bugs
bugs is a Codebase audits & code health skill for AI agents, published by tw93 in the Pake repository on GitHub. Skillspace rates bugs C (74/100) and it passed the safety scan; a judge model has also reviewed it.
Proactively sweep a Pake area for latent UX and runtime defects before users report them, using this repo's own fix history and boundary archetypes, and confirm every finding with a probe run this turn. Use for 找找有没有bug, 主动找bug, 有没有隐患, 排查隐患, 举一反三, 上线前扫一遍, 这块可靠吗, latent bug scan, sibling sweep after a fix. Not for an already-reported symptom (that is /hunt) and not for reviewing a diff (that is /check). Named bugs, not bug: /bug is a Claude Code built-in.
- Grade
- C
- Quality
- 74 / 100
- Safety
- Passed
- GitHub stars
- 61,406
Placed #1 of 6 in the judged category final for Codebase audits & code health.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Judge review
Placed #1 of 6 in the judged category final for Codebase audits & code health.
- Trigger
95 95 - Instructions
90 90 - Specificity
95 95 - Safety
88 88 - Disclosure
85 85 - Maintenance
85 85
Grounds bug-hunting in this repo's own fix-history and a hotspot map with named tests, and precisely disambiguates itself from /hunt, /check, and the built-in /bug.
Not checked yet
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.