jetpack-compose-audit

Audit Android Jetpack Compose repositories for performance, state management, side effects, and composable API quality. Scans source code, scores each category from 0-10, writes a strict markdown report, and summarizes the most important fixes. Use when reviewing a Compose codebase, rating repository quality, inspecting recomposition/state issues, or running a Compose audit.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-5

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

A well-engineered, highly actionable audit skill: clear sequenced workflow with validation and fallbacks, copy-paste commands, and clean progressive disclosure into real bundle files. The only weakness is mild redundancy between the When-To-Use trigger list, Audit Principles, and What To Avoid.

Suggestions

Trim the "When To Use" trigger-phrase bullets, since the same triggers already appear in the frontmatter description — keep only any net-new triggers not already covered.

Consolidate "Audit Principles" and "What To Avoid" where they overlap (e.g., evidence-based scoring vs. generic-checklist warning) to remove duplicated guidance.

The "Out Of Scope In v1" list is thorough; consider folding the shorter scope bullets into the existing material-3 deferral note to tighten the opening.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly earns its place (init-script injection, ceiling-check math, fallback logic, exact file paths), but the "When To Use" trigger-phrase list largely duplicates the frontmatter description and "What To Avoid" overlaps "Audit Principles" — minor instances that could be trimmed, placing it at the 4 anchor rather than the 5 anchor's "every token earns its place".	4 / 5
Actionability	Copy-paste-ready commands appear throughout — `rg -l 'com\.android\.application' -g '.gradle'`, ordered gradle tasks, the `--init-script` build invocation, the `find ... -name '*-classes.txt'` collector, and a concrete ceiling-math example — covering both the success and fallback cases as the 5 anchor requires.	5 / 5
Workflow Clarity	A clearly sequenced 9-step process with explicit validation (Step 1 fast-fail, Step 6 "Verify Findings" before deducting, Step 7 mandatory ceiling check, Step 8 no-silent-overwrite) and feedback loops (Step 4 build-failure fallback with confidence downgrade), matching the 5 anchor; the destructive/batch cap does not apply because validation is present.	5 / 5
Progressive Disclosure	SKILL.md acts as an overview pointing one level deep to real, substantive bundle files (references/scoring.md, search-playbook.md, report-template.md, canonical-sources.md, diagnostics.md and scripts/compose-reports.init.gradle — all verified present, 1071 lines total), each clearly signaled inline and in a final References section, matching the 5 anchor.	5 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

A strong description: third-person voice, explicit "Use when" trigger clause, multiple concrete actions, and a clearly distinct Compose-audit niche. No first/second-person voice issues and no vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across four named categories — "Scans source code, scores each category from 0-10, writes a strict markdown report, and summarizes the most important fixes" — giving comprehensive coverage of the skill's capabilities, matching the score-5 anchor rather than the 4 anchor's "minor gaps".	5 / 5
Completeness	Explicitly answers both what (audit/scan/score/report/summarize) and when (a dedicated "Use when..." clause with concrete trigger phrases), squarely matching the 5 anchor; the 4 anchor's "when could be more explicit" does not apply here.	5 / 5
Trigger Term Quality	The "Use when reviewing a Compose codebase, rating repository quality, inspecting recomposition/state issues, or running a Compose audit" clause supplies natural synonyms (audit, review, rate, inspect) a user would actually say; it is not below the 5 anchor since coverage is comprehensive for this domain.	5 / 5
Distinctiveness Conflict Risk	The narrow "Android Jetpack Compose" audit niche with its four specific categories and explicit deferral to a separate material-3 skill gives it a clear niche with minimal conflict risk, matching the 5 anchor.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: oxyroid/M3UAndroid
Path: .claude/skills/jetpack-compose-audit/SKILL.md
Commit: 650d06b

Reviewed: 13 days 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.