介绍 SkillHub 社区 Skill「agent+obsidian=长期记忆」（@user_7da98a98/obsidian-memory，v1.0.2）。从 SOUL.md 的 OBSIDIAN_MEMORY_PATH 定位 Obsidian 记忆库，任务初加载 profile、rules 与近期日志，在「任务完成」或 /记一下 等触发词下写回 Markdown。包内 v2.0 说明含命中打点、/审计记忆、重复踩坑升级 rules.md 等 Anti-Rot 治理。含 skillhub 安装命令、记忆目录结构与 SOUL 配置要点，适合需要可编辑长期记忆的写作与开发场景。

一键配置飞书：用 Skill 缩短飞书接入步骤

飞书接入常涉及开放平台应用、凭证与本地配置，步骤分散易漏。「一键配置飞书」是 SkillHub 社区 Skill（@user_3ad8e894/feishu-quick-setup，v1.0.0，it-ops-security），简介为 30 秒接入飞书，标签 requires_api_key=false。本文基于 SkillHub 公开信息与安装文档，说明定位、可核实能力、skillhub install 与 Cursor/Claude Code/Codex 的 skills 目录，以及通过对话触发 Skill 的典型用法与社区来源注意事项。

AI摘要阅读：长文六模式结构化提炼

AI摘要阅读是 SkillHub 社区技能 @user_70c2f807/summary-reader（v1.0.0），面向长文与文档提炼结构化摘要，支持极简、结构化、脉络梳理、定向提取、对比、深度精读六种模式。官方说明为纯本地运行、无需联网，且 requires_api_key=false。文章说明定位与六种模式，并给出 SkillHub CLI 与 Agent 安装指引（含 Cursor 的 ~/.cursor/skills/ 示例），典型用法为启用 Skill 后指定模式处理正文。

文件自动归档助手：按类型与规则整理杂乱文件夹

文件自动归档助手（@user_e5701557/file-auto-archiver，v1.0.0）是 SkillHub 社区办公效率类 Skill，按文件类型、日期或关键词整理图片、文档、视频、代码等，标签 requires_api_key=false。本文基于 SkillHub 公开信息说明定位、能力与安装：可用 skillhub install 安装到 Cursor、Claude Code 等 skills 目录，或通过官方安装提示词让 AI 按 skillhub.md 配置。并给出对话式整理示例与备份、预览等注意事项。

运营数据复盘｜简诗 AI：用同口径数据还原过程，把复盘落到下一轮行动

SkillHub 社区 Skill「运营数据复盘｜简诗 AI」（@user_fccf428b/operations-retrospective-facilitator，v1.0.3，data-analysis）用于把目标、数据、过程与异常整理为目标对照、事实时间线、偏差、原因假设与可观察指标，并禁止把相关性当根因、缺数当零。本文介绍其核对清单与交付物、SkillHub CLI 安装到 Cursor 等 skills 目录的方法，以及无需 API Key 的适用场景与输入注意。

倪海厦skill·经方中医AI：在 Agent 里固定经方派辨证与选方思路

SkillHub 社区技能「倪海厦skill·经方中医AI」（@user_bbd159f4/nihaixa-perspective，v1.0.0）将倪海厦经方派心智模型写入 SKILL.md：六经辨证、阳气论、经典至上、经方为主，并声明基于梁冬对话、人纪班记录与医案等素材的知识范围。无需 API Key。本文说明其定位、触发词、skillhub 安装命令及各客户端 skills 目录，并给出可复现的提问示例与医疗免责注意。

副业探索器：用 Agent Skill 把「技能与时间」落成可执行的副业方案

副业探索器（@user_70c2f807/side-hustle-explorer，v1.0.1）是 SkillHub 社区 business-ops 类 Skill，无需 API Key。它在用户谈及副业、兼职、技能变现等场景时，按 SKILL.md 执行三步流程：画像、方向匹配、30 天启动计划，输出含收入区间与风险提示的结构化报告，并明确不处理创业规划、投资或违法收入。本文介绍其定位、能力与安装命令（skillhub install --namespace user_70c2f807），以及 Cursor、Claude Code、Codex 等 skills 目录配置要点与典型对话示例。

aigc-shed：面向论文段落的 AIGC 降重 Skill

aigc-shed 是 SkillHub 社区 Skill（@user_c880a486/aigcshed，v1.0.0），面向论文段落做 AIGC 降重与去机器味改写，保留学术核心。本文依据官方简介与 SkillHub 安装文档，说明定位、触发场景、skillhub CLI 安装命令（含 Cursor 的 ~/.cursor/skills/ 目录）、典型对话用法，并区分不适用场景与学术诚信注意点。标签 requires_api_key=false，无需额外 API Key。

前端页面设置：用 Skill 约束 AI 产出有辨识度的前端界面

SkillHub 社区 Skill「前端页面设置」（@user_d18a1d0d/frontend-design-ld，v1.0.0）面向建站、落地页、仪表盘、React 组件与 Web UI 美化等任务，强调 production-grade 设计质量并避免 generic AI 审美。无需 API Key。文章说明定位与核心能力，并给出 skillhub CLI 安装命令、Cursor/Claude Code/Codex 的 skills 目录及官方安装提示词，附适用场景与目录配置注意事项。

微博热手：在 Agent 里直接拉取微博热搜榜

「微博热手」是 SkillHub 社区 Skill（@user_9ccfb9fb/weibo-hot-search-pro，v1.0.0），归类 knowledge-management，用于在用户询问热搜、今日热搜、微博热搜、热点新闻、头条时触发，拉取微博热搜榜并支持前 N 条，返回排名、标题与热度值。官方标注 requires_api_key=false。安装可让 AI 按 skillhub.cn/install/skillhub.md 安装该坐标，或使用 skillhub install 并 --dir 指向 Agent 的 skills 目录。适合在 Cursor 等环境中用对话快速查看榜单；数据以平台为准，社区维护需自行关注更新。

Mental Health Analysis Tool：用 Agent Skill 做视频导向的心理健康分析

介绍 SkillHub 社区 Skill「Mental Health Analysis Tool | 心理健康分析工具」（v1.0.6，@user_bb47e3e3/psychology-analysis）。说明其通过视频分析识别常见心理问题倾向、输出结构化报告与改善建议的定位，requires_api_key=false。给出按 skillhub.cn 安装文档与 CLI 安装到 Cursor 等 skills 目录的步骤，以及基于官方能力的对话式用法示意，并强调非临床诊断、隐私合规与能力边界。

财报暴雷·财务诡计：SkillHub 专业类 Skill 的安装与包内能力说明

介绍 SkillHub 坐标 @user_231765ee/jango-v3（v1.0.0，professional，requires_api_key=false）的元数据与 skillhub install 安装方式，并说明 Cursor、Claude Code、Codex 常用 skills 目录。重点据安装包 SKILL.md 描述八层推理指纹蒸馏、九模块部署约束及评审/指导/授课/讨论四类任务与自评。同时标明上架名称「财报暴雷·财务诡计」与包内「学者推理蒸馏器」不一致，避免误用。

基于第一性原理的财务分析技能：上市公司财报深度分析与持续迭代

介绍 SkillHub 社区技能「基于第一性原理的财务分析技能」（@user_d0c0f066/financial-analysis-plus，v1.0.0）。面向上市公司年报/季报/半年报解读与财务分析触发场景，涵盖业绩点评、营收与毛利率拆解、现金流与资产负债、ROE 与估值等；不支持纯宏观、非上市简单问答及无财务数据的行业研究。说明 skillhub CLI 安装、各 Agent skills 目录及典型对话用法，并给出官方页面与 API 地址。

Document Summarize：把 URL 与本地文档交给 Agent 做结构化摘要

Document Summarize 是 SkillHub 社区技能（@user_7eecc4ea/summarize-new，v1.0.0），在用户提出总结、摘要、提炼要点或提供 URL/文件路径时触发，支持 HTML、PDF、Markdown、TXT。本文说明其定位、核实功能、通过 skillhub CLI 安装到 Cursor 等 skills 目录的步骤，以及典型对话用法与安装路径注意事项；数据与安装命令均来自官方页面与 SkillHub 安装文档。

数学建模全流程专家：竞赛五阶段与论文双引擎

本文介绍 SkillHub 社区 Skill「数学建模全流程专家」（@user_0210c829/mathmodel-workflow-v3，v3.0.0）。它覆盖吃透赛题、建模、编码求解、论文撰写与验收门禁五阶段，支持 Typst/LaTeX 双引擎与题型防错知识库，且无需 API Key。文章说明定位与核心能力，给出 skillhub CLI 安装命令及 Cursor、Claude Code、Codex 的 skills 目录示例，并说明在 Agent 中按阶段启用的方式与社区来源的使用注意。

员工克隆Skill：把个人工作风格打包成 Agent 可安装的 SKILL

员工克隆Skill（@user_ef64daef/kelong，v1.0.0）是 SkillHub 社区 ai-agent 类技能，支持问答创建、文档与聊天记录建模、场景校准，生成数字克隆体用于回复、决策辅助与话术推荐，并强调六大安全边界与只建议不操作。训练结果可导出标准 SKILL，通过 skillhub CLI 安装到 Cursor、Claude Code、Codex 等 skills 目录。本文基于官方页面与安装文档整理定位、能力与安装步骤，不编造配置与案例。

Usingagentskills：在 SkillHub 安装并交给 Agent 使用的 ai-agent 技能

Usingagentskills（@user_3c6cb52e/using-agent-skills-lr-61zp）是 SkillHub 上 1.0.0 版本的社区 ai-agent 技能，标签 requires_api_key=false。公开简介说明其用于帮助 AI Agent 更高效完成与 Agent Skills 相关的任务。本文依据 SkillHub 页面与 skillhub.cn/install/skillhub.md，说明 CLI 检查、skillhub install 与常用 skills 目录（Cursor、Claude Code、Codex），并提醒安装须指定 --dir、细节以本地 SKILL.md 为准。

后宫佳丽.skill：多角色情感陪聊 Skill

后宫佳丽.skill（@user_ae5129cb/hougongjiali，v1.0.1）是 SkillHub 社区 life-service 类 Skill，面向多角色 AI 情感陪聊。本文基于官方页面与包内 SKILL.md，介绍五位人设、亲密度与情绪急救、profiles.json 记忆、无需 API Key 的安装方式（skillhub install hougongjiali --namespace user_ae5129cb），以及 Cursor 等客户端 skills 目录配置与典型对话触发词。

学校财务分析：在 Agent 里做培训机构收款与课消统计

学校财务分析是 SkillHub 社区 Skill（@user_06ad406b/finance-record，v1.0.0），无需 API Key。面向英语培训机构，在 Agent 中记录收款、退费、课消，汇总本月净额与收款目标完成率，以表格与经营建议输出且禁止编造数据。本文说明定位、核心能力、skillhub install 安装路径及典型触发词用法，并给出官方页面链接。

算命大师：在 Agent 里统一接入多体系命理占卜 Skill

算命大师（@user_8dd18822/fortune-telling-master）是 SkillHub 社区发布的 knowledge-management 类 Agent Skill，v1.0.0，无需 API Key。它整合八字、紫微、奇门、六爻、梅花、塔罗、星盘、风水、起名、合婚择吉等话题，在用户提及算命、排盘、运势等关键词时激活，并声明仅作文化参考。本文基于官方页面说明安装命令、各客户端 skills 目录与典型对话用法。

曾仕强教授思想解惑：在 Agent 里接入曾师视角的知识类 Skill

曾仕强教授思想解惑是 SkillHub 上归类为 knowledge-management 的 Agent Skill，坐标 @user_c0ec2a90/zengshiqiang，官方入口为 api.skillhub.cn/user_c0ec2a90/zengshiqiang。平台展示评分 98622、下载 727 次。安装需 skillhub CLI 并对命名空间 user_c0ec2a90 登录或传入 API Key，再用 --dir 指向 Cursor 等客户端的 skills 目录。公开接口未提供包内详情，触发条件与示例以安装后的 SKILL.md 为准；须与站内其他 zengshiqiang 命名空间区分。

视频/文章链接自动转存：链接一键进知识库收件箱

介绍 SkillHub 社区 Skill「视频/文章链接自动转存」（@user_ae7a4960/links-pipeline，v2.0.0）。它是一条链接处理管线：识别抖音、小红书、B 站视频与公众号/网页文章，自动下载或提取正文、转录视频、识别主题并路由到知识库收件箱。文章说明其定位与核心能力，并依据 skillhub.cn 安装文档给出 CLI 检查、安装命令及 Cursor/Claude Code/Codex 常见 skills 目录；典型用法以提供 URL 触发管线为主。标注 requires_api_key=false 及安装路径等注意事项。

企业人事合规风险诊断：八大人事模块的合规清单 Skill

SkillHub 社区 Skill「企业人事合规风险诊断」（v1.0.1，@user_6d4b0067/compliance-risk-diagnosis）将招聘、合同、考勤、薪酬、社保、培训、离职、档案八大模块的合规标准、法规依据、风险点与检查清单写入 SKILL.md，供 Cursor 等 Agent 做结构化自检与整改表输出。本文说明定位、核心能力、skillhub install 命令与各客户端 skills 目录，并提示其仅为参考清单而非法律意见。

Graphql设计：为 AI Agent 准备的 GraphQL 设计 Skill

Graphql设计是 SkillHub 社区技能（@user_3c6cb52e/graphql-design-sh-4mq9ya，v1.0.0，dev-programming），简介为帮助 AI Agent 高效完成 GraphQL 设计相关任务，且 requires_api_key=false。本文基于 SkillHub 展示页与官方安装文档，说明定位、安装方式（提示词或 skillhub CLI 并指定 Cursor/Claude/Codex 等 skills 目录）、典型启用步骤，并提醒社区来源与公开资料未展开的细节需以安装后的 SKILL.md 为准。

恋爱聊天军师 V2.0.0：用 Skill 把聊天记录拆成可执行的回复建议

恋爱聊天军师是 SkillHub 社区 life-service 类 Skill（@user_cefa66c8/dating-chat-strategist，v2.0.0），面向容易讨好、拿捏不好分寸的主动聊天场景。支持粘贴聊天记录，分析对方态度与潜台词，给出自然不卑微的回复建议并提示踩雷点；requires_api_key=false。文章说明定位、核心能力，以及用 skillhub CLI 或安装提示词装入 Cursor 等客户端 skills 目录的步骤与典型提问方式。

百宸法律智能体：在 AI 对话里接入律所知识库的法律专业 Skill

百宸法律智能体是 SkillHub 上由百宸律师事务所推出的专业类 Agent Skill（@user_148deca1/baichen-legal，v1.0.0），基于律所法律智能体知识库，覆盖民商事诉讼、刑事辩护、合同审查、公司治理、劳动合规、私募股权与涉外投资等场景。本文依据 SkillHub 公开简介与安装文档，说明定位、触发关键词、skillhub install 与 Cursor skills 目录配置，并列出合同审查、诉讼策略、尽职调查等典型对话用法及官方明确的不适用边界（造价、财税、须执业律师办理事项）。无需 API Key。

投资每日早报：把每日股市新闻收成主线与信号

投资每日早报（@user_0c7f1934/daily-stock-news-v2，v2.0.4）是 SkillHub 社区 professional 类 Skill，无需 API Key。用户用「股市早报」「主线是什么」「今日操作建议」等自然语言触发后，按交易员方法论框架对当日股市新闻做结构化分析，输出主线、潜在主线与买卖信号。文章说明定位、能力、skillhub install 到 Cursor/Claude Code/Codex 等 skills 目录的步骤，以及典型提问与使用注意。

股票持仓分析：用 Agent Skill 做财报与基本面多维拆解

介绍 SkillHub 社区 Skill「股票持仓分析」（@user_0c7f1934/stock-holding-analysis，v1.2.3）。当用户提及股票名称、代码或持仓分析时，按 Skill 指引从财务、基本面、行业趋势、供需、政策与地缘等维度组织回答，适用于投资决策、持仓检视与调研。文章说明 requires_api_key=false、professional 分类及官方统计，并给出 Agent 提示词安装与 skillhub CLI（含 Cursor、Claude Code、Codex 目录）示例与典型触发话术。

提示词大师：用自然语言把需求交给 Agent 拆解与交付

提示词大师（@user_5d00e27d/majia-prompt-translator）是 SkillHub 社区 ai-agent 类 Skill，v1.0.9，无需 API Key。面向不熟悉 prompt 的用户：用自然语言说需求，由 Agent 理解意图、拆解问题并交付生成、分析、规划、建议、查询等结果；首次使用会调研需求方向。本文依据 SkillHub 公开信息与安装文档，说明定位、能力、skillhub CLI 安装路径（含 Cursor 的 ~/.cursor/skills/）及典型对话用法与注意事项。

电脑管家：让 Agent 直接操控本机音量、电源与系统设置

电脑管家（@user_ad872d55/pc-butler，v2.0.3）是 SkillHub 社区 ai-agent 类 Skill，无需 API Key。它将音量、亮度、锁屏、应用与网络、截屏、剪贴板、媒体、内存清理、关机重启等能力封装给 Cursor、Claude Code、Codex 等 Agent，并支持审计日志、可逆快照、电源计划、外接显示器 DDC/CI、合盖保活与健康巡检。文章说明定位、已核实功能、skillhub CLI 安装路径与典型对话触发方式，并提醒高权限与机型差异风险。

测试：在对话里发现并安装 Agent Skill

SkillHub 社区 Skill「测试」（@user_9d09f246/123，v1.0.0）面向用户询问「怎么做 X」「有没有 skill」等场景，引导 Agent 发现并安装可扩展能力的 Skill。无需 API Key。安装可让 AI 按 skillhub.md 处理，或用 skillhub install user_9d09f246/123 并指定 Cursor 等 skills 目录。

理财推荐Finance：为 Agent 补齐财富管理说明与问答能力

理财推荐Finance（@user_0caf726f/wealth-management，v1.0.2）是 SkillHub 社区 professional 类 Skill，无需 API Key。它面向个人金融与财富管理，覆盖银行财富产品说明、理财产品推荐、收益与持有期、节假日收益规则及常见问答。文章说明其定位与核心能力，并给出通过 skillhub CLI 或按 skillhub.md 提示安装的步骤，以及 Cursor、Claude Code、Codex 等 skills 目录注意事项。适用需在 Agent 中稳定做理财说明与知识问答的场景；社区内容不构成投资建议，关键信息须以官方披露为准。

指数通（stock-index-expert）：在 Agent 里做指数行情与框架化投资分析

指数通（stock-index-expert）是 SkillHub 社区 Skill（v1.0.3，@user_545d9f52/stock-index），定位为指数投资分析助手：解读 A 股、港股、美股指数，关联财经新闻，并结合巴菲特、达利欧、林奇等 9 位大师框架给出视角；标注 requires_api_key=false。本文基于 SkillHub 官方简介与安装文档，说明能力边界、skillhub CLI 安装到 Cursor/Claude/Codex 等 skills 目录的步骤，以及自然语言典型提问方式与使用注意。

儿童心理学专家 child psychologist：为 Agent 配置儿童心理陪伴人设

儿童心理学专家 child psychologist（@user_b419ecaa/childpsychologist，v1.0.0）是 SkillHub education 类社区 Skill，通过 SKILL.md 为 Agent 配置「团团」儿童临床心理人设、四星成长流程与共情应答规则，无需 API Key。文章说明其专业定位与适用场景，给出 skillhub 安装到 Cursor 等 skills 目录的命令，并提供可复现的对话示例，并提醒非医疗服务、大包体书摘占用上下文及社区内容需自行甄别等限制。

本地知识库智能问答：用个人文档做问答、报告与向量索引

介绍 SkillHub 社区技能「本地知识库智能问答」（@user_4c392ef3/knowledge-qa，v1.0.0）。面向 PDF/Markdown/Word 等个人资料，支持基于知识库问答、生成报告与思维导图、上传索引与分区/向量库管理；触发词涵盖「基于知识库」「查一下知识库」「整理成报告」等。说明 skillhub CLI 安装到 Cursor 等 skills 目录的方法，并提示 requires_api_key 标签与安装路径注意事项。

AI Skill 跨平台同步工具：在多端 Agent 间复制 SKILL.md 技能包

介绍 SkillHub 社区 Skill「AI Skill跨平台同步工具」（@user_3c6cb52e/sync-skill-b3jf，v1.0.0）。它面向多平台 Agent 开发者，说明如何用 sync-skill 将符合 SKILL.md 格式的技能文件夹在 Claude Code、Cursor、Codex 等平台目录间复制，支持 global/project 作用域、交互选择与覆盖确认。文章给出 skillhub 安装命令、常用 skills 路径及 npx sync-skill 示例，并说明无需 API Key、Node.js 版本与模型字段需手动调整等注意点。

胡来给你算一卦：在 Agent 里接入娱乐向卜卦 Skill

胡来给你算一卦是 SkillHub 社区 life-service 类 Skill（@user_83002a29/hulai-diviation，v1.0.2，无需 API Key）。在用户说算一卦、卜卦、今日运势等词时触发，支持八卦主卦、场景卦与自定义卦三种模式，并按 SKILL.md 固定 Markdown 模板返回娱乐解读。文章说明 SkillHub CLI 安装、Cursor 等 skills 目录下的 skillhub install 命令，以及 Zip 下载与典型触发话术，并提醒仅供娱乐、随机抽取等限制。

生成会议纪要：在 Agent 里把讨论整理成纪要

SkillHub 社区 Skill「生成会议纪要」（@user_a05742e7/wgd-9527，v1.0.0）面向 office-efficiency 场景，在用户需要写会议纪要或整理讨论要点时触发，标签 requires_api_key=false。本文基于官方页面与安装文档，说明定位、可核实能力、skillhub CLI 安装命令及 Cursor/Claude Code/Codex 的 skills 目录，并给出可复现的自然语言触发示例与使用注意。

记账自动化：在对话里完成记一笔、汇总与周报

记账自动化（@user_70c2f807/expense-tracker-plus）是 SkillHub 社区 life-service 技能 v1.0.1，无需 API Key。基于 SKILL.md，支持自然语言记一笔、自动分类与纠正、日周月汇总、周报导出及预算与趋势类对话能力；数据仅在当前会话内，需定期出周报复制保存。文章说明 skillhub CLI 安装命令、Cursor/Claude/Codex 的 skills 目录及文档中的典型提示示例，并列出与企业财务、税务等不适用边界。

职场高情商回复：在 Agent 里生成得体、安全的职场表达

职场高情商回复（@user_f705b760/gqs135）是 SkillHub 社区发布的 business-ops 类 Agent Skill，v1.0.0，无需 API Key。面向领导、同事、下属、体制内与危机等 23+ 场景，帮助在 Agent 中生成得体、安全、高情商的回复。文章说明其定位与发布信息，给出按 skillhub.md 安装到 Cursor、Claude Code、Codex 等 skills 目录的命令与路径差异，并提醒社区来源内容与高风险场合需人工审阅。

游戏AI设计：为 Agent 补齐游戏 AI 工作流

游戏AI设计是 SkillHub 社区技能 @user_3c6cb52e/game-ai-sh-l82bv3（v1.0.0，分类 ai-agent），面向游戏 AI 设计场景，帮助 Agent 按 SKILL.md 高效完成相关任务，且标记 requires_api_key=false。本文基于 SkillHub 页面与官方安装文档，说明定位、可核实能力、skillhub CLI 安装命令及各客户端 skills 目录差异，并给出安装后发起领域任务的典型流程与适用注意。

财务报表分析：在 Agent 里上传报表并获取运营建议

SkillHub 社区 Skill「财务报表分析」（@user_4cdf8f25/financial-statement-analyzer，v2.10.0，professional，无需 API Key）面向上传公司财务报表后的解读与运营建设性意见。文章说明其定位、已核实功能、按 skillhub.cn 安装文档用 CLI 安装到 Cursor/Claude Code 等 skills 目录的步骤，以及典型对话用法与合规边界；高级量化指标以安装后的 SKILL.md 为准。

科研选题品味：把「感觉不错」变成可检验的选题门禁

科研选题品味（@user_a95aac1d/taste-check，v2.2.2）是 SkillHub 上的 professional 类 Agent Skill，无需 API Key。它将杨振宁、Hamming、Uri Alon、Chris Olah、Schulman 的科研品味判断落实为选题七道门、过程三道门与定期校准，输出可溯源的红黄绿判决并以反诘对照而非替你做结论。支持完整/快速选题审计与过程审计，触发语含科研品味、research-taste、科研品味 quick/process 等。安装需 SkillHub CLI，并用 skillhub install 指定 Cursor 等客户端的 skills 目录。

中医综合指南：在 Agent 里统一经方、道医与药膳知识

中医综合指南是 SkillHub 社区 Skill（@user_148deca1/tcm-comprehensive-guide，v1.0.0），整合经方医案临床实践、道医经典文献与药膳食疗养生，无需 API Key。文章说明其触发词与不适用边界，并给出按 skillhub.cn 文档安装到 Cursor、Claude Code 等 skills 目录的步骤。适合在 Agent 中整理六经辨证、方证对应、体质调理等话题，但不能替代执业医师诊断与处方。

法律文书助手：在 Agent 里做合同审查与文书起草的 Skill

法律文书助手是 SkillHub 社区 Skill（@user_70c2f807/legal-doc-assistant，v1.0.0，professional，无需 API Key）。基于 SKILL.md 约定触发词、非律师边界与四步流程，覆盖合同审查、协议起草、条款解读与常见咨询，并规定结构化输出与免责提示。文章说明 skillhub CLI 安装命令及 Cursor、Claude Code、Codex 的 skills 目录，并给出官方快速开始对话示例。

音乐歌曲评鉴师：用 Agent Skill 把听歌变成可练习的鉴赏

音乐歌曲评鉴师是 SkillHub 社区 education 类 Skill（@user_aad6add3/music-appreciation，v1.0.0），从听感到审美分层拆解旋律、节奏、音色、编曲、歌词与风格，无需 API Key。文章说明其定位与核心维度，并给出 skillhub CLI 安装命令及 Cursor、Claude Code、Codex 等 skills 目录配置要点，辅以对话触发评鉴的用法与适用边界。

三分钟读完一本书：用 Agent Skill 快速把握书籍要点

介绍 SkillHub 社区 Skill「三分钟读完一本书」（@user_41864c0f/book-3min-reading）：面向快速了解书目、摘要、读书笔记与核心观点，无需 API Key。说明核心能力、触发关键词、通过 skillhub CLI 安装到 Cursor/Claude Code 等 skills 目录的步骤，以及社区 Skill 使用时的核对与局限。

技能发现专家：在 ClawHub、skills.sh 与 SkillHub 之间选技能

技能发现专家是 SkillHub 社区 ai-agent 类 Skill，坐标 @user_28a6fb7f/skill-discovery-expert，无需 API Key。它面向 ClawHub、skills.sh、SkillHub 三大平台，按需求、网络与时效制定搜索与安装方案。文章说明其定位、核心能力、通过 skillhub CLI 或官方提示词安装到 Cursor 等目录的方法，以及「找技能」「推荐技能」等触发式用法与使用注意。

金融决策：在 Agent 里固定宏观与个股分析输出结构

金融决策是 SkillHub 社区 Skill（@user_06ad406b/finance-record-qhj，v1.0.0，professional，无需 API Key）。通过锦鲤经济师角色约束宏观、估值、半导体标的与仓位管理话术，并按核心要点、详细拆解、具体行动、信心指数四段输出，结尾要求不构成投资建议。文章说明安装命令、Cursor 等 skills 目录及可复现的对话触发示例，并提醒无行情接口、需自行核实数据。

网文自检大师：用 Agent Skill 做稿件错误与合规自检

网文自检大师是 SkillHub 社区 content-creation 类 Agent Skill（@user_24c2df14/novel-self-check，v1.0.0），面向网文作者，用于快速排查文本错误、规避平台违规风险并提升过审率。技能登记 requires_api_key=false。本文基于 SkillHub 官方简介与安装文档，说明技能定位、可核实功能、通过 skillhub CLI 或 AI 提示安装到 Cursor/Claude Code/Codex 等 skills 目录的步骤，以及分章提交文稿进行自检的典型用法与合规边界。

论文速读：用 Agent Skill 把学术论文拆成结构化摘要

论文速读是 SkillHub 社区 Skill（@user_70c2f807/paper-speed-reader，v1.0.0，knowledge-management），由 user_70c2f807 发布，无需 API Key。它在用户粘贴论文文本后，按 SKILL.md 流程提取研究问题、方法、发现、贡献与局限，支持通俗解释与多篇对比，并输出固定模板的速读报告；不处理 PDF 直读、论文写作、文献综述撰写或查重。文章说明 SkillHub 安装方式、Cursor/Claude Code/Codex 常见 skills 目录及典型对话用法。

学术写作词库：章节模板、短语库与过渡词

介绍 SkillHub 社区 Skill「学术写作词库」（@user_8d26dabd/academic-writing-bank，v2.0.9）。它通过 SKILL.md 与 references 提供八章段落骨架、六类中英短语、100+ 过渡词及中文规范与避坑指南，并明确不代写完整段落。文章说明 skillhub CLI 安装命令、Cursor 等 skills 目录路径，以及文献综述开头、实验结果表达等典型对话用法与学术伦理边界。

《Cursor Docs》-Rollouts

Rollouts monitors each pull request from review to production. It writes a rollout plan when the pull request opens, checks the change against your telemetry after it deploys, and reports its health in every environment.

《Cursor Docs》-Cursor web release notes

Weekly changes to Cursor on the web, from integrations and admin settings to automations, the APIs, security and approval agents, and models. Each entry covers one week and is labeled with the Monday that starts it. Cloud Agents and Bugbot have their own pages.

《Cursor Docs》-Cursor SDK release notes

The latest features, improvements, and fixes shipping to the Cursor SDK, covering @cursor/sdk on npm and cursor sdk on PyPI.

《Cursor Docs》-Origin CLI release notes

New features, improvements, and fixes in the Origin CLI. Each entry covers one release and is labeled with its release date. Changes to Origin on the web and in the API are in the Origin release notes.

《Cursor Docs》-Origin release notes

Weekly changes to Origin on the web and in the Origin API. Each entry covers one week of changes and is labeled with the Monday that starts it. Endpoint level API changes are in the Origin API changelog.

《Cursor Docs》-Cursor mobile release notes

New features, improvements, and fixes in Cursor for iOS. Each entry covers one app version.

《Cursor Docs》-Cursor IDE release notes

New features, improvements, and fixes in the Cursor IDE. Each entry covers one minor version, including the patch releases that follow it. Changes to the Agents Window have their own page.

《Cursor Docs》-Cloud Agents release notes

Weekly changes to Cloud Agents. Each entry covers one week of changes and is labeled with the Monday that starts it.

《Cursor Docs》-Bugbot release notes

Weekly changes to Bugbot. Each entry covers one week of changes and is labeled with the Monday that starts it.

《Cursor Docs》-Agents Window release notes

New features, improvements, and fixes in the Agents Window. The Agents Window ships with the Cursor app, so each entry covers one minor version, including the patch releases that follow it. Editor changes are in the Cursor IDE release notes.

《Cursor Docs》-Release notes

Every Cursor product in one timeline, newest first, with up to 10 recent releases each. Filter by product, open a product's page for its full history, or follow along with the RSS feed.

《Cursor Docs》-Code Tours

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Set up CloneKit in CI with `origin repo clone-fast`

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Publish to the App Marketplace

The Origin API reference covers authentication, installation, scopes, and webhooks.

《Cursor Docs》-Build an Origin App

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Origin Apps

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Agents and automations

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Muse Wonder

Teams and Enterprise admins who configured model access before Meta was available need to enable the Meta provider before Muse Wonder appears for their members.

《Cursor Docs》-Grok 4 7

Grok 4.7 is a frontier model from Cursor and SpaceXAI for coding and knowledge work. It builds on Grok 4.6 with a larger base, longer training on harder multi hour tasks, and stronger self verification.

《Cursor Docs》-Glm 5 3 Flash

GLM 5.3 Flash is the smaller, faster member of Z.ai's GLM 5.3 family. It supports image inputs, a 1M token context window, and three reasoning levels (Low, High, and Max), with High as the default. Add it to the model picker from Cursor Settings Models . For higher quality on harder tasks, use GLM 5.3.

《Cursor Docs》-Glm 5 3

GLM 5.3 is Z.ai's latest open weight coding model and the successor to GLM 5.2. It supports a 1M token context window and three reasoning levels (Low, High, and Max), with High as the default. Add it to the model picker from Cursor Settings Models . For a faster, lower cost option from the same family, see GLM 5.3 Flash.

《Cursor Docs》-Gemini 4 Argon

Gemini 4 Argon is Google's frontier Gemini model. Use it for complex, multi step coding work that benefits from deeper reasoning and a large context window.

《Cursor Docs》-Gemini 3 5 Flash Lite

This model is used only by the Auto review classifier inside Cursor. It isn't selectable as a chat or agent model.

《Cursor Docs》-Claude Sonnet 5 5

Claude Sonnet 5.5 is Anthropic's latest medium tier model and the successor to Sonnet 5. It scores 55.5% on CursorBench at max effort, second only to Opus 5.5. It keeps Sonnet 5's input and output rates and halves the cache read rate. Add it to the model picker from Cursor Settings Models .

《Cursor Docs》-Claude Opus 5 5

Claude Opus 5.5 is Anthropic's latest Opus model and replaces Opus 5. It sets a new high score on CursorBench, ahead of Fable 5.1, and costs 20% less than Opus 5 per token. We recommend the high thinking variant for the best results.

《Cursor Docs》-Claude Haiku 5 5

Claude Haiku 5.5 is the fastest model in Anthropic's Claude 5.5 family and the successor to Claude 4.5 Haiku. It scores 48.4% on CursorBench at max effort, on the same cost performance curve as Sonnet 5.5 and Opus 5.5, at a tenth of Haiku 4.5's per token price for requests up to 100k input tokens. Add it to the model picker from Cursor Settings Models .

《Cursor Docs》-Deploy Grok Bot to your organization

Your IT team installs the Grok Bot desktop app on member devices with the tools it already uses for other software: download a versioned installer, push it, and decide when devices move to a new release. Dashboard controls for turning Grok Bot on and scoping access are on Grok Bot for Teams and Enterprise, and deploying the Cursor editor is covered in Deployment patterns.

《Cursor Docs》-Manage Grok Bot computers

Each member of your team gets one hosted computer where every Bot they run does its work. Manage Member Computers and Data , under Security & Compliance on the Grok Bot page of the Cursor dashboard, lets organization admins recreate or terminate computers across many members at once, or delete all of a member's Grok Bot data. Terminate Inactive Computers , under Bot Computers , turns on automatic termination for computers that go 30 days without use. For the rest of the admin controls, see Grok Bot for Teams and Enterprise.

《Cursor Docs》-Tenancy Restriction

Your network can limit which Cursor organizations and teams a request may use. Do that by adding one HTTP header on traffic to Cursor. Cursor never sets this header, and the dashboard has no switch for it. If the header is absent, Cursor applies no restriction from this mechanism.

《Cursor Docs》-Origin Migration API

Origin is in Early Beta and subject to change. Review the OpenAPI specification when updating an integration.

《Cursor Docs》-Origin MCP tool reference

Every tool the Origin MCP server at https://api.origin.cursor.com/mcp lists, in listing order. Parameters are the JSON Schema clients receive from tools/list.

《Cursor Docs》-Origin MCP

Origin is in Early Beta and subject to change.

《Cursor Docs》-Origin Grants API

Origin is in Early Beta and subject to change.

《Cursor Docs》-Origin API Changelog

The Origin API is in Early Beta and subject to change. Review the OpenAPI specification when updating an integration.

《Cursor Docs》-Acting on behalf of users

Origin is in Early Beta and subject to change.

《Cursor Docs》-Cursor Origin API

Early Beta reference for the Cursor Origin API. Origin is Cursor's code forge; its public REST API lets apps and tools work with Origin repositories, commits, checks, pull requests, apps, and installations.

《Cursor Docs》-Projects

A Project takes on a larger body of work, such as a feature, a migration, or a full app. You direct it by chatting with its coordinator agent. The coordinator doesn't write code itself. It plans the work, delegates it to agents that write the code, and brings the finished work back to you to check. Projects live in the left hand nav of the Agents Window and run on Cloud Agents.

《Cursor Docs》-Legacy Cursor plans

Legacy Cursor plans are the plans Cursor sold before The X Subscription: Hobby, Start, Pro, Pro+, Ultra, and Teams with Standard and Premium seats. They keep working as they are. New customers start on The X Subscription, and this page is for anyone still on a legacy plan who wants to know how it works and how it compares.

报销整理：用 Agent Skill 处理差旅票据与报销清单

报销整理（@user_c0c19625/baoxiao-tby）是 SkillHub 社区 business-ops 类 Skill，v1.0.1，用于差旅费用整理、票据处理、机票折扣计算与报销清单生成，无需 API Key。文章说明其定位与核实功能，并给出 skillhub CLI 安装命令及 Cursor、Claude Code 等 skills 目录配置要点，典型用法为在对话中描述报销需求并由 Agent 按 SKILL.md 执行。适用经常出差、已在编码助手中使用 Skills 的用户；提交前仍需人工复核财务规则。

gbt-code-audit：按国标做 Agent 代码安全审计

gbt-code-audit（@user_9b59adcf/zzcp-gbt-code-audit，v2.0.4）是 SkillHub 社区 dev-programming 类 Skill，依据 GB/T 34943/34944/34946/39412 对 Java、C/C++、C#、Python 等源码做安全审计。采用快速扫描（正则及可选 Gitleaks、Bandit、Semgrep）与 LLM 深度审计双引擎，经 finalize_report 去重校验后输出国标映射的 Markdown 报告。无需 API Key，通过 skillhub install 安装到 Cursor 等 Agent 的 skills 目录即可按 SKILL.md 工作流使用。

全流程测试专家：面向接口文档的公司级测试 Skill

全流程测试专家（@user_24dd3388/full-flow-testing）是 SkillHub 社区发布的 dev-programming 类 Skill，定位为公司级接口测试助手。支持开发自测、单接口全面测试、业务流程测试、安全审计、缺陷定位与报告生成六种模式，可自动理解接口文档并沉淀知识库，每步需确认后执行，并支持多用户会话隔离。本文基于官方页面与 SkillHub 安装文档，说明能力边界、skillhub CLI 安装方式及在 Cursor 等客户端下的 skills 目录配置，不编造未公开的用法与案例。

改代码专家：把 Agent 拉进结构化代码审查流程

改代码专家（@user_f2e0c902/asddsawwqewq）是 SkillHub dev-programming 类社区 Skill v1.0.0，无需 API Key。安装 SKILL.md 后，在用户贴代码并提出审查、找 bug、优化或检查质量时，按规范可读性、逻辑错误、性能与安全四维输出 Markdown 审查报告。本文说明定位、能力与 skillhub install 安装路径，并提醒其本质是审查工作流而非自动改库。

AI打工人办公助手.skill：把日常办公流程收进一个 Skill

AI打工人办公助手（@user_ae5129cb/aidagongrenbangong，v1.0.0）是 SkillHub 社区办公效率类技能，帮助标准化文案、海报、PPT、Word、Excel 等日常工作，并支持标杆风格学习与任务管理。本文基于官方简介与 SkillHub 安装文档，说明定位、核心能力、skillhub install 与 Cursor 等客户端 skills 目录配置，以及按官方触发场景使用时的注意点；标签 requires_api_key=false。

日报助手：把零散工作记录整理成结构化日报

日报助手（@user_4efd104e/day-report）是 SkillHub 社区办公效率类 Skill，版本 1.0.0，无需 API Key。通过 SKILL.md 约定写作原则与固定栏目，将口语化工作记录、任务清单或转写文本整理为含今日完成、核心产出、后续计划及可选风险的日报。文章说明 skillhub CLI 安装命令、Cursor/Claude Code/Codex 的 skills 目录，并给出官方 few-shot 示例与适用边界。

图片处理专家：在 Agent 里用自然语言完成常见图片任务

「图片处理专家」（@user_92725383/image-processor-expert，v1.0.0）是 SkillHub 社区 design-media 类 Skill，无需 API Key。支持压缩、裁剪、旋转、格式转换、水印、批量处理及二维码/条形码生成，适合在 Cursor、Claude Code 等 Agent 中用自然语言完成常见配图任务。文章说明其定位与触发词，并给出基于 skillhub.cn/install/skillhub.md 的 CLI 与提示词安装方式及典型对话示例。

翻译小助手：自动判向的图文翻译 Skill

翻译小助手（@user_674c7529/ttk5835-1）是 SkillHub education 类社区技能，自动识别语种并按固定规则翻译：中文译英文，英/日/韩/法/德/西班牙语译中文。支持文本直译与图片 OCR 后对照输出原文与译文，交互强调只给结果、少反问。requires_api_key=false。安装需 skillhub CLI，并用 --dir 指向 Cursor 等 Agent 的 skills 目录。适合文档对照与截图外文处理，专业术语仍需人工校对。

AI 法律合同审查：在 Agent 里做中文合同风险审查

介绍 SkillHub 社区 Skill「AI 法律合同审查」（@user_1a470ba8/workbuddy-contract-review，v6.0.1）。面向买卖、技术、租赁、劳动等中文合同，提供风险识别、关键信息提取与审查报告；v5.x 起含法条与指导案例溯源、谈判辅助、双语及日韩审查、金额校验、台账履约、档案检索与类案参考。说明 skillhub 安装路径、API Key 要求及适用场景与合规注意。

网页搜索技能：为 Agent 补上可触发的网页检索与汇总

介绍 SkillHub 社区技能「网页搜索技能」（@user_c5d687fe/web-search-skill-v2，v1.0.0）。说明其通过「搜索」「查一下」等自然语言触发网页搜索并汇总结果，标注 requires_api_key=false。给出 skillhub CLI 安装步骤、Cursor/Claude Code/Codex 的 skills 目录与 install 命令示例，并说明适用场景与安装路径注意事项。

全网热搜 Skill：聚合 56+ 中文平台热榜查询

SkillHub 技能「全网热搜-聚合56+热榜数据」（@user_82aab149/dailyhot-skill，v1.0.0）面向知乎、微博、B站、抖音等 56+ 中文平台，通过 SKILL.md 约定在用户提及热点/热榜/热搜/汇总时由 Agent 触发查询。支持单平台 query-hot 脚本、关键词筛选与多平台并行汇总；需 Node 20+、npm install 并启动 localhost:6688 本地服务，无需 API Key。本文说明 SkillHub 安装路径、Cursor/Claude Code/Codex skills 目录及典型自然语言与命令行用法。

SKILL.md 模板生成器：为腾讯 SkillHub 一键产出标准技能文件

社区 Skill「SKILL.md模板生成器·腾讯SkillHub专用」（@user_a41ae6c8/skill-md-template-maker，v1.0.0）面向在腾讯 SkillHub 上架技能的开发者：根据需求描述生成可复制的完整 SKILL.md，无需 API Key。文章说明其定位、安装方式（skillhub CLI 与 --dir 目录）、典型对话用法，以及适用场景与上架前需自行核对的事项，并给出官方 SkillHub 页面与安装文档链接。

演讲稿生成：按主题与时长产出完整讲稿结构

演讲稿生成是 SkillHub 社区 Skill（@user_70c2f807/speech-script-generator，v1.0.0，content-creation）。根据主题与时长生成含开场、正文、结尾和金句的完整演讲稿，标签 requires_api_key=false。文章说明定位、核心能力、通过 skillhub CLI 安装到 Cursor 等 Agent skills 目录的步骤，以及典型调用方式与使用注意。

全科老中医：在 Agent 里接入中医全科健康顾问能力

全科老中医是 SkillHub 社区 professional 类 Skill（@user_ad872d55/chinese-medcine，v2.1.1），无需 API Key。提供对话问诊、体检报告解读、体质辨识、量化药膳食疗、外治法指导，支持专业/科普双轨与企微格式，框架参考《黄帝内经》《伤寒论》。本文说明定位、能力与 skillhub 安装到 Cursor 等客户端 skills 目录的步骤，并提示社区健康顾问非医疗诊断替代。

玮德工程造价助手：企业版 SkillHub 造价领域 Agent 技能

玮德工程造价助手（@weidecost/weide-cost-assistant）是 SkillHub 上由玮德工程造价发布的企业源 professional 类 Agent Skill，当前版本 1.1.2，无需 API Key。文章基于 SkillHub 页面与安装文档，说明其定位、公开资料中的能力线索、skillhub CLI 安装命令及 Cursor/Claude Code/Codex 的 skills 目录，并提醒与社区衍生包区分及专业审核责任。

联网搜索助手：在 Agent 里按需联网检索

联网搜索助手是 SkillHub 社区技能 @user_93e1e6e4/web-search-assistant（v1.0.0），用于检索新闻、实时数据与资料，标签 requires_api_key=false。本文说明其定位、能力与适用边界，并给出基于 skillhub CLI 的安装命令及 Cursor 等客户端 skills 目录。典型用法为对话中使用「用 web-search 查一下…」触发检索，适合查热点与找资料，不用于常识问答、闲聊或代写文章。

20位投资大师帮你做股票分析：在 Agent 里做多视角股票研判

SkillHub 社区 Skill「20位投资大师帮你做股票分析」（@user_7f864702/investmentguru，v1.0.2）将 7 位中国与 13 位国际投资人框架、腾讯财经与 yfinance 行情抓取、多维度报告及 Agent 对话触发写入 SKILL.md 与 Python 包。本文基于官方页面与 v1.0.2 包内容，说明数据抓取、智能匹配大师、对比分析与 CLI/API 用法，并给出 skillhub install、Zip 下载与 pip install -e . 的安装步骤及 Cursor/Claude/Codex skills 目录要点。requires_api_key 为 false；使用前须自行核验行情与结论，输出不构成投资建议。

AI 自我复盘：把每日回顾交给 Agent Skill

AI 自我复盘（@user_fe828a0e/self-reivew-pro）是 SkillHub 社区 ai-agent 类 Skill，用于每日复盘、深度洞察与方法提炼。用户说「复盘」「自我复盘」「每天回顾」时触发，也可在每天 22:00 通过定时任务运行；标签 requires_api_key=false。本文说明定位、核实功能、skillhub CLI 安装到 Cursor 等 skills 目录的步骤，以及对话与定时两种典型用法与注意事项。

印象笔记官方 Skill：让 AI 助手直连个人知识库

印象笔记官方 Skill（@yinxiang/yinxiangskill，v1.0.4）由印象笔记发布，让 OpenClaw、Claude Code、Cursor、Codex、WorkBuddy 等客户端在授权后通过对话保存笔记与网页剪藏，按关键词、标签、笔记本与时间搜索，并支持改标题正文、移动笔记与整理笔记本。本文说明其定位、已核实功能，以及按 SkillHub 文档用 skillhub install 安装到各客户端 skills 目录的步骤与典型自然语言用法。

小游戏开发专家：把抽象玩法需求落成可玩的小游戏

小游戏开发专家（@user_f52ec6c7/gamemaker）是 SkillHub 社区 dev-programming 类 Skill，v1.0.0，无需 API Key。它将抽象需求转化为可玩的 2D/3D 小游戏，覆盖闭环设计、状态管理、碰撞检测、粒子特效与代码调试。文章说明其定位与核心能力，并给出按 skillhub.cn 安装文档启用 CLI、用 --dir 安装到 Cursor 等 skills 目录的步骤，以及与官方简介一致的任务提示示例。

学术论文工作坊：一键装齐 14 个学术 Skill

学术论文工作坊（@user_8d26dabd/academic-paper-workshop，v2.3.8）是 SkillHub 上的 professional 类社区技能，面向写论文时需要多种 Agent 能力的场景：一次安装 14 个学术相关 Skill，并自动检测技能目录中的缺失项并补全。本文基于 SkillHub 页面与官方安装文档，说明定位、核实功能边界、给出 skillhub CLI 与 Cursor 等客户端的 skills 目录安装方式，以及启用后的典型对话步骤与注意事项。

前端设计优化 skill：用 Agent Skill 做 UI/UX 八维审查

介绍 SkillHub 社区 Skill「前端设计优化 skill」（@user_8ec29dbe/frontend-design-optimizer，v1.0.1）。面向功能已通但观感与体验欠佳的前端页面，从视觉层次、排版、色彩、响应式、交互、动效、无障碍与性能八个维度组织优化与审查，无需 API Key。说明社区来源、design-media 分类及官方安装路径（skillhub CLI 与 --dir），并给出在 Cursor 等客户端中的典型启用方式。

小说写作全流程技能：把 Agent 小说创作收成可执行工作流

介绍 SkillHub 社区 Skill「小说写作全流程技能」（@user_fa4109f3/novel-writing-new，v6.0.0）。说明其用 SKILL.md 固化剧本转小说、逻辑核查、去重与字数控制等流程，以及 12 层体系与 references 索引。给出 skillhub CLI 安装命令、Cursor 等客户端 skills 目录与可复现的对话用法示例；标注无需 API Key、社区来源与使用注意。

旅行攻略大师丨travel-planner：把出行对话落成按小时可执行的行程

旅行攻略大师（@user_8e413e07/travel-planner-max）是 SkillHub 社区 life-service 类 Skill，无需 API Key。它在用户出现旅行、X 日游、周末去哪等意图时，引导 Agent 输出精确到小时的行程，并尽量包含真实店名、地址、营业时间、人均、景点开放时间与游览时长。文章说明其定位、触发范围，以及通过 SkillHub 提示词或 skillhub CLI 安装到 Cursor 等客户端 skills 目录的步骤，并给出可复现的对话示例与使用注意。

可转债投资导航图：把兰色体系装进 Agent Skill

可转债投资导航图是 SkillHub 上基于兰色可转债投资书籍提炼的 professional 类 Skill（v5.5.2，@user_e2ff9e78/cn-investment-navigation-map），涵盖三线复式投资法、安全弹性双原则、分散持仓、两个价值锚点、打新策略及下修与强赎等触发场景，哲学为保本第一。本文说明其定位与核心能力，并给出按 skillhub.cn 安装文档使用 CLI 安装到 Cursor、Claude Code、Codex 等 skills 目录的步骤，以及典型提问方式与合规注意。无需 API Key。

微信小游戏助手：在 AI 编程环境里安装微信小游戏开发 Skill

微信小游戏助手（@tencent-adm/weixin-minigame-helper）是微信小游戏团队在 SkillHub 发布的 dev-programming 类 Skill，简介为微信小游戏开发工具包，版本 v1.0.2，无需 SkillHub API Key。文章说明其定位与发布信息，并给出官方安装提示词、skillhub CLI 安装命令及 Cursor 等客户端的 skills 目录路径，提醒具体能力以 SKILL.md 为准。

代码解释器：用 Skill 把陌生代码讲清楚

代码解释器是 SkillHub 社区 Skill @user_70c2f807/code-explainer（dev-programming，v1.0.0），帮助开发者理解陌生代码逻辑：解释功能、标注关键行、指出潜在问题，无需 API Key。文章说明其定位与核心能力，并给出基于 skillhub.cn/install/skillhub.md 的 CLI 安装步骤、Cursor 等客户端 skills 目录，以及通过对话触发解释的用法与适用注意。

头脑风暴：在写代码前先厘清意图与方案

SkillHub 社区 Skill「头脑风暴」（@user_142af50a/brainstorming-v2，v1.0.0）要求 Agent 在创建功能、组件或修改行为前先探索用户意图、需求与设计。本文介绍其定位、核心约束、基于 skillhub CLI 的安装方式（含 Cursor 等 skills 目录），以及典型使用节奏与注意事项。无需 API Key。

商业分析超级工作台：把 BABOK 与咨询方法论装进 Agent Skill

商业分析超级工作台（Business Analysis Super Workbench）是 SkillHub 社区 Skill @user_82981261/ba-workbench，v2.0.0，professional 分类，无需 API Key。它将 IIBA BABOK V3、PMI-PBA 与咨询方法论等收敛为 14 阶段分析链路，覆盖 100+ 框架、50+ 交付物声明与 8 种 BA 角色，并列出中英文触发词。文章说明定位与核心能力，给出 skillhub CLI 与 Cursor/Claude Code/Codex 的 skills 目录安装方式，以及按阶段、交付物与角色发起对话的用法，并提醒社区来源与数据需人工校验。

尾盘选股法：在对话里按多维度筛沪深股票

尾盘选股法是 SkillHub 社区 professional 技能 @user_323d092a/stocks-fliter（v1.0.2），从沪市、深市按量比、流通市值、换手率、涨幅、均线多头排列、成交量台阶式上升等约 10 维度做两阶段筛选，requires_api_key=false。文章说明其定位、能力与安装方式：通过 skillhub install 并 --dir 指向 Cursor、Claude Code、Codex 等 skills 目录，或在对话中按官方提示词引用 skillhub.cn 安装文档；典型用法为自然语言描述筛选条件由 Agent 执行。附适用场景与投资风险提示，并给出官方 SkillHub 页面与 API 坐标。

Arshis-游戏策划-全流程：面向全生命周期的游戏设计 Skill

Arshis-游戏策划-全流程（@user_b167603f/game-plan，v2.5.1）是 SkillHub 社区 professional 类 Skill，无需 API Key。支持设计文档生成、审查建议、世界观管理、数值设计与需求文档，并宣称可辅助开发流程与趋势规划，覆盖技术策划与 AI 开发策划。本文基于官方页面说明安装方式：SkillHub CLI 与 skillhub install，并区分 Cursor、Claude Code、Codex 的 skills 目录，供策划与独立开发者选用。

PPT大纲自动生成器：从主题到可执行的大纲结构

PPT大纲自动生成器是 SkillHub 社区 Skill（@user_1636f9a8/ppt-outline-generator，v1.0.0，office-efficiency），输入主题即可生成完整规范的 PPT 大纲，覆盖课堂汇报、工作汇报、答辩、产品介绍、活动方案等场景，且 requires_api_key=false。本文说明其定位、能力与触发语，并依据 skillhub.cn 安装文档给出 CLI 检查、安装命令及各 Agent skills 目录要点，附可复现的对话示例与使用注意。

恋爱导师童锦城：在 Agent 里用「童锦程视角」做关系与人际分析

恋爱导师童锦城是 SkillHub 社区 life-service 类 Skill（@user_9b440ffa/skill-tongjincheng-main，v1.0.0，无需 API Key），内容搬运自 GitHub skill-tongjincheng。安装后通过「童锦程」「深情祖师爷」等触发词，以五个心智模型与九条决策启发式分析恋爱、人际与个人成长问题，并标明商业场景与替代本人等边界。本文说明定位、能力、SkillHub CLI 安装路径及典型对话用法。

敏感信息检测与可逆脱敏工具：在 Agent 对话链路里做强制隐私保护

介绍 SkillHub 社区 Skill「敏感信息检测与可逆脱敏工具」（@user_cf24022c/sensitive-detector v2.0.1）：对手机号、身份证、银行卡等文本做可逆脱敏，本地 OCR 检测图片并拒绝处理，拦截绕过意图，支持最长一天的临时禁用。无需 API Key。文章说明定位、四项核心能力、基于 skillhub CLI 的安装路径（含 Cursor 等目录），以及适用场景与使用注意，并附官方页面与安装文档链接。

java代码检查工具：在 AI 对话里做 Java 代码审查

java代码检查工具（@user_1ee8e350/java-check-tool，v1.0.3）是 SkillHub 社区发布的 dev-programming 类 Skill，定位为 Java 代码检查与审查助手，适用于代码审查、Bug 分析、安全漏洞提示、性能优化建议与质量评估，无需 API Key。文章说明其能力边界、skillhub CLI 与 AI 提示词两种安装方式，以及 Cursor 等客户端的 skills 目录配置，并提醒审查结果需与测试及专业扫描工具配合使用。

中医理论智能体：在 Agent 里按七大体系做辨证与理论解释

介绍 SkillHub 社区技能「中医理论智能体」（@user_3299a8e6/tcm-theory，v1.0.0）。技能覆盖阴阳五行、脏腑、气血津液、经络、病因病机、四诊与辨证论治，适用于概念讲解、病机分析、舌脉解读、方剂方向与中西医对照等场景，且无需 API Key。文章说明通过官方提示词或 skillhub CLI 安装到 Cursor、Claude Code、Codex 等 skills 目录的方法，并提醒社区技能仅作理论辅助、不能替代临床诊疗。

skillhub-skill：在 Agent 项目里用 SkillHub 装技能

skillhub-skill（@user_11b15315/skillhub-skill，v1.0.1）是 SkillHub 商店上的 ai-agent 类 Skill，简介为 Skillhub 官方安装用版本，无需 API Key。它配合 skillhub CLI 与 skillhub.md，指导 Agent 检查 CLI、搜索商店技能，并用 --dir 安装到 Cursor、Codex、Claude Code 等客户端的 skills 目录，避免默认 ./skills 无法加载。文章说明官方安装命令、典型工作流与适用场景，数据以 SkillHub 页面为准。

前端设计：用 Skill 约束 AI 做现代界面

SkillHub 社区 Skill「前端设计」（@user_e07fe912/frontend-design-v2，v2.0.0）将专家级前端设计指引写入 SKILL.md，适用于落地页、仪表盘及通用界面，且无需 API Key。文章说明其定位、已公开能力边界，并给出 skillhub CLI 安装命令、Cursor 等客户端 skills 目录及官方对话安装提示。适合用 Agent 写前端但希望视觉更统一的开发者；注意 --dir 路径与社区维护节奏。

高情商回复：用 Agent Skill 润色社交与婚恋聊天

高情商回复是 SkillHub 社区 Skill（@user_29dc410e/self-higheq，v1.0.0，business-ops），面向陌陌、探探、微信、QQ 等社交婚恋场景，支持温柔高情商、甜妹、御姐、搞笑沙雕等多人设辅助搭讪与润色。requires_api_key=false。本文说明其定位、核心能力，以及按 skillhub.cn 文档用 CLI 安装到 Cursor、Claude Code、Codex 等 skills 目录的步骤与典型对话用法，并提醒合规与人设选择注意点。

记忆使用技能：用文件与流程约束 Agent 的持久上下文

介绍 SkillHub 社区 Skill「记忆使用技能」（@user_7d16a562/context-memory-pro，v1.0.2）。它通过文件系统与规则流程实现持久记忆，核心为任务开始判断、读取记忆、执行、保存，适合频繁切换话题的 AI 协作。文章说明定位、能力、SkillHub CLI 安装路径（含 Cursor 等目录）及使用注意，数据以官方页面与抓取资料为准，无需 API Key。

长篇小说创作助手：在 Agent 里做网络小说创作与续写

SkillHub 社区技能「长篇小说创作助手」（@user_6d3be094/full-length-novel-writer，v1.0.4）面向网络小说创作：新建作品、续写与创作讨论。分类 content-creation，无需 API Key。可通过 skillhub CLI 安装到 Cursor、Claude Code、Codex 等 skills 目录。本文基于官方简介与 SkillHub 安装文档说明定位、能力与安装步骤，并给出与触发条件一致的自然语言用法示例。

50个免费api：把常用开放接口收进 Agent Skill

SkillHub 社区 Skill「50个免费api」（@user_29dc410e/free-api-50，v1.0.1）将天气、快递、IP 定位、A 股行情、翻译、OCR、二维码等数十类免费开放能力整理为 Agent 可遵循的指引，标签标明 requires_api_key=false。文章说明其定位与能力清单，并给出按 skillhub.md 的提示词安装与 CLI 安装命令（含 Cursor、Claude Code、Codex 的 skills 目录），以及可复现的自然语言试用方式与使用注意。

合同智能助手：在 Agent 里跑通合同起草与审查

合同智能助手（@user_ef64daef/hetongzhushou，v1.0.1）是 SkillHub 社区 professional 类 Skill，集合同生成、审查与管理于一体，支持 100+ 模板、AI 起草、风险与合规审查、条款建议、Word 导出与存档；requires_api_key=false。本文说明其定位、核实功能、按 skillhub.md 与 CLI 安装到 Cursor/Claude Code 等 skills 目录的方式，以及典型对话用法与法务审核等注意事项。

提示词炼金术：用四元蒸馏框架改写 Prompt

介绍 SkillHub 社区 Skill「提示词炼金术」（@user_83d7fe7a/prompt-alchemist，v1.0.4）。它融合 Goodside、涂津豪、Schulhoff、李继刚等方法论，按诊断→结构→思考→压缩四步输出蒸馏版提示词；说明 skillhub CLI 安装命令、Cursor/Claude Code/Codex 的 skills 目录、触发语与不适用场景（非改 Prompt、纯聊天、代码调试），并给出典型使用方式与官方链接。

A股股票分析系统：在 Agent 里用自然语言查 A 股

A股股票分析系统是 SkillHub 社区 Skill（@user_daa4eabf/stock-analyzer，v1.0.0），安装后可用股票代码或名称发起分析，示例为「请分析一下寒武纪」，数据来自腾讯/新浪财经，无需 API Key。文章说明定位、核心能力、skillhub CLI 与提示词安装方式、典型用法及适用边界。

skill-assistant 使用助理：围绕真实任务管理 WorkBuddy Skill

介绍 SkillHub 上架的 WorkBuddySkill使用管理指南（@org-gv4zgi7j/workbuddy-assistant，v6.8.1）。说明其作为 skill-assistant 使用助理的定位：围绕真实任务完成 Skill 的选择、安装、调用、组合与维护；给出 skillhub CLI 安装命令、Cursor/workbuddy 等 skills 目录约定，以及通过官方提示词或对话复现的用法；并注明 requires_api_key=false 与 SkillHub 统计来源。

设计大师：在 Agent 里做 UI/UX 诊断与设计系统协作

设计大师是 SkillHub 社区 Skill @user_ad872d55/design-master（v2.2.0，design-media），融合 UI/UX、网页设计评价、美学、VI 与设计系统管理，可诊断「页面看着怪」根因；无需 API Key。文章说明定位、触发词、SkillHub CLI 与提示词安装方式及 Cursor 等 skills 目录，并给出基于官方简介的可复现对话用法。

全栈开发伴侣：按项目类型自动切换开发流程的 Skill

全栈开发伴侣（@user_8a92847d/fullstack-companion）是 SkillHub 社区 dev-programming 类 Skill，v1.0.0，无需 API Key。它自动检测工作区偏前端、后端或全栈，路由到对应开发模式，并内置后端开发、前端开发与代码规范三套子流程。文章说明定位、能力边界，以及通过 skillhub CLI 安装到 Cursor、Claude Code、Codex 等 skills 目录的步骤与典型使用方式，并给出官方页面与安装文档链接。

公文写作：把党政公文技法装进 Agent Skill

SkillHub 社区 Skill「公文写作」（v3.2.8，professional）将党政公文写作技法整理为 SKILL.md，含 15 种法定公文模板、事务公文要点、语言规范、修改七步法、领导讲话稿指导、AI 写作适配、自检清单、易错点手册与 AI 润色工作流；无需 API Key。文章说明定位、核实功能、按 skillhub.md 与 CLI 安装到 Cursor/Claude Code 等 skills 目录，并给出可复现的对话用法与适用注意。

公众号爆款写作台：从选题到排版的公众号内容生产 Skill

公众号爆款写作台（@davtime/wechat-writer-pro，v1.0.1）是达维在 SkillHub 发布的企业来源内容创作 Skill，覆盖选题、风格、结构、正文、去 AI 味、排版、配图封面与 SEO 变现等环节，支持投喂素材重组与给定命题创作，无需 API 密钥。本文说明其定位、核心能力，以及按 skillhub.md 使用 CLI 安装到 Cursor 等客户端 skills 目录的步骤与两种典型用法，并提示安装路径与版本查阅事项。

表格使用技能：以电子表格为输入输出的 Agent Skill

表格使用技能（@user_90d58900/excel01）是 SkillHub 社区 office-efficiency 类 Skill，无需 API Key。它规定当 .xlsx、.xlsm、.csv、.tsv 为主要输入或输出时 Agent 应启用：读写修复、新建、格式转换与脏数据整理；交付物非表格时不触发。文章说明定位、能力边界，以及按 skillhub.md 用 skillhub install 安装到 Cursor、Claude Code、Codex 等 skills 目录的步骤与典型对话触发方式。

前端美化：用 Agent Skill 做有辨识度的生产级界面

「前端美化」是 SkillHub 社区 Skill（@user_c6f1a0f0/114514，v1.0.0，dev-programming），通过 SKILL.md 引导 Agent 在搭建网站、落地页、仪表盘、React 组件或美化 Web UI 时，输出有辨识度、可交付的前端代码，并强调避免 generic AI aesthetics。无需 API Key。本文介绍定位、能力、基于 skillhub CLI 的安装路径（含 Cursor 等 skills 目录）及与官方简介一致的使用方式。

多语种翻译（支持语音）：在 Agent 里覆盖二十余种语言的翻译能力

SkillHub 社区 Skill「多语种翻译（支持语音）」（@user_29dc410e/all-translate，v1.0.0）面向在 Cursor 等 Agent 中处理多语言文本的场景，简介覆盖英日韩法德阿西俄葡意泰越印荷希瑞捷波马哈高老蒙维吾尔等语种，标签 requires_api_key=false。本文说明其定位、能力边界，并按 skillhub.cn 安装文档给出 CLI 检查、install 命令及 Cursor/Claude Code/Codex 的 skills 目录示例，典型用法为对话内指明语种与待译内容。

obsidian Skill：把 Obsidian 笔记库当作磁盘文件夹交给 Agent 管理

介绍 SkillHub 上的 @zcwl/obsidian（智创未来，v1.0.0，knowledge-management）。技能核心理念是 Obsidian 笔记库即本机文件夹、可直接做文件级管理，且无需 API Key。文章说明其定位、可核实能力、按 skillhub.md 安装到 Cursor/Claude Code 等 skills 目录的步骤，以及路径备份与客户端并行的注意点；典型操作以本地 SKILL.md 为准。

法律诉讼：用七步分析与证据矩阵辅助案件梳理

SkillHub 社区 Skill「法律诉讼」（@user_378eb7ca/pro-legal-strategist-v2，v1.0.3）面向诉讼与案件分析，采用官方简介中的七步分析法与证据矩阵建模，无需 API Key。文章说明其定位、可核实功能、通过 skillhub CLI 或安装提示词在 Cursor 等环境启用（--dir 指向 skills 目录），以及典型对话用法与合规边界。数据以 SkillHub 页面为准：professional 分类，评分 100000，下载 27815。

China Labor Dispute Resolution: Using Skill to Anchor Mainland Employment Issues in Legal Provisions, Evidence, and Procedural Paths

Introducing the SkillHub community skill "PRC Labor Law Dispute Resolution" (@user_84b8c7d7/prc-labor-law-resolution, v1.0.8). The skill is intended for labor employment and disputes in mainland China. It requires verification of official Chinese-language legal sources, identification of disputed issues, evidence planning, and transparent calculation of claimed amounts, and covers negotiation, labor administration, mediation, arbitration, litigation, and enforcement. It also supports colloquial triggers and multi-issue analysis. It describes two installation methods—via the skillhub CLI or a prompt—and skills directories such as Cursor. It is not applicable to non-mainland Chinese law or purely criminal, tax, or other specialized fields.

Intelligent Stock Sentiment AI Assistant: Market Data, Breaking News, and Capital Flows in a Single Conversation

The Intelligent AI Assistant for Equity Sentiment is a data-analysis category Skill in the SkillHub community (@user_8c7f0f65/topnews, version 8.8.8, no API key required). It aggregates the three major U.S. stock indices, futures, CLS 7×24 rapid news (bullish/bearish/neutral), macro and international news, northbound capital flows and margin trading, and provides a market environment judgment as bullish, bearish, or range-bound. This article explains its positioning, verified features, and the steps to install it into the skills directories for Cursor, Claude Code, Codex, and others using `skillhub install` per `skillhub.md`, along with typical conversational usage, while noting the boundaries for community maintenance and data compliance.

Office Automation Pro: Delegate Common Office Workflows to Agent Skills

Office Automation Pro (@user_c2b88a14/office-automation-pro) is a SkillHub Community Edition v1.0.0 office-efficiency Skill whose description covers document processing, data organization, email management, scheduling, and report generation, and is tagged as requiring no API Key. Based on public SkillHub materials, this article explains its positioning and capability boundaries and provides the skillhub CLI installation command and the skills directory paths for Cursor, Claude Code, and Codex, to facilitate loading SKILL.md in an Agent and using it according to specific scenarios.

Corporate Legal.SKILL: Install @indiv-ebandao/corporate-legal in an Agent

Corporate Legal.SKILL (@indiv-ebandao/corporate-legal, v1.0.2) is a professional-category community skill on SkillHub, tagged `requires_api_key=false`. Based on the SkillHub page and installation documentation, the article explains how to install it into the skills directory of Cursor, Claude Code, and other tools using `skillhub install` or the official prompt. It also notes that if public materials do not provide a detailed feature list, the local `SKILL.md` should be treated as authoritative, and outputs require manual legal review.

Enterprise Legal.SKILL: Decomposing Common Corporate Legal Matters into Routable Sub-Skill Packs

Corporate Legal.SKILL (corporate-legal) is a comprehensive corporate legal skill package published by Wisdom & Peninsula, a community author on SkillHub. The latest version is v1.0.2, and it is categorized under Professional and Legal Compliance. It divides background checks, resolutions, compliance reviews, similar cases, legal daily reports, legal documents, e-signatures, and risk assessments into eight subskills, routed via SKILL.md and executed by reading templates from references. The article explains how to install it from SkillHub (through chat prompts or the skillhub CLI), the skills directories for Cursor, Codex, and Claude Code, and typical trigger phrases and usage boundaries such as lawyer review and the currency of regulations.

Scam Prevention Master.Skill: Embedding Everyday Fraud Detection into an Agent

Fraud Prevention Master.Skill (@user_741dc82b/anti-fraud) is an anti-fraud skill in SkillHub’s lifestyle services category. It helps identify suspicious SMS messages, links, and chats, proactively issues warnings when signals such as money transfers, verification codes, or screen sharing appear, and supports anti-fraud education and role-playing drills. The article describes its core capabilities, installation paths in environments such as SkillHub CLI and Cursor, as well as typical triggering methods and usage notes.

AI-Fee Removal Tool: Rewriting AI Drafts to Sound More Human

Article AI-Like Writing Reduction Tool (@user_ab5ae6ee/unclecheng-reduce-ai-perception-v2, v1.0.5) is a content-creation community skill on SkillHub that requires no API key. When users ask to remove an AI-like tone, polish the text, or make it sound more natural, it detects and fixes issues such as high-frequency AI phrasing, excessive structuring, mechanical transition words, and formulaic endings. This article explains its positioning, capabilities, and installation command (using skillhub install with Cursor or other skills directories), and provides typical in-conversation triggers and usage notes.

CRO: Systematically Reviewing Marketing Page and Form Conversion Rates with Agent Skills

CRO is a conversion rate optimization Agent Skill (v2.0.3) in the open-source marketingskills library, designed for scenarios such as homepages, landing pages, pricing pages, and lead forms. It uses a seven-dimension framework covering value propositions, headlines, CTAs, and trust signals to output quick wins, high-impact changes, experiment hypotheses, and copy alternatives, and can route to related skills such as form.md, experiments.md, signup, and ab-testing. Install the full library with `npx skills add coreyhaines31/marketingskills` and use it alongside product-marketing context in environments such as Cursor, Claude Code, and Codex.

Supabase Skill: Enabling AI Assistants to Perform Full-Stack Development Following Supabase's Official Workflow

Introduces the Supabase Skill (0.1.2) maintained by Supabase in the agent-skills repository. It covers product areas such as Database, Auth, Edge Functions, Realtime, and Storage, along with SSR integrations including Next.js, and features built-in guidance on changelog-first changes, post-change verification, exposing Data APIs, and an RLS security checklist. It explains installation and updates via `npx skills add`, provides typical natural-language task examples, and is suitable for developers using agents such as Cursor for Supabase development and troubleshooting.

turnstile-spin: Building an End-to-End, Acceptance-Ready Agent Flow for Turnstile Integration

turnstile-spin is an Agent Skill maintained by Cloudflare in the cloudflare/skills repository for creating, repairing, or migrating Turnstile bot verification in existing front-end and back-end applications. Using authentication detection, widget creation scripts, and a multi-step wizard under the `scripts` directory, it scans the codebase, embeds the Turnstile widget according to Next.js, Astro, or SvelteKit references, integrates site verification into existing backends, and performs live validation before reporting success. It is suitable for scenarios such as registration and login forms or API abuse prevention; ensure the required API Token permission is `Account.Turnstile:Edit`, and be aware of Wrangler usage constraints and hostname validation for local and production environments.

context-fundamentals: Foundational Mental Models for Context Engineering

context-fundamentals is the foundational Skill in muratcankoylan's open-source collection, Agent Skills for Context Engineering. It uses SKILL.md to define the full composition of context during inference (system prompt, tool definitions, retrieved documents, message history, and tool outputs), and establishes mental models such as a finite attention budget and the U-shaped attention curve, emphasizing signal quality over token accumulation. The article explains when this Skill should be activated, its routing relationship with operational Skills such as context-degradation, and directory-level installation methods via the Claude Code plugin marketplace, Cursor, and Codex. It also provides an example of the official system prompt partitioning and a recommended reading order, making it suitable as introductory background reading for the context engineering series.

babysitting-pr: Have the Agent Continuously Keep PRs Mergeable

"babysitting-pr" is from awesome-cursor-skills, a SKILL.md that instructs the Cursor Agent to fetch status via gh when a PR is opened, address CI failures and review comments, resolve merge conflicts with main, and recheck using gh pr checks --watch after pushing. The document specifies a maximum of three fix-push-check cycles, prohibits force-pushing, and requires reporting items that need design decisions to the user. It is suitable for teams that want to keep PRs continuously merge-ready; to install it, place the skill in .cursor/skills/.

writing-tests: A Cursor Skill for Generating Unit and Integration Tests for Existing Code

writing-tests, from awesome-cursor-skills, is a SKILL.md workflow for Cursor Agent that identifies testing stacks such as Jest/Vitest, analyzes exported APIs and uncovered branches, generates unit and integration tests according to project conventions, and uses vi.mock and Testing Library to handle dependencies and React components. It is suitable for adding missing tests, improving test coverage, or writing tests for a single module; place the Skill in .cursor/skills/ for automatic discovery by the Agent.

adding-docker: Generate Production-Grade Docker Configurations for Your Application

adding-docker is an Agent Skill in awesome-cursor-skills. When a user asks to containerize an application, it follows the SKILL.md workflow to detect the runtime (e.g., package.json, go.mod), generates a multi-stage Dockerfile and .dockerignore, and adds docker-compose.yml when dependencies such as a database are present. The documentation emphasizes using Alpine images, never baking .env into the image, ignoring unrelated packages in a monorepo, and including a production HEALTHCHECK. Installation is done by placing SKILL.md in .cursor/skills/ so the Agent can discover it automatically.

Suggesting Cursor Rules: When Correcting the Same Convention Repeatedly, Write It as a Cursor Rule

suggesting-cursor-rules is a Cursor-Native Skill in awesome-cursor-skills. When a user corrects the same code convention two or more times, expresses a fixed preference, or the Agent repeatedly makes the same type of error, the Agent proposes creating a .mdc rule file under .cursor/rules/. After user consent, it writes the description, globs, and convention entries. The Skill is user-invocable and requires copying SKILL.md to .cursor/skills/ so that the Agent can discover it automatically. This article introduces the trigger conditions, proposal wording, rule template, and official examples, explaining the meta-workflow in which Rules and Skills work together.

Product Strategy: Building a Product Strategy with the Nine-Section Product Strategy Canvas

product-strategy is an Agent Skill under the pm-product-strategy plugin in phuryn/pm-skills. It guides the assistant to create a strategic document using the nine sections of the Product Strategy Canvas—vision, segments, costs, value proposition, trade-offs, metrics, growth, capabilities, and defensibility—and performs consistency checks, identifies key assumptions, and recommends low-effort validation experiments. It supports Claude Cowork/Code, Codex CLI, and environments like Cursor by copying SKILL.md. Its methodology shares the same origin as Product Compass and is suitable for product teams that need structured product direction.

prd-development: An Agent Skill for Turning Discovery Notes Into a Deliverable PRD

prd-development from deanpeters/Product-Manager-Skills is a workflow-style Skill for major requirements. It uses a 10-section PRD template and eight stages to weave together the problem, users, strategic context, solution, success metrics, user stories, and out-of-scope items into a living document, and marks gaps in template.md with Assumption/Open Question notes. It can be invoked with discovery materials or started from problem definition, and can be paired with workshop-facilitation for step-by-step guidance, making it suitable for structuring requirements before engineering handoff.

wp-playground: Guiding AI Assistants Through WordPress Playground, Scenario by Scenario

wp-playground is the Playground routing wrapper in the official WordPress agent-skills. Instead of duplicating the Blueprint schema, it routes by intent to the blueprint skill or references such as cli, website, and debugging. It covers local execution with @wp-playground/cli, sharing on playground.wordpress.net, mounting, version switching, and Xdebug and WebMCP browser workflows. It requires Node.js 20.18+ and targets WordPress 7.0+. It can be installed into a project or the global Cursor directory via npx skills add.

Expo-Upgrade: Using the Official Skill to Turn Expo SDK Updates Into a Reproducible Process

expo-upgrade is an MIT-licensed open-source Skill maintained by the Expo team in expo/skills, designed for Expo SDK upgrades, dependency conflicts, deprecated package migrations, and cache cleanup. The article provides step-by-step commands (expo install, expo-doctor, cache clearing, and prebuild branching), SDK 53–56-specific references, notes on Hermes and the New Architecture, and a housekeeping checklist. It can be installed in Cursor and similar tools using npx skills add expo/skills; Claude Code and Codex can use the official Expo plugin. It is well suited for AI-agent-driven reproducible upgrades and reducing missed breaking changes in peer dependencies and packages such as expo-av.

clickhouse-best-practices: Constraining ClickHouse Reviews and Recommendations with 31 Rules

An Agent Skill maintained by ClickHouse Inc. that requires checking the 31 rules in rules/ and citing rule names before reviewing schemas, queries, and configurations. It covers primary keys and data types, JOINs and skipping indices, batch writes and mutation avoidance, as well as MCP/CLI connectivity, a seven-step schema discovery process, and secure query workflows. It can be installed with npx skills add clickhouse/agent-skills or clickhousectl skills, aligns with the official Best Practices documentation, and is suitable for teams using AI agents for ClickHouse design and SQL review.

Cloudflare One: Using Agent Skills to Guide Zero-Trust and SASE Deployment

cloudflare-one is an official Cloudflare Agent Skill for designing, configuring, troubleshooting, and reviewing zero-trust and SASE deployments of Cloudflare One (including Access, Gateway, WARP, Tunnel, WAN, DLP, CASB, and more). The skill prescribes a workflow: classify the task, gather account and traffic context, consult current documentation and APIs, and then propose change sets within guardrails that include validation and rollback; migration use cases are paired with cloudflare-one-migrations. The article describes installation methods (Cursor, npx skills, Claude Code, and Codex) and typical conversational usage.

firebase-basics: Writing the Firebase CLI Getting Started Workflow into an Agent Skill

firebase-basics from Google's google/skills repository is categorized as Serverless and focuses on Firebase CLI installation and version checks, login (including --no-localhost), project creation and firebase use switching, and retrieving google-services.json and GoogleService-Info.plist via apps:sdkconfig. It explicitly does not cover implementation topics such as Hosting, Firestore, and Auth. The article explains the npx skills add installation method and principles such as confirming the project ID first and prioritizing MCP and official documentation searches, making it well suited for Firebase project initialization in environments like Cursor.

Courier: Using Agent Skills to Integrate Multi-Channel Notifications into Cursor

courier is an official MIT-licensed Agent Skill from Courier that teaches coding assistants how to integrate email, SMS, push, in-app inbox, Slack, Teams, WhatsApp, and other notifications through a unified send API, covering templates, routing, preferences, Journeys, and CLI/MCP troubleshooting. Install it with npx skills add trycourier/courier-skills; it generates Node.js/Python code based on the types from installed SDKs and follows rules such as idempotency, E.164 formatting, and separating transactional from marketing messages, helping SaaS teams lower the barrier to integrating a notification BaaS.

dsh-cursor-dev: Integrating Cursor CLI into DSH as a Sub-Coding Agent

`dsh-cursor-dev` is a DSH workflow plugin that integrates the local Cursor CLI into the framework, enabling the parent model to delegate coding tasks to Cursor, review the results, and continue working. The plugin supports independent selection of the parent model and the Cursor model, and provides features such as subagent execution, session continuity, progress monitoring, and mirrored sub-sessions. Installation requires meeting the environment requirements for the DSH version, Node.js, and Cursor CLI. With tools such as `cursor_code` and `/cursor-subagent`, users can achieve efficient code writing and fixing.

DeepSeek Harness Plugin: xytoniki/dsh-cursor-agent

xytoki/dsh-cursor-agent is an open-source plugin designed to address the limitation that DeepSeek Harness (DSH) cannot reuse Cursor’s native ecosystem. By invoking Cursor’s undocumented server-side protocol, it enables DSH to directly use Cursor’s native agent loop, tool capabilities, and model configurations, delivering an experience consistent with Cursor. The plugin supports retaining native tools such as file read/write and web search, and automatically manages context. Installation is straightforward, but users should be aware of the risks and functional limitations associated with protocol reverse engineering.

dsh-subagent-cursor: Local Cursor Subagent Provider

`dsh-subagent-cursor` is a DeepSeek Harness plugin that registers Cursor as a subagent via a Profile Bundle, providing local one-shot task execution capabilities. It supports both CLI-driven and SDK-driven modes, and features automatic permission management, summary-first result presentation, and command approval level configuration (balanced/trusted/strict). After installation, it must be mounted in the configuration. Note that CLI mode requires prior login and does not support backgroundMode, making it suitable for scenarios that require securely embedding local code execution capabilities into an agent chain.

SpecWave: Multi-Host Coding Standards and Harness Workflow Tool

SpecWave is a multi-host coding CLI tool that natively integrates the ICVO specification into clients such as Cursor, Claude Code, and DSH through declarative adapter tables. It provides built-in Harness process commands and task-gating mechanisms to ensure consistent and verifiable coding behavior across tools. Users must meet the Node.js version requirements, apply configurations via the `host apply` command, and verify task gating using `verify`, establishing a strongly constrained execution environment for multi-agent collaboration.

DeepSeek Harness Plugin: Load Cursor / Gemini / Copilot Workspace Rules

`youjiaqi421/dsh-plugin-workspace-rules` is a workflow plugin for DeepSeek Harness (DSH) designed to address the issue of DSH being unable to read files such as `.cursorrules` or `GEMINI.md` defined by tools like Cursor, Gemini CLI, and Copilot. The plugin merges external workspace instructions and injects them into DSH’s system prompt, supporting real-time synchronization, size limits, and syntax preservation. Users need to install it from GitHub and can customize file paths, size limits, and reading order in `cordis.patch.yml`. During installation, be aware of build restrictions related to pnpm 10+.

《Cursor Docs》-Subagents

Subagents are specialized AI assistants that Cursor's agent can delegate tasks to. Each subagent operates in its own context window, handles specific types of work, and returns its result to the parent agent. Use subagents to break down complex tasks, do work in parallel, and preserve context in the main conversation.

《Cursor Docs》-Agent Skills

Agent Skills is an open standard for extending AI agents with specialized capabilities. Skills package domain specific knowledge and workflows that agents can use to perform specific tasks.

《Cursor Docs》-Security Agents

Security Agents scan your code for security bugs, risky patterns, and vulnerabilities.

《Cursor Docs》-Cursor TypeScript SDK

The @cursor/sdk package lets you call Cursor's agent from your own code. The same agent that runs in the Cursor IDE, CLI, and web app is now scriptable from TypeScript. Run the /sdk skill inside Cursor to get started.

《Cursor Docs》-Cursor Python SDK

The cursor sdk package lets you call Cursor's agent from your own Python code. The same agent that runs in the Cursor IDE, CLI, and web app is scriptable from Python with sync and async clients, typed dataclasses, and ordinary iteration for streams and pages. Run the /sdk skill inside Cursor to get started.

《Cursor Docs》-SDK Changelog

The latest features, improvements, and fixes shipping to the Cursor SDK, covering @cursor/sdk on npm and cursor sdk on PyPI.

《Cursor Docs》-Cursor SDK Bridge

The SDK Bridge is a small local server that embeds the TypeScript SDK and exposes the same agent surface over a stable Connect/protobuf protocol. Use it to script Cursor agents from languages without a first party SDK.

《Cursor Docs》-Rules

Rules provide system level instructions to Agent. They bundle prompts, scripts, and more together, making it easy to manage and share workflows across your team.

《Cursor Docs》-Third Party Hooks

Cursor supports loading hooks from third party tools, enabling compatibility with existing hook configurations from other AI coding assistants.

《Cursor Docs》-sandbox.json reference

Configure sandbox behavior with a sandbox.json file to control network access, filesystem paths, and more.

《Cursor Docs》-Plugins reference

Reference documentation for building, structuring, and submitting Cursor plugins. Plugins package rules, skills, agents, commands, MCP servers, and hooks into distributable bundles that work in the Cursor IDE.

《Cursor Docs》-permissions.json reference

Use permissions.json to configure MCP tool and terminal command allowlists and to steer the Auto review mode classifier so tools run without approval.

《Cursor Docs》-Keyboard Shortcuts

Overview of keyboard shortcuts in Cursor. See all keyboard shortcuts by pressing Cmd R then Cmd S or by opening command palette Cmd Shift P and searching for Keyboard Shortcuts.

《Cursor Docs》-Ignore file

Cursor reads your project's codebase to power its features. Control which directories and files Cursor can access using a .cursorignore file in your root directory.

《Cursor Docs》-Deeplinks

Deeplinks allow you to share prompts, commands, and rules with others, enabling collaboration and knowledge sharing across teams and communities.

《Cursor Docs》-Plugins

Plugins package rules, skills, agents, commands, MCP servers, and hooks into distributable bundles.

《Cursor Docs》-Settings

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Pull requests

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Mirror a GitHub repository

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Integrations

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Clone, Push & Pull

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Create an Origin repository

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Codebase settings

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Pull request commands

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Commands

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Install the CLI

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Browse & Search

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Origin

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Muse Spark 1 3

Meta is a new model provider in Cursor. Teams and Enterprise admins who configured model access before Meta was available need to enable the Meta provider before Muse Spark 1.3 appears for their members.

《Cursor Docs》-Kimi K3

Kimi K3 is Moonshot AI's latest open weight model. It sits above Kimi K2.7 Code for long running agent work: thorough upfront reasoning, strong one shot persistence, and the highest CursorBench score we've measured from an open model.

《Cursor Docs》-Kimi K2 7 Code

We recommend using Kimi K3 for new work. K2.7 Code remains available as a lower cost Moonshot option.

《Cursor Docs》-Grok 4 6

Grok 4.6 is a frontier model from Cursor and SpaceXAI for complex coding and knowledge work. It builds on Grok 4.5 with improved instruction following and long horizon agentic work.

《Cursor Docs》-Grok 4 5

We recommend using Grok 4.6 for improved instruction following and long horizon agentic work. Grok 4.5 remains available.

《Cursor Docs》-Gpt 5 Mini

We recommend using GPT 5.3 Codex for most tasks. It's more capable at a similar price point.

《Cursor Docs》-Gpt 5 Fast

We recommend using GPT 5.3 Codex. It's faster than previous generations and more cost effective.

《Cursor Docs》-Gpt 5 Codex

We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.

《Cursor Docs》-Gpt 5 6 Terra

GPT 5.6 Terra is the mid tier model in OpenAI's GPT 5.6 family. It sits between Sol and Luna on intelligence and price, making it a strong pick for everyday agentic coding when you want more capability than Luna without Sol's cost.

《Cursor Docs》-Gpt 5 6 Sol

GPT 5.6 Sol is OpenAI's flagship GPT 5.6 model in Cursor. It is the strongest of the Sol, Terra, and Luna family: persistent on long running agent work, fast enough for interactive sessions, and notably concise in how it communicates.

《Cursor Docs》-Gpt 5 6 Luna

GPT 5.6 Luna is the smallest and lowest cost model in OpenAI's GPT 5.6 family. Use it for high volume, latency sensitive, or cost sensitive agent work where Sol or Terra would be more than you need.

《Cursor Docs》-Gpt 5 5

GPT 5.5 is OpenAI's most intelligent model in Cursor. It keeps momentum on long running work and stays on task for significantly longer before stopping early, which matters most in complex, multi step coding sessions.

《Cursor Docs》-Gpt 5 4 Nano

GPT 5.4 Nano is the smallest and fastest model in the GPT 5.4 family. At $0.20 per million input tokens, it's built for high volume workloads where speed and cost matter more than peak reasoning. Reach for it when you need quick classification, extraction, ranking, or lightweight coding support.

《Cursor Docs》-Gpt 5 4 Mini

GPT 5.4 Mini brings good performance to cost sensitive workflows.

《Cursor Docs》-Gpt 5 4

GPT 5.4 is OpenAI's most capable model to date. It outperforms all other models on our internal benchmarks. For cost sensitive workflows where raw intelligence matters less, GPT 5.3 Codex remains a strong option at a lower price point.

《Cursor Docs》-Gpt 5 3 Codex

GPT 5.3 Codex is OpenAI's flagship coding model. It leads Terminal Bench by a wide margin and performs on par with Opus 4.6 on our internal benchmarks, at roughly one third the price. Much faster than previous GPT generations. A strong default for most coding tasks.

《Cursor Docs》-Gpt 5 2 Codex

We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.

《Cursor Docs》-Gpt 5 2

GPT 5.2 has access to all agent tools when used with Cursor including:

《Cursor Docs》-Gpt 5 1 Codex Mini

We recommend using GPT 5.3 Codex for most tasks. It's more capable at a similar price point.

《Cursor Docs》-Gpt 5 1 Codex Max

We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.

《Cursor Docs》-Gpt 5 1 Codex

We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.

《Cursor Docs》-Gpt 5

We recommend using GPT 5.3 Codex. It scores higher on benchmarks, is faster, and more cost effective.

《Cursor Docs》-Glm 5 2

GLM 5.2 has access to all agent tools when used with Cursor including:

《Cursor Docs》-Gemini 3 Pro Image Preview

This model is used exclusively for the image generation tool inside Cursor. It is not selectable as a chat model.

《Cursor Docs》-Gemini 3 Pro

We recommend using Gemini 3.1 Pro. It's the latest version with stronger multimodal capabilities and the same pricing.

《Cursor Docs》-Gemini 3 Flash

Gemini 3 Flash is Google's speed optimized model. At $0.50 per million input tokens, it's one of the cheapest options available. Use it for simple coding tasks, quick edits, and executing plans written by a more capable model.

《Cursor Docs》-Gemini 3 8 Flash

Gemini 3.8 Flash is Google's latest speed tier model. It pairs strong agentic coding performance with low per token costs. Use it for high throughput coding tasks that benefit from reasoning and a large context window.

《Cursor Docs》-Gemini 3 7 Flash

We recommend using Gemini 3.8 Flash. It's Google's latest speed tier model at the same price.

《Cursor Docs》-Gemini 3 6 Flash

We recommend using Gemini 3.8 Flash. It's Google's latest speed tier model with lower input and output prices.

《Cursor Docs》-Gemini 3 5 Flash

We recommend using Gemini 3.8 Flash. It's Google's latest speed tier model with lower input and output prices.

《Cursor Docs》-Gemini 3 1 Pro

Gemini 3.1 Pro is Google's latest model. It processes images alongside code, making it strong for UI/UX work from design mockups. It supports context windows up to 1M tokens.

《Cursor Docs》-Gemini 2 5 Flash

We recommend using Gemini 3.8 Flash. It's Google's latest speed tier model.

《Cursor Docs》-Cursor Composer 2 5

Composer 2.5 is Cursor's own agentic model. It builds on Composer 2 with stronger intelligence on long agentic tasks, better effort calibration, tool selection, intent understanding, and reliability.

《Cursor Docs》-Cursor Composer 1

We strongly recommend using Composer 2.5. It's smarter and includes more usage on individual plans.

《Cursor Docs》-Claude Sonnet 5

Claude Sonnet 5 is Anthropic's latest medium tier model and replaces Sonnet 4.6. It pushes quality close to Opus while keeping Sonnet's lower per token price. It supports thinking mode and context windows up to 1M tokens, making it a strong default for everyday coding when you want frontier reasoning without Opus pricing.

《Cursor Docs》-Claude Opus 5

Claude Opus 5 is Anthropic's latest Opus model and replaces Opus 4.8. It is a step change over Opus 4.8 on agentic coding, professional knowledge work, and long horizon reasoning, and it lands on par with Fable 5 on CursorBench at Opus pricing. We recommend the high thinking variant for the best results.

《Cursor Docs》-Claude Opus 4 8

We recommend using Claude Opus 5. It replaces Opus 4.8 with stronger agentic coding and long horizon reasoning at the same price.

《Cursor Docs》-Claude Opus 4 7 Fast

Fast mode for Claude Opus 4.7 bills at a much higher per token rate than standard Opus 4.7. Use it selectively for time sensitive or critical work where cost is secondary.

《Cursor Docs》-Claude Opus 4 7

We recommend using Claude Opus 5. It is Anthropic's latest Opus release with the same pricing and stronger agentic capabilities.

《Cursor Docs》-Claude Opus 4 6

We recommend using Claude Opus 5. It scores higher on CursorBench, offers stronger autonomous capabilities, and is priced the same.

《Cursor Docs》-Claude Opus 4 5

We recommend using Claude Opus 5. It's the latest Opus with stronger reasoning and code quality.

《Cursor Docs》-Claude Fable 5 1

Claude Fable 5.1 is Anthropic's latest Mythos class model and replaces Fable 5. It is built for long running, complex, and asynchronous coding and knowledge work. Input and output rates match Fable 5. Prompt cache reads are 75% cheaper.

《Cursor Docs》-Claude Fable 5

We recommend using Claude Fable 5.1. It is Anthropic's latest Mythos class model, with cheaper prompt cache reads. Fable 5 remains available.

《Cursor Docs》-Claude 4 Sonnet 1M

We recommend using Claude Sonnet 5, which also supports up to 1M tokens of context.

《Cursor Docs》-Claude 4 Sonnet

We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.

《Cursor Docs》-Claude 4 6 Sonnet

We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.

《Cursor Docs》-Claude 4 5 Sonnet

We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.

《Cursor Docs》-Claude 4 5 Haiku

For stronger results, consider Claude Sonnet 5 or Gemini 3 Flash for a fast, affordable alternative.

《Cursor Docs》-Models & Pricing

Cursor supports frontier models from OpenAI, Anthropic, Google, SpaceXAI, and more. Pro, Pro Plus, and Ultra include two usage pools so you can pick the right balance of intelligence, speed, and cost. Start, our plan for developers in India, covers the Cursor Models pool.

《Cursor Docs》-MCP Install Links

Looking to share MCP servers, rules, and more? Plugins make it easier to bundle and distribute everything in one package. You can publish to the Cursor Marketplace or your team's private marketplace.

《Cursor Docs》-Model Context Protocol (MCP)

What is MCP?

《Cursor Docs》-Xcode

Xcode 26.3+ exposes a built in MCP server that gives Cursor direct access to your Xcode projects. Cursor's agent can read and edit files, trigger builds, run tests, capture SwiftUI previews, and search Apple's documentation; all without leaving your editor.

《Cursor Docs》-Slack

With Cursor's integration for Slack, you can use Cloud Agents to work on your tasks directly from Slack by mentioning @cursor with a prompt.

《Cursor Docs》-Notion

Connect Cursor to Notion so you can delegate specs, tasks, and comments to agents. Because the integration is built on the Cursor SDK, every agent uses the same runtime, harness, and models that power Cursor.

《Cursor Docs》-Microsoft Teams

With Cursor's integration for Microsoft Teams, you can use Cloud Agents to work on tasks directly from Microsoft Teams by mentioning @Cursor with a prompt.

《Cursor Docs》-Linear

Use Cloud Agents directly from Linear by delegating issues to Cursor or mentioning @Cursor in comments.

《Cursor Docs》-Jira

With Cursor's integration for Jira, you can use Cloud Agents to work on Jira work items by assigning them to Cursor or mentioning @Cursor in Jira.

《Cursor Docs》-JetBrains

Use Cursor's AI agent in IntelliJ IDEA, PyCharm, WebStorm, and other JetBrains IDEs through the Agent Client Protocol (ACP).

《Cursor Docs》-GitLab

The GitLab integration connects your repositories so you can use features like Cloud Agents and Bugbot.

《Cursor Docs》-GitHub

The Cursor GitHub app connects your repositories so you can use features like Cloud Agents and Bugbot.

《Cursor Docs》-Cursor Blame

Understanding how AI contributed to your codebase helps with review, compliance, and debugging. This page covers how Cursor Blame surfaces AI versus human authorship in git history.

《Cursor Docs》-Bitbucket

Connect Bitbucket Cloud repositories to Cloud Agents and Bugbot. Connect Bitbucket Data Center repositories to Bugbot.

《Cursor Docs》-Azure DevOps

The Azure DevOps integration connects Azure DevOps Services repositories to Cloud Agents and Bugbot.

《Cursor Docs》-Hooks

Hooks let you observe, control, and extend the agent loop using custom scripts. Define hooks in hooks.json files at the project or user level, or install them through plugins from Customize . Hooks are spawned processes that communicate over stdio using JSON in both directions. They run before or after defined stages of the agent loop and can observe, block, or modify behavior.

《Cursor Docs》-Work with Grok Bot

Everything about working with Bots day to day: creating and managing them, messaging and collaborating, the computer they share, and turning finished work into skills and routines.

《Cursor Docs》-Grok Bot use cases

The best Bot roles own a repeatable outcome, not a loose category of questions. Start each role with read and prepare work, review the result, and only then add approved actions or a routine.

《Cursor Docs》-Grok Bot for Teams and Enterprise

Grok Bot gives each person on your team standing Bots for everyday work: research, operations, documents, browsing, and automations. This page is for team and organization admins rolling Grok Bot out. Security reviewers should start with Grok Bot security and the Grok Bot security FAQ. Members who want the approval model should start there too.

《Cursor Docs》-Settings and notifications

Grok Bot settings cover app wide and desktop local behavior. Each Bot's profile and notification preference live in its conversation details. Open settings from the account menu or with Cmd+,.

《Cursor Docs》-Grok Bot security FAQ

These are the questions security reviews ask most often. The controls behind each answer are on Grok Bot security. Dashboard settings and rollout steps are on Grok Bot for Teams and Enterprise.

《Cursor Docs》-Grok Bot security

Use these controls and deployment details to decide whether Grok Bot is allowed in, and to limit what Bots can access, change, and retain. Rollout steps and the dashboard settings list live on Grok Bot for Teams and Enterprise. Common review questions are on Grok Bot security FAQ.

《Cursor Docs》-Configure TLS-inspecting proxies

The Grok Bot desktop app connects from each member's device to two places: Cursor's API at .cursor.sh for chat, sign in, and approvals, and the member's hosted computer at a nested . .cursorvm.com hostname for computer setup, screen, and shell. Secure web gateways that inspect TLS often let the first through and break the second. The desktop app then hangs or errors during computer setup; in some setups chat keeps working while the computer never connects. Zscaler is the most common example, and this page uses it for specifics; the same steps apply to any gateway that re signs TLS or buffers responses. This page is for the IT team that runs your gateway. The shared domain list and streaming tests live on Enterprise network configuration; this page covers what Grok Bot adds.

《Cursor Docs》-Connect to private networks

Grok Bot computers run in Cursor's cloud and reach the internet through shared static egress IP addresses. If the systems your Bots need, such as internal APIs, source control, databases, or staging environments, live on a private network, you can connect by installing your organization's networking client on every team computer through Team Setup . Tailscale and Cloudflare Tunnel are common choices, and this page has a worked example for each. Other VPN, zero trust, or mesh clients that run on Linux follow the same pattern. Your services stay off the public internet, and access is governed by the access controls and identity provider you already use.

《Cursor Docs》-Configure identity and access

This guide is for admins running Okta or Microsoft Entra ID. It covers giving people outside your engineering organization access to Grok Bot through your Cursor team, and letting members sign in to IdP provisioned apps from the Bot's computer. For the broader security model, see Grok Bot security.

《Cursor Docs》-Get started with Grok Bot

This guide takes you from install to your first finished task. You'll set up the desktop app, create a Bot with a clear job, and review its work.

《Cursor Docs》-Grok Bot

Grok Bot gives you Bots you can keep around: AI teammates with names, jobs, and context that compounds over time. Each Bot works on a persistent cloud computer with a browser, filesystem, and terminal, so tasks finish in your real tools instead of as chat drafts. Get started with your first Bot, or read how teams roll it out.

《Cursor Docs》-Quickstart

This guide gets you from install to your first useful change in Cursor. You'll sign in, ask Cursor to explain your codebase, make a small edit, and review the result.

《Cursor Docs》-Extension API reference

Cursor exposes extension APIs under vscode.cursor for programmatic configuration. Use these APIs from VS Code extensions to register MCP servers and plugin paths without editing config files.

《Cursor Docs》-Run Cursor in your evals

Use the Cursor SDK to run Cursor's agent loop inside your own eval harness. The same agent that powers the Cursor IDE, CLI, and web app is scriptable from TypeScript, so you can score Grok 4.6 (and other models we support) on your benchmarks.

《Cursor Docs》-Security and Privacy Hardening

This page consolidates the security and privacy guidance spread across the Cursor docs into one reference, so teams configuring Cursor can review and apply the right controls without hunting through every page. Each item links to its source doc for the full detail.

《Cursor Docs》-Privacy and Data Governance

Understanding how data flows through Cursor is critical for security reviews and compliance assessments. This documentation explains what data goes where, what guarantees you have, and where that data lives geographically.

《Cursor Docs》-Pooled usage

Pooled usage gives your Enterprise team a shared usage pool instead of fixed per user allocations. Everyone draws from a single committed amount that spans your contract period, so agent usage is available wherever it's needed most.

《Cursor Docs》-Organizations

Organizations are the top level container for Enterprise customers. They sit above teams and give you one place to manage shared identity, administration, and organization wide settings.

《Cursor Docs》-Organization Groups

Organization Groups are org level cohorts in Cursor Enterprise, such as Engineering, Contractors, or Pilot Users. Members can come from any team in your Organization, and a user can belong to many groups at once.

《Cursor Docs》-OpenTelemetry Export Wire Reference

Companion to OpenTelemetry Export. Full wire surface: every metric, log event, attribute, enum, and presence rule.

《Cursor Docs》-OpenTelemetry Export

OpenTelemetry Export streams Cursor usage data for your team to a collector you run. Cursor sends metrics (tokens, tool calls, best effort cost) and logs (API requests, errors, corrections, skills, hooks, plugins, cloud agent lifecycle events, and recorded Grok Bot actions) to one team managed destination. Export runs server side.

《Cursor Docs》-Network Configuration

Cursor needs to communicate with backend services and AI providers. This documentation covers how to configure Cursor to work within your network infrastructure, including proxies, firewalls, and encryption requirements.

《Cursor Docs》-Model and Integration Management

Your team can access multiple AI models and integrate Cursor with various services. This documentation covers how to control which models are available, manage MCP server trust, and set up integrations with tools like Slack, GitHub, and Linear.

《Cursor Docs》-LLM Safety and Controls

AI models can behave unexpectedly. This documentation covers how to control what agents can do, set up safety guardrails, and guide LLM behavior toward desired outcomes.

《Cursor Docs》-Identity and Access Management

Identity and access management controls who can use Cursor in your organization and what they can do. You'll set up authentication, automate user provisioning, and enforce policies through device management.

《Cursor Docs》-Endpoint Security Configuration

Cursor loads JavaScript modules and performs file I/O during startup. Endpoint security software that intercepts file operations or injects into processes can slow startup past internal timeouts, causing features like Agent to fail. This page covers how to configure exclusions so Cursor works alongside your security stack.

《Cursor Docs》-Deployment Patterns

This guide covers how to deploy the Cursor editor and CLI tools to developer machines in your organization. Most organizations deploy both the editor (for daily development work) and the CLI (for automation, CI/CD, and scripting).

《Cursor Docs》-Compliance and Monitoring

Compliance requires visibility into who did what, when, and why. This documentation covers audit logs, AI code tracking, certifications, and how to meet regulatory requirements.

《Cursor Docs》-Team Pools

A pool is a named routing target that connects requests with Self Hosted Machines workers. Requests wait in the pool until an available worker claims them. Create separate pools for different execution environments, such as gpu for work that needs GPUs or ios for work that needs a Mac.

《Cursor Docs》-My Machines

My Machines is the personal Self Hosted Machines configuration. It lets a specific user run Cloud Agent tool calls on a machine they already use: a laptop, devbox, or remote VM. Use it when that machine is the desired execution environment for a repo.

《Cursor Docs》-Integrations

Run Team Pool workers on an infrastructure partner's platform, or start from a reference template you clone and adapt. Every option runs the same worker: the Cursor CLI opens an outbound HTTPS connection to Cursor, and Cursor sends agent tool calls over that connection.

《Cursor Docs》-Computer use and desktop sharing

Computer use lets an agent on a Self Hosted Machines worker click, type, take screenshots, and drive applications with a UI. Agents can also drive a browser when the worker has Chrome or Chromium installed. It works on macOS and Linux workers, for both My Machines and Team Pools. Desktop sharing lets authorized viewers watch or take control of a Linux agent desktop from Cursor. For the product behavior on managed Cloud Agents, see Capabilities.

《Cursor Docs》-Choose where Cloud Agents run

Cursor hosted Cloud Agents run each agent in an isolated cloud VM with managed lifecycle, saved environments, artifact capture, and dashboard controls for secrets and network access.

《Cursor Docs》-Subagents

Subagents are specialized AI assistants that Cursor's agent can delegate tasks to. Each subagent operates in its own context window, handles specific types of work, and returns its result to the parent agent. Use subagents to break down complex tasks, do work in parallel, and preserve context in the main conversation.

《Cursor Docs》-Agent Skills

Agent Skills is an open standard for extending AI agents with specialized capabilities. Skills package domain specific knowledge and workflows that agents can use to perform specific tasks.

《Cursor Docs》-Security Agents

Security Agents scan your code for security bugs, risky patterns, and vulnerabilities.

《Cursor Docs》-Cursor TypeScript SDK

The @cursor/sdk package lets you call Cursor's agent from your own code. The same agent that runs in the Cursor IDE, CLI, and web app is now scriptable from TypeScript. Run the /sdk skill inside Cursor to get started.

《Cursor Docs》-Cursor Python SDK

The cursor sdk package lets you call Cursor's agent from your own Python code. The same agent that runs in the Cursor IDE, CLI, and web app is scriptable from Python with sync and async clients, typed dataclasses, and ordinary iteration for streams and pages. Run the /sdk skill inside Cursor to get started.

《Cursor Docs》-SDK Changelog

The latest features, improvements, and fixes shipping to the Cursor SDK, covering @cursor/sdk on npm and cursor sdk on PyPI.

《Cursor Docs》-Cursor SDK Bridge

The SDK Bridge is a small local server that embeds the TypeScript SDK and exposes the same agent surface over a stable Connect/protobuf protocol. Use it to script Cursor agents from languages without a first party SDK.

《Cursor Docs》-Rules

Rules provide system level instructions to Agent. They bundle prompts, scripts, and more together, making it easy to manage and share workflows across your team.

《Cursor Docs》-Third Party Hooks

Cursor supports loading hooks from third party tools, enabling compatibility with existing hook configurations from other AI coding assistants.

《Cursor Docs》-sandbox.json reference

Configure sandbox behavior with a sandbox.json file to control network access, filesystem paths, and more.

《Cursor Docs》-Plugins reference

Reference documentation for building, structuring, and submitting Cursor plugins. Plugins package rules, skills, agents, commands, MCP servers, and hooks into distributable bundles that work in the Cursor IDE.

《Cursor Docs》-permissions.json reference

Use permissions.json to configure MCP tool and terminal command allowlists and to steer the Auto review mode classifier so tools run without approval.

《Cursor Docs》-Keyboard Shortcuts

Overview of keyboard shortcuts in Cursor. See all keyboard shortcuts by pressing Cmd R then Cmd S or by opening command palette Cmd Shift P and searching for Keyboard Shortcuts.

《Cursor Docs》-Ignore file

Cursor reads and indexes your project's codebase to power its features. Control which directories and files Cursor can access using a .cursorignore file in your root directory.

《Cursor Docs》-Deeplinks

Deeplinks allow you to share prompts, commands, and rules with others, enabling collaboration and knowledge sharing across teams and communities.

《Cursor Docs》-Plugins

Plugins package rules, skills, agents, commands, MCP servers, and hooks into distributable bundles.

《Cursor Docs》-Settings

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Pull requests

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Mirror a GitHub repository

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Integrations

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Clone, Push & Pull

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Create an Origin repository

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Codebase settings

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Pull request commands

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Commands

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Install the CLI

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Browse & Search

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Origin

Origin is currently released in early beta. You can create repos, push and pull with git, mirror from GitHub, browse and search code, open and merge pull requests, and share with your Cursor team.

《Cursor Docs》-Kimi K3

Kimi K3 is Moonshot AI's latest open weight model. It sits above Kimi K2.7 Code for long running agent work: thorough upfront reasoning, strong one shot persistence, and the highest CursorBench score we've measured from an open model.

《Cursor Docs》-Kimi K2 7 Code

We recommend using Kimi K3 for new work. K2.7 Code remains available as a lower cost Moonshot option.

《Cursor Docs》-Grok 4 6

Grok 4.6 is a frontier model from Cursor and SpaceXAI for complex coding and knowledge work. It builds on Grok 4.5 with improved instruction following and long horizon agentic work.

《Cursor Docs》-Grok 4 5

We recommend using Grok 4.6 for improved instruction following and long horizon agentic work. Grok 4.5 remains available.

《Cursor Docs》-Gpt 5 Mini

We recommend using GPT 5.3 Codex for most tasks. It's more capable at a similar price point.

《Cursor Docs》-Gpt 5 Fast

We recommend using GPT 5.3 Codex. It's faster than previous generations and more cost effective.

《Cursor Docs》-Gpt 5 Codex

We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.

《Cursor Docs》-Gpt 5 6 Terra

GPT 5.6 Terra is the mid tier model in OpenAI's GPT 5.6 family. It sits between Sol and Luna on intelligence and price, making it a strong pick for everyday agentic coding when you want more capability than Luna without Sol's cost.

《Cursor Docs》-Gpt 5 6 Sol

GPT 5.6 Sol is OpenAI's flagship GPT 5.6 model in Cursor. It is the strongest of the Sol, Terra, and Luna family: persistent on long running agent work, fast enough for interactive sessions, and notably concise in how it communicates.

《Cursor Docs》-Gpt 5 6 Luna

GPT 5.6 Luna is the smallest and lowest cost model in OpenAI's GPT 5.6 family. Use it for high volume, latency sensitive, or cost sensitive agent work where Sol or Terra would be more than you need.

《Cursor Docs》-Gpt 5 5

GPT 5.5 is OpenAI's most intelligent model in Cursor. It keeps momentum on long running work and stays on task for significantly longer before stopping early, which matters most in complex, multi step coding sessions.

《Cursor Docs》-Gpt 5 4 Nano

GPT 5.4 Nano is the smallest and fastest model in the GPT 5.4 family. At $0.20 per million input tokens, it's built for high volume workloads where speed and cost matter more than peak reasoning. Reach for it when you need quick classification, extraction, ranking, or lightweight coding support.

《Cursor Docs》-Gpt 5 4 Mini

GPT 5.4 Mini brings good performance to cost sensitive workflows.

《Cursor Docs》-Gpt 5 4

GPT 5.4 is OpenAI's most capable model to date. It outperforms all other models on our internal benchmarks. For cost sensitive workflows where raw intelligence matters less, GPT 5.3 Codex remains a strong option at a lower price point.

《Cursor Docs》-Gpt 5 3 Codex

GPT 5.3 Codex is OpenAI's flagship coding model. It leads Terminal Bench by a wide margin and performs on par with Opus 4.6 on our internal benchmarks, at roughly one third the price. Much faster than previous GPT generations. A strong default for most coding tasks.

《Cursor Docs》-Gpt 5 2 Codex

We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.

《Cursor Docs》-Gpt 5 2

GPT 5.2 has access to all agent tools when used with Cursor including:

《Cursor Docs》-Gpt 5 1 Codex Mini

We recommend using GPT 5.3 Codex for most tasks. It's more capable at a similar price point.

《Cursor Docs》-Gpt 5 1 Codex Max

We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.

《Cursor Docs》-Gpt 5 1 Codex

We recommend using GPT 5.3 Codex. It scores higher on benchmarks and is faster.

《Cursor Docs》-Gpt 5

We recommend using GPT 5.3 Codex. It scores higher on benchmarks, is faster, and more cost effective.

《Cursor Docs》-Glm 5 2

GLM 5.2 has access to all agent tools when used with Cursor including:

《Cursor Docs》-Gemini 3 Pro Image Preview

This model is used exclusively for the image generation tool inside Cursor. It is not selectable as a chat model.

《Cursor Docs》-Gemini 3 Pro

We recommend using Gemini 3.1 Pro. It's the latest version with stronger multimodal capabilities and the same pricing.

《Cursor Docs》-Gemini 3 Flash

Gemini 3 Flash is Google's speed optimized model. At $0.50 per million input tokens, it's one of the cheapest options available. Use it for simple coding tasks, quick edits, and executing plans written by a more capable model.

《Cursor Docs》-Gemini 3 7 Flash

Gemini 3.7 Flash is Google's latest speed tier model. It pairs strong agentic coding performance with low per token costs. Use it for high throughput coding tasks that benefit from reasoning and a large context window.

《Cursor Docs》-Gemini 3 6 Flash

We recommend using Gemini 3.7 Flash. It's Google's latest speed tier model with lower input and output prices.

《Cursor Docs》-Gemini 3 5 Flash

We recommend using Gemini 3.7 Flash. It's Google's latest speed tier model with lower input and output prices.

《Cursor Docs》-Gemini 3 1 Pro

Gemini 3.1 Pro is Google's latest model. It processes images alongside code, making it strong for UI/UX work from design mockups. It supports context windows up to 1M tokens.

《Cursor Docs》-Gemini 2 5 Flash

We recommend using Gemini 3.7 Flash. It's Google's latest speed tier model.

《Cursor Docs》-Cursor Composer 2 5

Composer 2.5 is Cursor's own agentic model. It builds on Composer 2 with stronger intelligence on long agentic tasks, better effort calibration, tool selection, intent understanding, and reliability.

《Cursor Docs》-Cursor Composer 1

We strongly recommend using Composer 2.5. It's smarter and includes more usage on individual plans.

《Cursor Docs》-Claude Sonnet 5

Claude Sonnet 5 is Anthropic's latest medium tier model and replaces Sonnet 4.6. It pushes quality close to Opus while keeping Sonnet's lower per token price. It supports thinking mode and context windows up to 1M tokens, making it a strong default for everyday coding when you want frontier reasoning without Opus pricing.

《Cursor Docs》-Claude Opus 5

Claude Opus 5 is Anthropic's latest Opus model and replaces Opus 4.8. It is a step change over Opus 4.8 on agentic coding, professional knowledge work, and long horizon reasoning, and it lands on par with Fable 5 on CursorBench at Opus pricing. We recommend the high thinking variant for the best results.

《Cursor Docs》-Claude Opus 4 8

We recommend using Claude Opus 5. It replaces Opus 4.8 with stronger agentic coding and long horizon reasoning at the same price.

《Cursor Docs》-Claude Opus 4 7 Fast

Fast mode for Claude Opus 4.7 bills at a much higher per token rate than standard Opus 4.7. Use it selectively for time sensitive or critical work where cost is secondary.

《Cursor Docs》-Claude Opus 4 7

We recommend using Claude Opus 5. It is Anthropic's latest Opus release with the same pricing and stronger agentic capabilities.

《Cursor Docs》-Claude Opus 4 6

We recommend using Claude Opus 5. It scores higher on CursorBench, offers stronger autonomous capabilities, and is priced the same.

《Cursor Docs》-Claude Opus 4 5

We recommend using Claude Opus 5. It's the latest Opus with stronger reasoning and code quality.

《Cursor Docs》-Claude Fable 5

Claude Fable 5 is Anthropic's most capable generally available model for autonomous knowledge work and coding. It is a Mythos class model with strong safeguards, built to handle long running, complex, and asynchronous tasks where earlier models needed more frequent check ins.

《Cursor Docs》-Claude 4 Sonnet 1M

We recommend using Claude Sonnet 5, which also supports up to 1M tokens of context.

《Cursor Docs》-Claude 4 Sonnet

We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.

《Cursor Docs》-Claude 4 6 Sonnet

We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.

《Cursor Docs》-Claude 4 5 Sonnet

We recommend using Claude Sonnet 5. It's the latest Sonnet with stronger capabilities at a lower price.

《Cursor Docs》-Claude 4 5 Haiku

For stronger results, consider Claude Sonnet 5 or Gemini 3 Flash for a fast, affordable alternative.

《Cursor Docs》-Models & Pricing

Cursor supports frontier models from OpenAI, Anthropic, Google, SpaceXAI, and more. Pro, Pro Plus, and Ultra include two usage pools so you can pick the right balance of intelligence, speed, and cost. Start, our plan for developers in India, covers the Cursor Models pool.

《Cursor Docs》-MCP Install Links

Looking to share MCP servers, rules, and more? Plugins make it easier to bundle and distribute everything in one package. You can publish to the Cursor Marketplace or your team's private marketplace.

《Cursor Docs》-Model Context Protocol (MCP)

What is MCP?

《Cursor Docs》-Xcode

Xcode 26.3+ exposes a built in MCP server that gives Cursor direct access to your Xcode projects. Cursor's agent can read and edit files, trigger builds, run tests, capture SwiftUI previews, and search Apple's documentation; all without leaving your editor.

《Cursor Docs》-Slack

With Cursor's integration for Slack, you can use Cloud Agents to work on your tasks directly from Slack by mentioning @cursor with a prompt.

《Cursor Docs》-Notion

Connect Cursor to Notion so you can delegate specs, tasks, and comments to agents. Because the integration is built on the Cursor SDK, every agent uses the same runtime, harness, and models that power Cursor.

《Cursor Docs》-Microsoft Teams

With Cursor's integration for Microsoft Teams, you can use Cloud Agents to work on tasks directly from Microsoft Teams by mentioning @Cursor with a prompt.

《Cursor Docs》-Linear

Use Cloud Agents directly from Linear by delegating issues to Cursor or mentioning @Cursor in comments.

《Cursor Docs》-Jira

With Cursor's integration for Jira, you can use Cloud Agents to work on Jira work items by assigning them to Cursor or mentioning @Cursor in Jira.

《Cursor Docs》-JetBrains

Use Cursor's AI agent in IntelliJ IDEA, PyCharm, WebStorm, and other JetBrains IDEs through the Agent Client Protocol (ACP).

《Cursor Docs》-GitLab

The GitLab integration connects your repositories so you can use features like Cloud Agents and Bugbot.

《Cursor Docs》-GitHub

The Cursor GitHub app connects your repositories so you can use features like Cloud Agents and Bugbot.

《Cursor Docs》-Cursor Blame

Understanding how AI contributed to your codebase helps with review, compliance, and debugging. This page covers how Cursor Blame surfaces AI versus human authorship in git history.

《Cursor Docs》-Bitbucket

Connect Bitbucket Cloud repositories to Cloud Agents and Bugbot. Connect Bitbucket Data Center repositories to Bugbot.

《Cursor Docs》-Azure DevOps

The Azure DevOps integration connects Azure DevOps Services repositories to Cloud Agents and Bugbot.

《Cursor Docs》-Hooks

Hooks let you observe, control, and extend the agent loop using custom scripts. Define hooks in hooks.json files at the project or user level, or install them through plugins from Customize . Hooks are spawned processes that communicate over stdio using JSON in both directions. They run before or after defined stages of the agent loop and can observe, block, or modify behavior.

《Cursor Docs》-Quickstart

This guide gets you from install to your first useful change in Cursor. You'll sign in, ask Cursor to explain your codebase, make a small edit, and review the result.

《Cursor Docs》-Extension API reference

Cursor exposes extension APIs under vscode.cursor for programmatic configuration. Use these APIs from VS Code extensions to register MCP servers and plugin paths without editing config files.

《Cursor Docs》-Run Cursor in your evals

Use the Cursor SDK to run Cursor's agent loop inside your own eval harness. The same agent that powers the Cursor IDE, CLI, and web app is scriptable from TypeScript, so you can score Grok 4.6 (and other models we support) on your benchmarks.

《Cursor Docs》-Security and Privacy Hardening

This page consolidates the security and privacy guidance spread across the Cursor docs into one reference, so teams configuring Cursor can review and apply the right controls without hunting through every page. Each item links to its source doc for the full detail.

《Cursor Docs》-Privacy and Data Governance

Understanding how data flows through Cursor is critical for security reviews and compliance assessments. This documentation explains what data goes where, what guarantees you have, and where that data lives geographically.

《Cursor Docs》-Pooled usage

Pooled usage gives your Enterprise team a shared usage pool instead of fixed per user allocations. Everyone draws from a single committed amount that spans your contract period, so agent usage is available wherever it's needed most.

《Cursor Docs》-Organizations

Organizations are the top level container for Enterprise customers. They sit above teams and give you one place to manage shared identity, administration, and organization wide settings.

《Cursor Docs》-Organization Groups

Organization Groups are org level cohorts in Cursor Enterprise, such as Engineering, Contractors, or Pilot Users. Members can come from any team in your Organization, and a user can belong to many groups at once.

《Cursor Docs》-OpenTelemetry Export Wire Reference

Companion to OpenTelemetry Export. Full wire surface: every metric, log event, attribute, enum, and presence rule.

《Cursor Docs》-OpenTelemetry Export

OpenTelemetry Export streams Cursor usage data for your team to a collector you run. Cursor sends metrics (tokens, tool calls, best effort cost) and logs (API requests, errors, corrections, skills, hooks, plugins, and cloud agent lifecycle events) to one team managed destination. Export runs server side.

《Cursor Docs》-Network Configuration

Cursor needs to communicate with backend services and AI providers. This documentation covers how to configure Cursor to work within your network infrastructure, including proxies, firewalls, and encryption requirements.

《Cursor Docs》-Model and Integration Management

Your team can access multiple AI models and integrate Cursor with various services. This documentation covers how to control which models are available, manage MCP server trust, and set up integrations with tools like Slack, GitHub, and Linear.

《Cursor Docs》-LLM Safety and Controls