ponytail-review

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

Updated May 24, 2026
One-click install
npx skills add https://github.com/MWest2020/skill-forge --skill ponytail-review-mwest2020
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ponytail-review
Source: https://github.com/MWest2020/skill-forge/tree/main/skills/ponytail-review
Command: npx skills add https://github.com/MWest2020/skill-forge --skill ponytail-review-mwest2020

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Codebases accumulate unnecessary complexity: reinvented standard library functions, unneeded dependencies, speculative abstractions, and dead flexibility. This Skill performs a review pass focused exclusively on finding what to cut, complementing correctness-focused reviews. ## Core Features & Use Cases - Over-Engineering Detection: Flags dead code, hand-rolled stdlib equivalents, redundant dependencies, single-implementation abstractions, and verbose logic. - One-Line Findings: Each finding follows a strict format with location, tag (delete, stdlib, native, yagni, shrink), what to cut, and what replaces it. - Net-Line Scoring: Ends every review with a single metric estimating how many lines can be removed, or reports "Lean already. Ship." when nothing can be cut. - 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. ## Quick Start Ask the assistant to review this diff for over-engineering and tell me what can be deleted or simplified.

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?

Invoke the review with a phrase like "review for over-engineering" or "what can we delete" along with a diff. The output lists one finding per line with a tag, location, what to cut, and the simpler replacement, ending with a net line-reduction estimate.

What kinds of complexity does an over-engineering review find?

It finds five categories: dead code and unused flexibility (delete), hand-rolled logic the standard library ships (stdlib), dependencies duplicating platform features (native), abstractions with one implementation (yagni), and verbose logic with a shorter equivalent (shrink).

Does this review also catch bugs and security issues?

No. Correctness bugs, security holes, and performance problems are explicitly out of scope and belong to a normal review pass. This review only hunts unnecessary complexity and never flags a minimal smoke test as bloat.

Can the review apply the suggested deletions automatically?

No. The review only lists findings with locations and suggested replacements; it does not modify the code. You apply the changes yourself or in a separate editing step.

When should I not use an over-engineering review?

Skip it when you need correctness, security, or performance analysis, since those are excluded by design. It is also unnecessary for already-lean diffs, where it will simply report "Lean already. Ship."