deslop

Remove AI-generated code slop from a branch or diff. Use after writing or generating code to strip unnecessary comments, defensive checks, `any` casts, and style that does not match the surrounding file. For prose and markdown, use the humanizer skill instead.

Quality

92%

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

85%

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

A well-scoped, well-organized skill that is concise and clearly sequenced for a single task with a built-in verification loop. Its one real gap is the absence of a concrete before/after edit example, which would make the removal guidance fully actionable.

Suggestions

Add a short before/after code diff (e.g. an over-commented defensive block and its cleaned-up form) under 'What to remove' so the transformations are concrete and copy-paste ready.

Optionally make the implicit process explicit with a short numbered sequence (review diff for tells → surgical edits → run format/lint/tests → report summary) so the workflow is sequenced rather than implied by section order.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is lean and assumes Claude's competence — it names patterns ('comments a human would not add', 'casts to `any` used only to bypass a type error') without explaining what comments or types are, and every bullet earns its place.	3 / 3
Actionability	Guidance is specific in categories and includes one concrete command ('pnpm format && pnpm lint:fix'), but a code-editing skill lacks any before/after example showing an actual slop removal, leaving it short of copy-paste-ready; this matches the 'concrete guidance but incomplete / missing key details' anchor rather than a 2-below vague level.	2 / 3
Workflow Clarity	As a simple single-task skill the action is unambiguous, and the Guardrails supply an explicit verification step ('run pnpm format && pnpm lint:fix and let the tests pass') plus a fix-root-cause feedback loop, qualifying for the simple-skill exception to score 3.	3 / 3
Progressive Disclosure	Under 50 lines with no external references needed and no bundle files present; the body is organized into clear sections (When to use, What to remove, Guardrails, Related skills) with a one-level link to the humanizer skill, meeting the simple-skill criterion for a top score.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 tight, specific description that answers what, when, and how it differs from the adjacent humanizer skill. Voice is imperative/third person with no padding or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'strip unnecessary comments, defensive checks, `any` casts, and style that does not match the surrounding file' — matching the anchor for naming several specific concrete actions.	3 / 3
Completeness	Clearly states what ('Remove AI-generated code slop from a branch or diff') and an explicit when ('Use after writing or generating code to strip...'), satisfying the both-what-and-when anchor with an explicit trigger clause.	3 / 3
Trigger Term Quality	Natural developer terms a user would actually say appear throughout: 'AI-generated code slop', 'branch or diff', 'writing or generating code', giving good coverage of colloquial and technical triggers.	3 / 3
Distinctiveness Conflict Risk	The code-vs-prose boundary is explicit — 'For prose and markdown, use the humanizer skill instead' — carving a clear niche unlikely to trigger the wrong skill.	3 / 3
	Total	12 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: kubb-labs/kubb
Path: .agents/skills/deslop/SKILL.md
Commit: 8349acf

Reviewed: 2 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.