skill-cleaner

Codex/OpenClaw skill audit: live budget, usage, duplicates, compact descriptions.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-cleaner/SKILL.md

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 lean, executable, and well-structured, with concrete commands, a clear sequenced workflow that includes verification steps for destructive skill deletion, and appropriate one-level-deep references to the script bundle. It avoids teaching concepts Claude already knows.

Dimension	Reasoning	Score
Conciseness	The body is dense and lean — concrete commands and terse Analyzer Notes that encode non-obvious Codex internals Claude would not know (e.g. render.rs rules, models_cache.json) — without explaining concepts Claude already knows, matching the score-3 anchor.	3 / 3
Actionability	It provides fully executable, copy-paste-ready commands ("node --experimental-strip-types skills/skill-cleaner/scripts/skill-cleaner.ts --months 3") plus useful variants and a concrete report reading order, matching the score-3 anchor.	3 / 3
Workflow Clarity	A clear 3-step sequence (run analyzer, read report in order, verify before deleting/editing) includes explicit validation checkpoints ("Verify the kept copy exists and is loaded", confirm disposability before deletes) for a destructive workflow, matching the score-3 anchor.	3 / 3
Progressive Disclosure	The SKILL.md is a well-organized overview (Workflow, Analyzer Notes, Output Policy) with the heavy logic split into the referenced scripts/skill-cleaner.ts bundle file at one level of depth, matching the score-3 anchor.	3 / 3
	Total	12 / 12 Passed

Description

50%

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 tooling-scoped but terse, naming audit domains without an explicit "Use when..." trigger clause. It is clear enough to be distinct but lacks the trigger guidance and action breadth for top scores.

Suggestions

Add an explicit "Use when..." clause naming natural triggers, e.g. "Use when trimming skill prompt budget, finding duplicate skills, or auditing enabled/disabled skill roots."

Replace topic nouns with concrete actions where possible (e.g. "audit live budget, detect duplicate skills, compact verbose descriptions").

Broaden trigger-term coverage with common phrasings users actually say, such as "find duplicate skills" or "which skills to remove".

Dimension	Reasoning	Score
Specificity	Quotes "budget, usage, duplicates, compact descriptions" name concrete audit domains with the verb "audit", but these are topics rather than a list of multiple specific concrete actions, matching the score-2 anchor rather than score 3.	2 / 3
Completeness	It states what the skill does ("Codex/OpenClaw skill audit: live budget, usage, duplicates, compact descriptions") but has no "Use when..." or equivalent explicit trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like "skill audit", "budget", "usage", "duplicates" are ones a user might say, but coverage is terse and missing common variations, fitting the score-2 anchor of some relevant keywords.	2 / 3
Distinctiveness Conflict Risk	The "Codex/OpenClaw skill audit" niche is fairly distinct, but the terse domains (budget, usage, duplicates) could still overlap with generic skill-management tooling, matching the score-2 anchor.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: steipete/agent-scripts
Path: skills/skill-cleaner/SKILL.md
Commit: bb36883

Reviewed: about 13 hours 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.