Summary
Audits bash test scripts in `tests/manual/` against seven quality dimensions: harness adoption, golden file completeness, config sourcing, fail-fast behavior, template compliance, idempotency, and documentation. It's a specialized L3 worker that scores test evidence quality (X/10) and flags scripts that need rewrites versus ones you can keep. The two-layer detection is smart about context: it won't ding setup scripts for missing golden files or complain about harness adoption when no shared harness exists. Use this when you've got manual test suites producing evidence artifacts and need an audit of whether they're actually reproducible and useful. The severity weighting is reasonable: missing fail-fast or golden files gets flagged HIGH, template divergence is MEDIUM, missing READMEs are LOW.
Install to Claude Code
npx -y skills add levnikolaevich/claude-code-skills --skill ln-636-manual-test-auditor --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
