P

ponytail-audit

by @dietrichgebertv
4.7(120)

This skill audits an entire code repository to identify and rank over-engineered sections. It helps developers find and remove dead code, simplify complex implementations, or replace them with standard library/native features. By providing a prioritized list of optimization suggestions, this Skill significantly enhances the efficiency and accuracy of code reviews, effectively reducing technical debt and improving code quality, maintainability, and long-term project health.

code-auditrefactoringcode-qualitysimplificationover-engineeringGitHub
Installation
npx skills add https://github.com/dietrichgebert/ponytail --skill ponytail-audit
compare_arrows

Before / After Comparison

1 组
Before

Before this skill, developers or teams spent significant time on manual code reviews, line by line, to find over-engineered, redundant, or simplifiable code, which was time-consuming and prone to missing key optimization opportunities.

After

This skill automates the scanning of the entire code repository, quickly identifying and ranking over-engineered sections. It significantly reduces the time spent on manual audits and ensures more comprehensive coverage, improving code quality and maintenance efficiency.

SKILL.md

ponytail-review, repo-wide. Scan the whole tree instead of a diff. Rank findings biggest cut first.

Tags

Same as ponytail-review:

  • delete: dead code, unused flexibility, speculative feature. Replacement: nothing.
  • stdlib: hand-rolled thing the standard library ships. Name the function.
  • native: dependency or code doing what the platform already does. Name the feature.
  • yagni: abstraction with one implementation, config nobody sets, layer with one caller.
  • shrink: same logic, fewer lines. Show the shorter form.

Hunt

Deps the stdlib or platform already ships, single-implementation interfaces, factories with one product, wrappers that only delegate, files exporting one thing, dead flags and config, hand-rolled stdlib.

Output

One line per finding, ranked: <tag> <what to cut>. <replacement>. [path]. End with net: -<N> lines, -<M> deps possible. Nothing to cut: Lean already. Ship.

Boundaries

Scope: over-engineering and complexity only. Correctness bugs, security holes, and performance are explicitly out of scope. Route them to a normal review pass. Lists findings, applies nothing. One-shot. "stop ponytail-audit" or "normal mode" to revert.

User Reviews (0)

Write a Review

Effect
Usability
Docs
Compatibility

No reviews yet

Statistics

Installs43.1K
Rating4.7 / 5.0
Version
Updated2026年10月23日
Comparisons1

User Rating

4.7(120)
5
37%
4
43%
3
13%
2
5%
1
2%

Rate this Skill

0.0

Compatible Platforms

🤖claude-code

Timeline

Created2026年6月25日
Last Updated2026年10月23日
🎁 Agent Knowledge Cards
Survey