rmslop

Remove AI code slop

Quality

66%

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 ./.cursor/skills/rmslop/SKILL.md

Quality

Content

80%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.

The body is an exemplary lean, single-purpose instruction skill: concrete slop categories, an explicit reporting contract, and no wasted tokens. Its only real weakness is the absence of any validation step for what is a branch-wide batch of code edits, which the rubric caps at workflow clarity 3.

Suggestions

Add a verification step after the edits (e.g., run the project's tests or typecheck to confirm nothing broke) to lift workflow clarity above the destructive/batch cap of 3.

Include the concrete command for the first step, e.g., `git diff main...HEAD`, so the entry point is fully executable.

Dimension	Reasoning	Score
Conciseness	The body ("Check the diff against main, and remove all AI generated slop introduced in this branch" plus a five-bullet list) is lean with zero padding and fully assumes Claude's competence; every token earns its place, matching the anchor-5 example's economy.	5 / 5
Actionability	Concrete, actionable guidance throughout — specific slop categories ("Casts to any to get around type issues", "Extra defensive checks or try/catch blocks") and an explicit output contract ("only a 1-3 sentence summary") — but no exact command for checking the diff against main, leaving a minor gap versus fully executable guidance.	4 / 5
Workflow Clarity	A rough sequence exists (check diff against main → remove slop → report summary), but this is a batch of code edits across a branch with no validation or verification step (e.g., run tests/lint, confirm behavior unchanged); the rubric explicitly caps workflow clarity at 3 for destructive/batch operations lacking validation.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references and is well organized (overview paragraph, categorized bullet list, closing reporting instruction), which the rubric says can score 5 for simple skills.	5 / 5
	Total	17 / 20 Passed

Description

53%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 is concise and names a distinct, recognizable niche, but it is bare-bones: a single action with no 'when to use' guidance and no natural trigger phrases beyond the skill's own jargon. Adding a 'Use when...' clause and one or two user-facing trigger terms would move it from adequate to strong.

Suggestions

Add an explicit trigger clause, e.g., "Use when reviewing a branch of AI-generated code or when the user mentions slop, AI-generated artifacts, or cleaning up a diff."

Name 1-2 concrete actions or targets in the description (e.g., "Remove unnecessary comments, defensive checks, and `any` casts introduced by AI") to raise specificity.

Include natural synonyms users would actually say ("AI-generated code", "slop", "cleanup") to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	"Remove AI code slop" names the domain and one concrete action (remove), matching the '1-2 concrete actions but not comprehensive' anchor; it does not enumerate what counts as slop, keeping it below 4.	3 / 5
Completeness	There is a clear 'what' ("Remove AI code slop") but no 'when' clause or trigger guidance whatsoever; the rubric explicitly caps completeness at 3 for a missing 'Use when...' equivalent.	3 / 5
Trigger Term Quality	Keywords "AI", "code", and "slop" are relevant, but common natural variations users would say (e.g., "AI-generated code", "clean up slop", "tidy the diff") are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"AI code slop" carves out a fairly distinct niche that is unlikely to fire for unrelated skills, though it has minor overlap risk with general code-review and cleanup skills, matching anchor 4 rather than the clear-niche anchor 5.	4 / 5
	Total	13 / 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
description_field	'description' is very short (19 chars), consider making it more detailed	Warning

	Total	15 / 16 Passed

Repository: revokslab/ShipFree
Path: .cursor/skills/rmslop/SKILL.md
Commit: 94c4be7

Reviewed: 7 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.