ponytail-review

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

Updated May 26, 2026
One-click install
npx skills add https://github.com/avel123111/triplanio --skill ponytail-review-avel123111
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ponytail-review
Source: https://github.com/avel123111/triplanio/tree/main/.claude/skills/ponytail-review
Command: npx skills add https://github.com/avel123111/triplanio --skill ponytail-review-avel123111

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Codebases accumulate unnecessary complexity: reinvented standard library functions, unused dependencies, speculative abstractions, and dead flexibility. This Skill reviews diffs exclusively for over-engineering and tells you exactly what to cut, keeping code lean. ## Core Features & Use Cases - Complexity-Only Review: Hunts over-engineering while explicitly excluding correctness, security, and performance concerns, which belong to a normal review pass. - Tagged One-Line Findings: Each finding uses a tag (delete, stdlib, native, yagni, shrink) with the location, what to cut, and what replaces it. - Net-Line Scoring: Ends every review with a single metric, net: -<N> lines possible, or reports Lean already. Ship. when nothing can be cut. - Use Case: Before merging a pull request that adds a custom retry wrapper and a new date-formatting dependency, run this review to learn that the retry wrapper is deletable and Intl.DateTimeFormat replaces the dependency. ## 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?

Invoke this review on a diff and it returns one line per finding: location, a tag (delete, stdlib, native, yagni, shrink), what to cut, and what replaces it. It ends with a net-lines-removed score.

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

It finds hand-rolled code the standard library already ships, dependencies duplicating native platform features, abstractions with a single implementation, unused configuration, and dead speculative code.

Does this review catch bugs or security issues?

No. Correctness bugs, security holes, and performance problems are explicitly out of scope and should be routed to a normal review pass. This review only hunts unnecessary complexity.

Will the review apply the suggested deletions automatically?

No. It only lists findings with locations and replacements; it does not modify the code. You decide which suggestions 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 a single smoke test or assert-based self-check, which it considers the minimum, not bloat.