CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

deslop

Remove AI-generated code slop and clean up code style in the branch diff. Use for /deslop, "deslop this", or before committing.

66

Quality

83%

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

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.

A lean, well-organized instruction-only skill whose pattern list is concrete enough to act on directly. Its main weakness is the missing verification checkpoint for what is effectively a batch edit across the diff, which caps workflow clarity at 3.

Suggestions

Add an explicit verification step after cleanup, e.g., "Review the final diff to confirm only intended changes remain, and run tests/typecheck if available" — batch edits without validation cap workflow clarity at 3.

Include the concrete command for the diff step (e.g., `git diff main...HEAD`) and a short before/after example of one slop pattern and its fix.

DimensionReasoningScore

Conciseness

The ~23-line body is lean throughout — bullets like "Extra comments that are unnecessary or inconsistent with local style" and "Casts to `any` used only to bypass type issues" assume Claude's competence and explain nothing the model already knows. There is no padding anywhere to trim, so it matches anchor 5 rather than anchor 4.

5 / 5

Actionability

The guidance is concrete and pattern-specific ("Deeply nested code that should be simplified with early returns", "Defensive checks or try/catch blocks that are abnormal for trusted code paths"), giving clear instruction despite being instruction-only. It falls short of anchor 5 because "Check the diff against main" lacks the actual command (e.g., `git diff main`) and there are no before/after examples of the patterns.

4 / 5

Workflow Clarity

The single action (inspect the diff against main and remove slop) is unambiguous, but the workflow edits code across the entire branch diff — a batch modification — with no validation step: "Keep behavior unchanged unless fixing a clear bug" is a guardrail, not a checkpoint, and there is no verify/test step after edits. Per the batch-operation cap, workflow clarity cannot exceed 3; anchor 4 would require at least an explicit verification step.

3 / 5

Progressive Disclosure

The skill is under 50 lines, has no bundle files (references/, scripts/, assets/ absent), and is organized into clean sections ("## Focus Areas", "## Guardrails"), which qualifies for a 5 under the simple-skill exception. Nothing is inlined that belongs in a separate file, so anchor 4 does not apply.

5 / 5

Total

17

/

20

Passed

Description

78%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 cleanly and explicitly states both what the skill does and when to use it, with concrete trigger phrases including the slash command. It is somewhat light on enumerated capabilities and a few natural synonyms, holding specificity and trigger coverage at mid-high levels.

Suggestions

Enumerate two or three of the specific slop patterns handled (e.g., unnecessary comments, `any` casts, defensive try/catch) to raise capability specificity.

Add natural trigger synonyms such as "slop", "clean up the AI code", or "tidy the diff" so users' phrasing variants match without the slash command.

DimensionReasoningScore

Specificity

"Remove AI-generated code slop and clean up code style in the branch diff" names the domain plus two concrete actions, but does not enumerate the specific patterns handled (comments, `any` casts, defensive checks). It falls short of anchor 4 because the actions described are broad rather than a list of several specific ones.

3 / 5

Completeness

The 'what' is explicit ("Remove AI-generated code slop and clean up code style in the branch diff") and the 'when' is explicit with concrete trigger phrases ("Use for /deslop, \"deslop this\", or before committing"), matching the anchor-5 pattern of answering both with concrete triggers. It is not anchor 4 because the 'when' clause is already explicit and specific, not merely present.

5 / 5

Trigger Term Quality

"Use for /deslop, \"deslop this\", or before committing" includes the slash command, a natural user phrase, and a timing cue — good keyword coverage. Not anchor 5 because common synonyms such as "slop", "clean up AI code", or "tidy the diff" are absent.

4 / 5

Distinctiveness Conflict Risk

"AI-generated code slop" and "deslop" carve a clear, distinct niche with dedicated triggers. Minor overlap risk remains with generic code-cleanup/style/lint skills via the broader phrase "clean up code style" and the very broad "before committing" cue, keeping it below anchor 5.

4 / 5

Total

16

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

adamsardo/pstack-claude

Path

plugins/pstack/skills/deslop/SKILL.md

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.