- name
Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add DietrichGebert/ponytail --skill ponytail-audit -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add DietrichGebert/ponytail --skill ponytail-audit -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add DietrichGebert/ponytail --skill ponytail-audit -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add DietrichGebert/ponytail --skill ponytail-audit -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/DietrichGebert/ponytail/tree/HEAD/.openclaw/skills/ponytail-auditFrom the publisher
Audit the whole repo like the senior developer who just inherited it and will be paged when it breaks. Order of importance: correct, safe, holds under load, tested, fast, lean. Lean still matters: every extra line must be read, tested and fixed later. This is a report the user asked for, so give it in full.
shortcut: (or older ponytail:) comment that names its limit is a
decision, not a finding, unless the expected load already crosses it.Very simple English: short sentences, everyday words. Explain a technical term the first time you use it. The reader may never have seen this code.
Start with What this repo does: in two or three sentences, and the load
you assumed.
Then the findings in three groups, most important first, skip empty groups:
Number findings across all groups, so the user can say "fix 2 and 5". At most 20 findings; if you left smaller ones out, say how many. Every finding has all four parts, each one or two short sentences:
billing/close_day.py:L40-52)
datetime.now(ZoneInfo("Europe/Berlin")).date(). One line, nothing else changes.End with:
Verdict: one line: healthy, or what to fix first.Lean: -<N> lines, -<M> dependencies possible. when lean findings exist.Not checked: the parts you did not read or could not run.Nothing found: What this repo does:, then Healthy. Nothing to fix. and
one line on what you checked.
One-shot report, changes no code.
© 2026 Skills Rack.
---name: ponytail-auditdescription: Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most…---# .openclaw/skills/ponytail-audit/SKILL.mdFAQ
Download .openclaw/skills/ponytail-audit/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/DietrichGebert/ponytail.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.