ponytail-audit

Audit the whole repo for over-engineering. A ranked list of what to delete, simplify, or replace with stdlib or native features.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a tight, well-structured instruction set: concrete tags, a precise output format, a hunt checklist, and explicit scope boundaries. It is appropriately lean for a simple skill and needs no external references.

Dimension	Reasoning	Score
Conciseness	Every line earns its place with no concept explanations or padding — tag definitions, a hunt checklist, and an exact output format — assuming Claude's competence throughout.	3 / 3
Actionability	Provides concrete, copy-ready guidance: defined tags, an exact output line format '<tag> <what to cut>. <replacement>. [path]', and a net summary; the absence of code is justified for this instruction-only skill.	3 / 3
Workflow Clarity	As a simple single-purpose skill the action is unambiguous (scan whole tree, rank, emit one line per finding), so per the simple-skill scoring note it earns a 3 without needing validation checkpoints.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external references and well-organized sections (Tags, Hunt, Output, Boundaries), meeting the simple-skill criterion for a top progressive_disclosure score.	3 / 3
	Total	12 / 12 Passed

Description

62%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and lean about what the skill does, but omits an explicit 'Use when...' trigger and lacks the natural phrasings a user would actually say, capping trigger quality and completeness. It risks some overlap with broader code-review skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to simplify code, cut over-engineering, or reduce complexity across a repo.'

Include natural user phrasings like 'too complex', 'over-engineered', 'too much abstraction', or 'YAGNI' to improve trigger-term coverage.

Sharpen distinctiveness by contrasting with normal review (e.g. 'over-engineering only — not correctness or security').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'what to delete, simplify, or replace with stdlib or native features' — matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	It clearly states what the skill does, but lacks an explicit 'Use when...' trigger clause; per the guideline, a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	'over-engineering' and 'stdlib or native features' are relevant terms, but common natural variations a user would say (e.g. 'too complex', 'simplify my code', 'YAGNI', 'too much abstraction') are missing.	2 / 3
Distinctiveness Conflict Risk	The over-engineering/simplification niche is somewhat specific, but it could still overlap with general code-review or refactoring skills without a sharper distinguishing trigger.	2 / 3
	Total	9 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: DietrichGebert/ponytail
Commit: 14a0d79

Reviewed: about 1 hour ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.