skills.rest
amanpal3
amanpal3COMMUNITY
Explore all skills by this author →
GitHub

ponytail-audit

Audits an entire repository for over-engineering and ranks code to delete or simplify.

1|Updated Sep 3, 2026
Search Tags:#code review#refactoring#code audit#dead code#simplification#over-engineering#repository analysis
One-click install
npx skills add https://github.com/amanpal3/SKILLs --skill ponytail-audit-amanpal3
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ponytail-audit
Source: https://github.com/amanpal3/SKILLs/tree/main/.agent/plugins/ponytail/.openclaw/skills/ponytail-audit
Command: npx skills add https://github.com/amanpal3/SKILLs --skill ponytail-audit-amanpal3

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Codebases accumulate dead code, speculative abstractions, and hand-rolled utilities that duplicate the standard library. This Skill scans the whole repository and produces a ranked list of what to delete, simplify, or replace with stdlib or native platform features. ## Core Features & Use Cases - Repo-wide over-engineering audit: Scans the entire tree instead of a single diff and ranks findings biggest cut first. - Tagged findings: Classifies each finding as delete, stdlib, native, yagni, or shrink with a concrete replacement suggestion. - Net impact summary: Ends with an estimate of removable lines and dependencies, e.g. net: -300 lines, -2 deps possible. - Use Case: Before a major refactor, run the audit to find single-implementation interfaces, one-product factories, dead config flags, and wrappers that only delegate, then cut them in priority order. ## Quick Start Ask the agent to run ponytail-audit on this repository and list the top over-engineering findings ranked by biggest cut first.

Frequently Asked Questions about ponytail-audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find over-engineered code in my repository?▼

Run a repo-wide audit that scans the whole tree and ranks findings biggest cut first. Each finding is tagged as delete, stdlib, native, yagni, or shrink, with a concrete replacement such as a named standard library function.

What kinds of code smells does a complexity audit detect?▼

It targets dead code, unused flexibility, single-implementation interfaces, factories with one product, wrappers that only delegate, dead config flags, and hand-rolled utilities the standard library already ships.

Does the audit fix or modify the code it flags?▼

No. It only lists findings and applies nothing. The output is a ranked one-line-per-finding report ending with a net estimate of removable lines and dependencies, leaving all changes to the developer.

Does the over-engineering audit catch bugs or security issues?▼

No. Correctness bugs, security holes, and performance problems are explicitly out of scope and should be routed to a normal code review pass. The audit covers complexity and over-engineering only.

When should I run a repo-wide audit instead of a diff review?▼

Run it before major refactors, dependency cleanups, or release hardening when you want a prioritized deletion list across the whole tree rather than feedback limited to a single change set.

Related Skills

Explore More Software Engineering Skills→
dlwlrmaxdlwlrmax

clonedeps

Clone dependency source repositories into an ignored local workspace for agent inspection.

Community
Intermediate
nuttarujnuttaruj
3

simplify-code

Simplify over-engineered or duplicated code while preserving behavior through unchanged tests.

Community
Advanced
0xMerl990xMerl99
1

code-reviewer

Analyze code for bugs, security vulnerabilities, performance issues, and best practices.

Community
Intermediate
Chang-Shih-YungChang-Shih-Yung

health

Aggregate type checker, linter, and test results into a 0-10 composite score.

Community
Advanced