ponytail-review

Reviews code diffs for over-engineering and lists what to delete or simplify.

2|Updated Jan 26, 2026
One-click install
npx skills add https://github.com/Nzettodess/Awesome-Agent-Skills --skill ponytail-review-nzettodess
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ponytail-review
Source: https://github.com/Nzettodess/Awesome-Agent-Skills/tree/main/Skills/Development/ponytail-review
Command: npx skills add https://github.com/Nzettodess/Awesome-Agent-Skills --skill ponytail-review-nzettodess

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often focus on correctness while ignoring accumulated complexity: reinvented standard library functions, unnecessary dependencies, speculative abstractions, and dead flexibility. This Skill performs a review pass dedicated exclusively to finding what can be deleted or shrunk, keeping diffs lean. ## Core Features & Use Cases - Complexity-Only Review: Hunts over-engineering with five tagged finding types: delete, stdlib, native, yagni, and shrink, each with a concrete replacement suggestion. - One-Line Findings: Outputs terse findings in the format L<line>: <tag> <what>. <replacement>., ending with a net line-reduction score. - Clear Boundaries: Explicitly excludes correctness, security, and performance issues, routing them to a normal review pass, and never flags minimal smoke tests as bloat. - Use Case: After writing a pull request, ask for an over-engineering review to discover that a 27-line validator class can be replaced by a one-line check, or that moment.js can be swapped for Intl.DateTimeFormat with zero dependencies. ## Quick Start Review this diff for over-engineering and tell me what we can delete or simplify.

Frequently Asked Questions about ponytail-review

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

FAQPage Schema
How do I review code for over-engineering?▼

Run an over-engineering review pass on the diff that looks for reinvented standard library functions, unnecessary dependencies, speculative abstractions, and dead code. Each finding names the location, what to cut, and what replaces it, ending with a net line-reduction count.

What is the difference between over-engineering review and normal code review?▼

An over-engineering review only hunts complexity: dead code, unneeded abstractions, and replaceable dependencies. Correctness bugs, security holes, and performance issues are explicitly out of scope and belong in a standard correctness-focused review pass.

What kinds of findings does an over-engineering review produce?▼

Findings use five tags: delete for dead code, stdlib for hand-rolled standard library equivalents, native for platform-built-in replacements, yagni for speculative abstractions, and shrink for logic expressible in fewer lines.

Does the over-engineering review apply the suggested fixes automatically?▼

No, it only lists findings with locations and suggested replacements. The developer decides which simplifications to apply, keeping the review read-only and safe to run on any diff.

When should I not use an over-engineering focused review?▼

Avoid it when you need correctness, security, or performance feedback, since those are explicitly out of scope. It also treats a minimal smoke test or assert-based self-check as necessary, never as bloat to remove.