提示词审查打分并改进：用 Skill 复盘对话里的提问质量
介绍 SkillHub 社区 Skill「提示词审查打分并改进」（@user_6837aee4/prompt-reviewer-v2，v1.0.0）。它审计历史对话中的用户提问，做多维打分与痛点分析，并给出重构建议；无需 API Key。文章说明定位、核心能力、skillhub CLI 安装到 Cursor 等客户端 skills 目录的步骤，以及「提示词复盘」「prompt review」等官方触发语。适合希望系统改进与 AI 协作提问方式的开发者。
Read More提示词优化工具：把模糊需求写成结构化 AI 提示词
SkillHub 社区 Skill「提示词优化工具」（@user_7871dce1/prompt-optimizer-zh，v1.0.0）将模糊需求转为精确、结构化的 AI 提示词，基于 EARS（易用需求规格语法），适用于写作、代码生成与产品功能描述等 prompt 场景；标签 requires_api_key=false。本文说明定位、能力与通过 skillhub CLI 安装到 Cursor/Claude Code/Codex 等 skills 目录的步骤，并给出与官方简介一致的使用方式与注意事项。
Read MoreVibe Coding 架构师：写代码前先锁定架构并转成 Prompt
Vibe Coding 架构师是 SkillHub dev-programming 类 Agent Skill，强调在编码前用结构化思维确定架构，再将结论写成后续 AI 编程用的 Prompt。文章介绍其定位、分阶段工作流、基于 skillhub CLI 与官方 install 文档的安装方式（含 Cursor 等 skills 目录），以及新项目/MVP 与技术选型等适用场景；并说明纯 UI 修补、既有项目 bug 修复等不宜触发的情形。官方条目与安装文档链接见文末。
Read MorePrompt Engineering: Writing Agent Prompts as Reusable Engineering Standards
The prompt-engineering skill (v1.0, MIT) in oakoss/agent-skills organizes Chain-of-Thought, ReAct, Tree-of-Thoughts, extended thinking, and tool-call design into installable Agent Skills, with differentiated patterns for Claude 4.x, GPT-4.1, OpenAI o-series models, and multimodal scenarios. The article covers its core principles, pattern quick-reference, common mistakes, and pnpm dlx installation, explains that it suits structured reasoning and Agent workflows rather than simple Q&A or open-ended creative writing, and provides the official GitHub link.
Read Moredsh-tools-plugins: A Toolset for Transforming Vague Instructions into Structured Prompts
The DeepSeek Harness plugin uses the `optimize_prompt` tool to address unstable agent output quality caused by vague input instructions. This tool rewrites short instructions into structured prompts that include Role, Task, Constraints, and Output Format, improving execution determinism. Users can install and configure it via CLI, with support for manual invocation or automatic detection, making it suitable for improving the accuracy of agent task handling.
Read Morecyrus123456/dsh-johari-cognition-quadrant-dialog-composer
Cyrus123456 developed a UI plugin for DeepSeek Harness based on the Johari Window model, designed to structure dialogue context. Using a 2×2 quadrant panel, the plugin helps users distinguish information such as “what I know / AI does not know” and “what I do not know / AI does not know,” and generates structured prompts that are automatically inserted into the input box, addressing issues of missing context and fragmented thinking. Built with TypeScript and React 18, it is easy to install and well suited for developers who need in-depth context organization.
Read More