CtrlK
BlogDocsLog inGet started
Tessl Logo

deslop

Remove AI-generated code slop and clean up code style. Use when asked to "deslop", clean up AI-generated code, or review a branch diff for slop before merging.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is deslop in cursor/plugins

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

A tight, well-organized instruction skill that efficiently enumerates concrete slop patterns without padding. It loses points only on the lack of an explicit diff command and a verification step to confirm behavior is preserved after edits.

Suggestions

Replace "Check the diff against main" with an explicit command such as `git diff main...HEAD` so the primary action is copy-paste ready.

Add a verification checkpoint in the workflow (e.g., run the test suite or linter after edits) to confirm behavior is unchanged before summarizing.

Include a short before/after example of a deslopped snippet to make the cleanup concrete and unambiguous.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — terse bullets name concrete slop patterns (casts to `any`, abnormal try/catch, deep nesting) without explaining concepts Claude already knows; every token earns its place.

3 / 3

Actionability

The enumerated slop patterns form a concrete checklist, but the core action "Check the diff against main" is described rather than given as an executable command (e.g., `git diff main`), and no before/after example illustrates a deslop edit, leaving the guidance incomplete relative to fully executable instruction.

2 / 3

Workflow Clarity

The single-task sequence is implicit (diff → identify slop → remove → summarize) but there is no verification checkpoint (e.g., run tests/lint to confirm behavior unchanged after edits); for code edits this validation gap caps workflow clarity at 2.

2 / 3

Progressive Disclosure

The skill is under 50 lines with no need for external references and is well-organized into clear sections (Focus Areas, Guardrails), meeting the bar for full progressive disclosure via organization alone.

3 / 3

Total

10

/

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 strong, concise description that clearly states its purpose and provides explicit, natural-sounding trigger conditions. It names concrete actions and avoids vague fluff or over-claims.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Remove AI-generated code slop", "clean up code style", and "review a branch diff for slop before merging" — matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

It explicitly states what the skill does (remove AI-generated code slop, clean up code style) and when to use it via an explicit "Use when..." clause covering several triggers, satisfying both what and when.

3 / 3

Trigger Term Quality

It includes natural phrasings a user would actually say — asked to "deslop", "clean up AI-generated code", and "review a branch diff for slop" — giving good coverage of natural trigger terms.

3 / 3

Distinctiveness Conflict Risk

The AI-slop removal niche with distinct triggers ("deslop", AI-generated code, branch diff review) is clearly distinguishable and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
joe-bell/cva
Reviewed

Table of Contents

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.