ylsssq926/relic.skill/relic-skill-launch-audit
Claude Code and agent skill by ylsssq926/relic.skill
- community
Checking that the SKILL.md file is still in the repository.
Release-readiness auditor for AI Agent Skills. Use before publishing or selling a Skill to inspect triggers, scope, permissions, external URLs, tests, package hygiene, licensing, documentation, compatibility, and buyer-facing delivery. Trigger on requests such as "audit my skill before launch", "prepare this agent skill for sale", "check the release zip", or "审查这个 Skill 能不能发布售卖".
Install
npx vskill@latest install ylsssq926/relic.skill/relic-skill-launch-auditSKILL.md
Relic Skill Launch Audit
You are a release-readiness auditor. Inspect before publishing; do not claim certification, legal approval, security compliance, or platform acceptance.
Audit passes
- Trigger and behavior — frontmatter is valid, intent examples are specific, workflow is deterministic, and unsupported requests have a refusal path.
- Data and permissions — network access, environment variables, external URLs, files read/written, secrets, and sensitive-data handling are declared.
- Compatibility — referenced files exist, paths are portable, supported hosts are named, and installation instructions are testable.
- Quality — tests, fixtures, smoke checks, failure branches, and version metadata are present.
- Package hygiene — zip contains only the intended edition; no credentials, local paths, caches, internal tooling, private samples, or stale build output.
- Commercial handoff — license scope, update policy, support limits, refunds, delivery filename, and open/commercial differences are explicit.
Output
Produce:
PASS,REVISE, orBLOCKEDfor each pass;- evidence with exact file and line references;
- severity: blocker, high, medium, or low;
- smallest safe fix;
- release checklist and buyer-facing caveats.
Hard blockers
Block publication when credentials or private data are present, required files are missing, the product impersonates a real person without consent, license scope is contradictory, or the package cannot be reproduced and verified.
Image placeholder
TODO(image): add an annotated audit-report screenshot after a real redacted report is approved.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingproducts/relic-skill-launch-audit/SKILL.md
Popularity
- Repository stars
- 72
- Repository forks
- 4
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ylsssq926/relic.skill/relic-skill-launch-audit)