dsh-plugin-skill-manager：在 DeepSeek Harness Web 设置里统一管理 Skills
majinggui 维护的 DSH Web 工作流插件，在 Settings 增加 Skills 页：扫描用户级与可配置 skill 根，展示来源与优先级，按名启停（通过 frontmatter），内联编辑 SKILL.md，并支持上传 Markdown/zip 或 GitHub 链接安装。配置含 dshHome、extraRoots、installRoot 及 GitHub/上传/zip 限额。安装命令为 dsh plugin --profile web add @majinggui/dsh-plugin-skill-manager@latest，需 DSH >=0.2.0-rc.1。
Read Moredsh-skills-mcp-panel：在 Web GUI 里统一管理 Skills 与 MCP
dsh-skills-mcp-panel 是 KyattoCat 维护的 DSH Web 客户端插件（v0.2.0，MIT）。在 Settings → Agent presets → Skills/MCP 中按目录分组列出部署内全部 Skill 与 MCP，支持搜索、状态灯与热切换：Skill 通过 SKILL.md frontmatter 四态控制，MCP 在 cordis.patch.yml 标记块写入 disabled，live profile 下同会话生效。新装需重启 dsh web 一次。安装命令见官方 README 的 dsh plugin --profile web add。
Read More瓶颈猎手：为 AI Agent 准备的 SkillHub 社区技能
瓶颈猎手（@user_3c6cb52e/bottleneck-hunter-sh-lk3fez）是 SkillHub ai-agent 分类下的社区技能 v1.0.0，简介为帮助 Agent 高效完成瓶颈相关任务，标签 requires_api_key=false。本文依据 SkillHub 页面与 skillhub.md 说明 CLI 检查、skillhub install 与 Cursor/Claude Code/Codex 等 skills 目录，并说明公开资料未列细项能力、应以 SKILL.md 为准。
Read More虚幻引擎 Claude Code 技能：为 Agent 补齐虚幻引擎协作上下文
本文介绍 SkillHub 社区技能「虚幻引擎 Claude Code 技能」（@user_3c6cb52e/unreal-engine-sh-etzk7s，v1.0.0，ai-agent，requires_api_key=false）。它面向在 Claude Code、Cursor 等客户端中用 Agent 处理虚幻引擎相关任务的场景，将协作约定封装为通用 SKILL.md 格式。文中给出 skillhub CLI 检查、按客户端 skills 目录安装命令、以及官方页面提供的 Agent 安装提示句，并说明能力边界以安装后的 SKILL.md 为准，避免臆造未公开的功能细节。
Read More自动给微信好友发送消息：用 Skill 把微信发信交给 Agent
SkillHub 社区 Skill「自动给微信好友发送消息」（@user_24d6975e/wechat-chat，v1.0.0，ai-agent）面向 Agent 自动化微信好友发信。本文基于官方安装文档与商店元数据，说明 skillhub CLI 安装、Cursor 等环境的 skills 目录、官方提示词启用方式，并标明 requires_api_key=false 与公开资料边界；具体发信步骤以安装后的 SKILL.md 为准。
Read Moredsh-settings-mcp-skills: DeepSeek Harness Settings Page Patch
This is an MIT-licensed plugin developed for DeepSeek Harness (dsh), designed to extend configuration features via the web UI. It addresses the lack of MCP Servers and Skills settings pages in the official `web-app`. The plugin supports managing external MCP servers (with real-time status monitoring) and drag-and-drop uploading of local Skills, while being easy to install and not affecting core functionality.
Read More《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.
Read MoreDSH Plugin Manager: Manage MCP, Skills, and Built-in Plugin Packages within the Settings Panel
dsh-plugin-manager is a DSH dual-end client plugin maintained by liqichen, embedded within the DeepSeek Harness settings panel. It provides a graphical interface for managing MCP service toggles and deletions, Skills browsing with recycle-bin-style deletion, and read-only browsing of over 160 built-in plugin packages. Changes are written to cordis.patch.yml and ~/.dsh/skills/, taking effect immediately without restarting the dsh web. Configuration backups are automatically created before write operations. This article introduces the installation and registration steps, usage of the three tabs, API interfaces, as well as usage boundaries and recovery methods.
Read More《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.
Read MoreAdding E2E Tests: Building Playwright End-to-End Tests from Scratch with Agent Skill
### 正式翻译： # Adding E2E Tests from awesome-cursor-skills: Teach AI Agents to Build Playwright E2E Testing from Scratch This tutorial covers end-to-end setup with Playwright: installing dependencies, configuring `playwright.config.ts`, writing smoke tests and Page Objects, supplementing npm scripts and `.gitignore`, integrating GitHub Actions CI, and emphasizes best practices for `data-testid` and Playwright Codegen. It explains the positioning of this skill, its differences from webapp-testing, installation methods for Cursor/Claude Code, and a seven-step implementation workflow, making it suitable for frontend and full-stack projects that have not yet adopted E2E testing.
Read More