ponytail-review

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

Updated Jul 3, 2026
One-click install
npx skills add https://github.com/CHENHUI-X/toolbox --skill ponytail-review-chenhui-x
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ponytail-review
Source: https://github.com/CHENHUI-X/toolbox/tree/main/codex-skill/codex/ponytail-review
Command: npx skills add https://github.com/CHENHUI-X/toolbox --skill ponytail-review-chenhui-x

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Codebases accumulate unnecessary complexity: reinvented standard library functions, speculative abstractions, unused dependencies, and dead flexibility. This Skill performs a focused review pass that hunts only over-engineering, telling you exactly what to cut and what replaces it. ## Core Features & Use Cases - Complexity-Only Review: Flags dead code, hand-rolled stdlib equivalents, unneeded dependencies, and speculative abstractions, while explicitly excluding correctness, security, and performance concerns. - One-Line Findings: Each finding uses a compact tagged format (delete, stdlib, native, yagni, shrink) with the location, what to cut, and the replacement. - Net-Line Scoring: Ends every review with the total lines that could be removed, or confirms the diff is already lean. - Use Case: After opening a pull request, ask for an over-engineering review to discover that a 27-line validator class can be replaced by a single standard library call. ## Quick Start Ask the AI to review this diff for over-engineering and tell me what can be deleted.

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 flags dead code, hand-rolled stdlib equivalents, unneeded dependencies, and speculative abstractions. Each finding is one line with the location, what to cut, and what replaces it.

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

Over-engineering review only hunts unnecessary complexity: what to delete or simplify. Correctness bugs, security holes, and performance issues are explicitly out of scope and belong in a standard correctness-focused review pass.

Does this review apply the suggested fixes automatically?

No, it only lists findings with locations and suggested replacements. It does not modify the code, so you decide which simplifications to apply.

When should I not use an over-engineering review?

Skip it when you need correctness, security, or performance feedback, since those are out of scope. It also never flags minimal tests or assert-based self-checks, treating them as the acceptable minimum rather than bloat.

What kinds of findings does a complexity review report?

Findings use five tags: delete for dead code, stdlib for reinvented standard library functions, native for dependencies duplicating platform features, yagni for speculative abstractions, and shrink for logic expressible in fewer lines.