I built a governance layer for AI agent skills — with an AI agent as my pair programmer

Short summary

The author built skill-governance-toolkit, a reference implementation for governing AI agent skills across Claude Code, Copilot, Cursor, Codex CLI, and Gemini CLI. It includes six meta-skills (find, evaluate, compare, audit, build-portable, integrate) plus a deterministic audit engine deliverable as CLI, MCP tool, or Docker image. The project shipped 42 versioned releases in 18 days, with Claude Code writing most code while the author made architecture decisions.

• •skill-governance-toolkit provides scoring, auditing, and portability checks for AGENTS.md and SKILL.md files
• •Six meta-skills operate on other skills; deterministic audit engine ships as CLI, MCP, or Docker
• •Cross-runtime by design: works on Claude Code, Copilot, Cursor, Codex CLI, and Gemini CLI

Generated with AI, which can make mistakes.