cleanup

Run all code quality skills — effects, memo, callbacks, state, React Query, emcn design review, url-state, and comments — analyzing in parallel, then applying fixes sequentially

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/cleanup/SKILL.md

Quality

Content

67%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-structured orchestration skill with concrete invocations, explicit dependency ordering, and a real validation step; its main weaknesses are moderate verbosity from repeated rationale and a couple of minor validation/organization gaps.

Suggestions

State the effects→...→comments dependency order once and reference it, instead of repeating it in Step 2, Step 3, and the rationale prose, to tighten conciseness.

Add an explicit lint-failure recovery loop (e.g. 'If `bun run lint:check` fails, read the errors, fix, and re-run until it passes') to complete the validation feedback loop.

Consider moving the Boundary Audit Guidance into a short referenced section or trimming it to the essential non-negotiables so the main workflow stays the focus.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and information-dense, but the dependency order is stated three times and rationale such as 'this is what makes the ordering real' and the comments-last explanation restate earlier points, so it could be tightened; not a 4 due to these repeated justifications.	3 / 5
Actionability	Provides concrete slash-command invocations for all eight passes and a literal lint command (`bun run lint:check`), but the edit-application step is described procedurally rather than as copy-paste code, leaving a minor gap versus a 5.	4 / 5
Workflow Clarity	Clear four-step sequence with explicit pass ordering, a snapshot-relative re-derive feedback loop, and a final lint validation; capped below 5 because the lint-failure recovery path is not spelled out and there is no per-pass checkpoint.	4 / 5
Progressive Disclosure	Well-organized single-file structure with clear Step headers and no nested references; the Boundary Audit Guidance section is somewhat tangential at the end and the ~60-line body could arguably split that guidance out, keeping it just below 5.	4 / 5
	Total	15 / 20 Passed

Description

58%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.

The description clearly conveys what the skill does and names its constituents concretely, but it lacks any explicit "when to use" trigger guidance and omits natural user-facing trigger phrases. Adding a Use-when clause would lift the two capped dimensions.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when the user asks to clean up, refactor, or run code-quality checks across their changes.'

Include common user phrasings ('clean up my code', 'review my changes', 'refactor') alongside the technical skill names to improve trigger-term coverage.

Briefly state the outcome (e.g. 'consolidates proposals and applies non-conflicting fixes in dependency order') so the value proposition is explicit.

Dimension	Reasoning	Score
Specificity	Lists eight concrete sub-skills by name and two concrete actions ("analyzing in parallel, then applying fixes sequentially"), giving several specific actions with only minor coverage gaps; not a 5 because it does not enumerate what each pass actually inspects.	4 / 5
Completeness	The "what" is clear (run eight skills in parallel, apply fixes sequentially) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Relevant keywords appear ("code quality skills", effects, memo, callbacks, React Query) but natural user phrases like "clean up", "refactor", or "review my changes" are absent and synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	Orchestrating eight named skills is a distinct niche with minimal conflict risk, though a user requesting a single check (e.g. just "review my effects") could overlap with one of the sub-skills, keeping it just below 5.	4 / 5
	Total	14 / 20 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: simstudioai/sim
Path: .agents/skills/cleanup/SKILL.md
Commit: 417ae20

Reviewed: 3 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.