ponytail--ponytail-review

Reviews code diffs for over-engineering and lists deletable complexity with replacements.

Updated Dec 3, 2025
One-click install
npx skills add https://github.com/hhenrichsen/dots --skill ponytail-ponytail-review-hhenrichsen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ponytail--ponytail-review
Source: https://github.com/hhenrichsen/dots/tree/main/dot_skills/ponytail/ponytail-review
Command: npx skills add https://github.com/hhenrichsen/dots --skill ponytail-ponytail-review-hhenrichsen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Codebases accumulate unnecessary complexity: hand-rolled utilities duplicating the standard library, speculative abstractions with a single implementation, and dependencies that replicate native platform features. This Skill reviews diffs exclusively for over-engineering and tells you exactly what to delete. ## Core Features & Use Cases - Complexity-Only Review: Flags dead code, reinvented stdlib functions, unneeded dependencies, and speculative abstractions, while explicitly excluding correctness, security, and performance concerns. - One-Line Findings: Each finding uses a tagged format (delete, stdlib, native, yagni, shrink) with location, what to cut, and what replaces it. - Net-Line Scoring: Ends every review with a single metric estimating how many lines can be removed. - 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 one-line check, or that moment.js can be swapped for Intl.DateTimeFormat with zero dependencies. ## Quick Start Ask the AI to review this diff for over-engineering and tell me what can be deleted.

Frequently Asked Questions about ponytail--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 on the diff to get one-line findings tagged as delete, stdlib, native, yagni, or shrink. Each finding states the location, what to cut, and what replaces it, ending with a net-lines-removable score.

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

Over-engineering review hunts only unnecessary complexity: dead code, speculative abstractions, and redundant dependencies. Correctness bugs, security holes, and performance issues are explicitly out of scope and belong in a standard review pass.

Can this review detect unnecessary dependencies in my code?▼

Yes, findings tagged native flag dependencies that duplicate platform features, such as importing moment.js for one format call when Intl.DateTimeFormat works with zero dependencies. The replacement is named in each finding.

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

No, it only lists findings and never modifies code. Each finding describes what to cut and its replacement, but applying the changes is left to the developer or a separate editing step.

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

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