Skills for Real Engineers. Straight from my .agents directory.
ponytail-audit
Agent skill fromDietrichGebert/ponytail
Quality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.
How to install ponytail-audit
npx skills add DietrichGebert/ponytail# or add only this skill to Claude Code: copy the folder
.openclaw/skills/ponytail-audit/
# into
~/.claude/skills/ponytail-audit/ (all projects)
.claude/skills/ponytail-audit/ (one project)
1Audit the whole repo like the senior developer who just inherited it and2will be paged when it breaks. Order of importance: correct, safe, holds under3load, tested, fast, lean. Lean still matters: every extra line must be read,4tested and fixed later. This is a report the user asked for, so give it in full.56## 1. Map first78- Audit what the user names: a folder, a package, or the whole repo.9 Nothing named: the whole repo.10- Read the README, the deploy and build config, the dependency list, the11 entry points (main, routes, handlers, jobs, CLI commands) and the tests.12- Find the expected load: one person running a script, or many users and13 processes at once. Judge scale against that, and say which load you assumed.14- Trace the main flows end to end: where data comes in, what is stored,15 what goes out. Read those paths fully: input from users, money, auth,16 data writes, background jobs, anything shared between processes.17- Big repo: go deep where a mistake costs the most, not file by file. Say18 which parts you did not read.1920## 2. Look for21221. **Bug:** wrong result, crash, missed edge case (empty, zero, last item,23 rounding, time zones), callers that disagree with what a function returns,24 the same rule applied differently in two places.252. **Risk:** security holes (injection, weak randomness, secrets in code,26 missing checks on input from users), data loss (errors swallowed, writes27 in the wrong order, no transaction).28…
Excerpt shown under the repository's MIT license.
More skills in ponytail
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Production-grade engineering skills for AI coding agents.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
The open-source app everyone uses to manage agents at work
New AI tools and agent skills, once a week
The tools added to Tooluck that week, the newest skills for Claude Code, Codex and Cursor, and one side-by-side comparison. No spam, unsubscribe anytime.
