ponytail-review

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

1|Updated Sep 3, 2026
One-click install
npx skills add https://github.com/amanpal3/SKILLs --skill ponytail-review-amanpal3
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ponytail-review
Source: https://github.com/amanpal3/SKILLs/tree/main/.agent/plugins/ponytail/.openclaw/skills/ponytail-review
Command: npx skills add https://github.com/amanpal3/SKILLs --skill ponytail-review-amanpal3

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often focus on correctness while diffs quietly accumulate reinvented stdlib functions, needless dependencies, and speculative abstractions that inflate maintenance cost. This Skill audits a diff purely for unnecessary complexity and tells you exactly what to cut. ## Core Features & Use Cases - Over-Engineering Detection: Flags dead code, hand-rolled stdlib equivalents, redundant dependencies, single-implementation abstractions, and verbose logic using five tags: delete, stdlib, native, yagni, shrink. - One-Line Findings: Outputs each finding as a single line with location, what to cut, and its replacement, ending with a net line-reduction score. - Use Case: Before merging a pull request that adds a custom retry wrapper, a moment.js import for one format call, and an AbstractRepository with one implementation, run this review to get findings like L4: native: moment.js imported for one format call. Intl.DateTimeFormat, 0 deps. ## Quick Start Review this diff for over-engineering and list everything that can be deleted or replaced with standard library features.

Frequently Asked Questions about ponytail-review

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

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

Run this review on the diff to get one line per finding with location, what to cut, and its replacement. Findings use five tags: delete, stdlib, native, yagni, and shrink, ending with a net line-reduction score.

What kinds of code does an over-engineering review flag?▼

It flags dead code and speculative features (delete), hand-rolled logic the standard library ships (stdlib), dependencies duplicating platform features (native), abstractions with one implementation (yagni), and logic expressible in fewer lines (shrink).

Does this review catch bugs or security issues?▼

No. Correctness bugs, security holes, and performance problems are explicitly out of scope and should go through a normal review pass. This review covers only over-engineering and unnecessary complexity.

Will the review suggest deleting tests or smoke checks?▼

No. A single smoke test or assert-based self-check is considered the minimum, not bloat, and is never flagged for deletion. Only genuinely unnecessary code is listed.

Does the review apply the suggested fixes automatically?▼

No. It only lists findings with locations and suggested replacements; it does not modify the code. You decide which cuts to apply and make the changes yourself.