skill-release-auditlisted

Pre-publish quality and safety auditor for AI agent skills (SKILL.md + scripts/ + references/ format used by Claude Code, Cursor, OpenAI Codex, GitHub Copilot, OpenClaw, ClawHub, and compatible SkillHub registries). Six static-check modules (no LLM, no network by default): (1) syntax and logic correctness, (2) feature completeness, (3) edge-case and error handling, (4) data safety (detects files written inside the skill dir that would be lost on update), (5) dependency declaration vs code, (6) SKILL.md documentation standards. Per-registry rule profiles via `--target`. Pure reporter — never edits your files, never publishes. Use when publishing a skill, modifying an existing skill, or diagnosing why a skill behaves unexpectedly — run it as the last machine-checkable gate before release. Trigger phrases: "skill release audit", "audit before publishing", "pre-release check", "release gate", "skill safety check", "发版前检查", "skill 发布检查", "审查这个 skill 能不能发版".
Songhonglei/build-better-skills · ★ 1 · AI & Automation · score 74

Install: claude install-skill Songhonglei/build-better-skills

# skill-release-audit - **Version**: 1.0.4 - **License**: MIT - **Author**: Evan Song · [github.com/Songhonglei](https://github.com/Songhonglei) - **Repository**: https://github.com/Songhonglei/build-better-skills - **Part of**: [`build-better-skills`](https://github.com/Songhonglei/build-better-skills) suite — see [Stages](https://github.com/Songhonglei/build-better-skills#stages) for the lifecycle map. A six-module static inspector that catches mechanical problems machines can verify — broken Python syntax, undeclared env vars, files written inside the skill dir that would be lost on update, missing README/LICENSE for GitHub targets, mismatched docs and scripts. Pairs with [`glic-check`](https://github.com/Songhonglei/build-better-skills/tree/main/skills/glic-check) which does cognitive UGLIC review; together they cover both layers (see [Part of build-better-skills](#part-of-build-better-skills)). Prints a structured `✅/⚠️/❌` report per module with actionable fixes. **Does not auto-fix.** All fixes require user confirmation. --- ## Agent Behavior Rules (must-read) This skill is an **Auditor, not a Fixer.** After running the check, the agent must follow these rules strictly: 1. **Show the full report first** — every module result, every warning / error with its specific description. 2. **Suggest fixes per finding, but only as suggestions, not actions.** 3. **Wait for explicit user confirmation** before touching any file. 4. **Never modify SKILL.md, scripts/, refer