AngChow/requirement-drift-auditor
Claude Code Skill - 以原始需求为基准线审计代码 Git Diff，识别夹带的发散修改，生成本地 Markdown/HTML 审计报告。提测前的人工审查辅助工具。
Claude Code Skill - 以原始需求为基准线审计代码 Git Diff，识别夹带的发散修改，生成本地 Markdown/HTML 审计报告。提测前的人工审查辅助工具。
npx add-skill AngChow/requirement-drift-auditorClaude Code Skill - 以原始需求为基准线审计代码 Git Diff，识别夹带的发散修改，生成本地 Markdown/HTML 审计报告。提测前的人工审查辅助工具。
📊 把 Agent Skill 变成可测、可比、可改进的系统 · 35 个核心概念系统学习 OpenAI Agent Skills Evals 方法论
AutoML for Claude Code — multi-agent skill that designs, runs, and reports ML experiments from a text prompt
Write modern, high-performance C# code using records, pattern matching, value objects, async/await, Span<T>/Memory<T>, and best-practice API design patterns. Emphasizes functional-style programming with C# 12+ features.
Spec-Driven Development as a single Agent Skill
Exercise: Scale Institutional Knowledge Using Copilot Spaces
Automate Dialmycalls tasks via Rube MCP (Composio). Always search tools first for current schemas.