ponytail-audit
ponytail-audit is a Codebase audits & code health skill for AI agents, published by DietrichGebert in the ponytail repository on GitHub. Skillspace rates ponytail-audit C (74/100) and it passed the safety scan; a judge model has also reviewed it.
Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.
- Grade
- C
- Quality
- 74 / 100
- Safety
- Passed
- GitHub stars
- 137,112
Placed #4 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 #4 of 6 in the judged category final for Codebase audits & code health.
- Trigger
76 76 - Instructions
80 80 - Specificity
79 79 - Safety
91 91 - Disclosure
86 86 - Maintenance
76 76
Clean tag taxonomy and ranked output with honest scope limits (correctness and security explicitly out of scope), but thinner on concrete search commands than its ponytail-debt sibling.
Same terse, well-scoped over-engineering audit as its twin, but with a clean, valid one-line description.
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.