EastDong314/agent-skills

A focused code review skill that hunts down over-engineering: reinvented standard library functions, unnecessary dependencies, speculative abstractions, and dead flexibility. Each finding is a single line with location, what to cut, and what replaces it. Use it when the user asks for an over-engineering review, simplification, or invokes /ponytail-review.

What is agent-skills?

This skill, called the 'Ponytail Review,' is a specialized code review agent that targets over-engineering and unnecessary complexity in code diffs. Unlike a general correctness or security review, this skill explicitly ignores bugs, security holes, and performance issues, instead focusing solely on eliminating wasteful patterns: hand-rolled implementations of standard library functions, unnecessary dependencies, speculative abstractions (YAGNI), dead code, and overly verbose logic. Each finding is formatted as a single line specifying the file and line location, a tag (delete, stdlib, native, yagni, shrink), what to remove, and what simpler replacement to use. The review concludes with a net line count reduction, or 'Lean already. Ship.' if nothing can be cut. The skill supports both single-file and multi-file diffs and can be toggled off with 'stop ponytail-review' or 'normal mode'. It is designed to complement a standard code review by adding a dedicated complexity-focused pass.

Works with~Claude Code~Codex CLI~Cursor

npx skills add https://github.com/EastDong314/agent-skills/tree/HEAD/skills/ponytail-review

Documentation

Review diffs for unnecessary complexity. One line per finding: location, what to cut, what replaces it. The diff's best outcome is getting shorter.

Format

L<line>: <tag> <what>. <replacement>., or <file>:L<line>: ... for multi-file diffs.

Tags:

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.

Examples

❌ "This EmailValidator class might be more complex than necessary, have you considered whether all these validation rules are needed at this stage?"

✅ L12-38: stdlib: 27-line validator class. "@" in email, 1 line, real validation is the confirmation mail.

✅ L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps.

✅ repo.py:L88: yagni: AbstractRepository with one implementation. Inline it until a second one exists.

✅ L52-71: delete: retry wrapper around an idempotent local call. Nothing replaces it.

✅ L30-44: shrink: manual loop builds dict. dict(zip(keys, values)), 1 line.

Scoring

End with the only metric that matters: net: -<N> lines possible.

If there is nothing to cut, say Lean already. Ship. and stop.

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, not this one. A single smoke test or assert-based self-check is the ponytail minimum, not bloat, never flag it for deletion. Does not apply the fixes, only lists them. "stop ponytail-review" or "normal mode": revert to verbose review style.