Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
dietrichgebert avatar

Ponytail Audit

  • 11.1k installs
  • 96k repo stars
  • Updated July 15, 2026
  • dietrichgebert/ponytail

ponytail-audit is an agent skill for Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.

About

Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features. --- name: ponytail-audit description: "Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features." homepage: https://github.com/DietrichGebert/ponytail license: MIT --- 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. - `stdlib:` hand-rolled thing the standard library ships. - `native:` dependency or code doing what the platform already does. - `yagni:` abstraction with one implementation, config nobody sets, layer with one caller. - `shrink:` same logic, fewer lines. ## 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.

  • `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.

Ponytail Audit by the numbers

  • 11,138 all-time installs (skills.sh)
  • +1,448 installs in the week ending Aug 5, 2026 (Skillselion tracking)
  • Ranked #76 of 2,153 Testing & QA skills by installs in the Skillselion catalog
  • Security screen: LOW risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

ponytail-audit capabilities & compatibility

Capabilities
`delete:` dead code, unused flexibility, specula · `stdlib:` hand rolled thing the standard library · `native:` dependency or code doing what the plat · `yagni:` abstraction with one implementation, co · `shrink:` same logic, fewer lines. show the shor
Use cases
documentation
From the docs

What ponytail-audit says it does

--- name: ponytail-audit description: "Audit the whole repo for over-engineering.
SKILL.md
A ranked list of what to delete, simplify, or replace with stdlib or native features." homepage: https://github.com/DietrichGebert/ponytail license: MIT --- ponytail-review, repo-wide.
SKILL.md
## Tags Same as ponytail-review: - `delete:` dead code, unused flexibility, speculative feature.
SKILL.md
npx skills add https://github.com/dietrichgebert/ponytail --skill ponytail-audit

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs11.1k
repo stars96k
Security audit3 / 3 scanners passed
Last updatedJuly 15, 2026
Repositorydietrichgebert/ponytail

When should developers use ponytail-audit and what problem does it solve?

Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.

Who is it for?

Developers working with ponytail-audit patterns described in the skill documentation.

Skip if: Skip when cached docs are empty or the task is outside the skill's documented scope.

When should I use this skill?

Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.

What you get

Grounded guidance and workflows from SKILL.md for ponytail-audit.

  • Ranked over-engineering audit report

Files

SKILL.mdMarkdownGitHub ↗

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.

Related skills

How it compares

Choose ponytail-audit over ponytail-review when the scope is an entire repository health scan rather than reviewing a specific pull request diff.

FAQ

What does ponytail-audit do?

Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.

When should I invoke ponytail-audit?

Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.

Where is the source documentation?

Ground claims in SKILL.md excerpts and linked reference files from the cached docs.

Is Ponytail Audit safe to install?

skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.