deslop

Remove AI-generated code slop and clean up code style

Quality

61%

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-team-kit/skills/deslop/SKILL.md

Quality

Content

72%

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

The content is lean, well-organized, and assumes Claude's competence, but it lacks concrete commands and an explicit validation step for verifying behavior is unchanged. Adding a diff command and a verification checkpoint would lift the actionability and workflow-clarity dimensions.

Suggestions

Include a concrete command for inspecting the diff, e.g. `git diff main...HEAD` or `git log main..HEAD`, so the first step is copy-paste ready.

Add an explicit validation/verification step confirming behavior is unchanged (e.g., run the test suite or re-read the diff) before producing the final summary.

Optionally give one short before/after example of a slop pattern and its cleanup to anchor the abstract 'remove slop' direction.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient with no explanation of concepts Claude already knows; every line ('Check the diff against main', the Focus Areas bullets, the Guardrails) earns its place. Not level 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	Gives specific, actionable categories (unnecessary comments, defensive try/catch, casts to `any`, deeply nested code) but stops short of concrete commands like `git diff main...HEAD` or copy-paste-ready examples. Not level 3 because it is not fully executable/copy-paste ready; not level 1 because the guidance is concrete rather than abstract.	2 / 3
Workflow Clarity	The single action (remove slop from the branch diff) is unambiguous and Guardrails constrain behavior, but there is no explicit validation checkpoint confirming behavior is unchanged (e.g., run tests). Not level 3 because validation/feedback loops are missing for code modifications.	2 / 3
Progressive Disclosure	This is a simple skill under 50 lines with no need for external references, and the body is well-organized into Focus Areas and Guardrails sections. Per the simple-skills scoring note this warrants a 3.	3 / 3
	Total	10 / 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 concise and third person with a clear domain, but it omits any explicit 'Use when...' trigger guidance and only partially covers natural trigger terms. It is solid but not exemplary on the completeness and trigger-term dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when cleaning up code on a feature branch or when the user asks to remove AI code slop.'

Include more natural trigger terms users would say, such as 'clean up code', 'remove unnecessary comments', or 'simplify defensive checks'.

Sharpen distinctiveness by leading with the AI-slop-specific framing so it does not compete with general code-quality skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('AI-generated code slop') and concrete actions ('Remove', 'clean up code style') but is not comprehensive — no list of multiple specific concrete actions. It is not level 1 because the actions are concrete rather than vague like 'Helps with documents'.	2 / 3
Completeness	Clearly states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the guidelines. Not level 3 because the 'when' is entirely missing rather than explicit.	2 / 3
Trigger Term Quality	Contains some relevant terms ('code slop', 'code style') but misses common variations a user would naturally say (e.g., 'clean up code', 'remove comments', 'defensive checks'). Not level 3 due to limited coverage of natural terms.	2 / 3
Distinctiveness Conflict Risk	The 'AI-generated code slop' framing is a fairly distinct niche, but 'clean up code style' overlaps with general code-quality skills, so it could still trigger for related skills. Not level 3 because of that overlap.	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: cursor/plugins
Path: cursor-team-kit/skills/deslop/SKILL.md
Commit: fe77e77

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.