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.

Quality

79%

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 ./.agents/skills/deslop/SKILL.md

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

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, instruction-only skill: unambiguous task definition, concrete slop patterns, and sensible guardrails with zero padding. Its one real weakness is the absence of any verification checkpoint for what amounts to batch edits across a branch diff.

Suggestions

Add an explicit validation step after edits, e.g., "Re-run the diff against main to confirm behavior is unchanged" or "Run the test suite before summarizing", to lift workflow clarity above the batch-operation cap.

Include a concrete command for the first step, e.g., `git diff main...HEAD` to review the branch changes, making the guidance fully copy-paste executable.

Dimension	Reasoning	Score
Conciseness	Every line carries instructional weight: a one-line task statement, five concrete pattern bullets, and three guardrails. No concept explanations, no padding; assumes Claude's competence throughout. Matches anchor 5.	5 / 5
Actionability	"Check the diff against main and remove AI-generated slop" plus concrete pattern categories ("Casts to `any` used only to bypass type issues", "Deeply nested code that should be simplified with early returns") gives mostly executable guidance. Not 5 because the diff-acquisition step is stated abstractly with no concrete command (e.g., `git diff main...`).	4 / 5
Workflow Clarity	The sequence (diff against main, remove slop, summarize) is clear and guardrails exist, but this is a batch of edits across a branch with no explicit validation/verification step (no "run tests", no re-check of the diff). Per the rubric cap for batch operations without validation, workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	The skill is under 50 lines, self-contained with no external references needed, and organized into clear sections (Focus Areas, Guardrails). Per the simple-skill guideline, this matches anchor 5 with well-organized sections alone.	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 is concise, uses third person, and cleanly separates what the skill does from when to use it, with explicit trigger phrases including the distinctive term "deslop". Its main gaps are limited enumeration of the concrete actions and slight overlap of "clean up code style" with generic cleanup skills.

Suggestions

Enumerate 1-2 more concrete capabilities in the description (e.g., removing unnecessary comments, defensive checks, and `any` casts) to lift specificity.

Add natural trigger synonyms such as "remove AI slop" or "tidy up the diff" to broaden trigger-term coverage.

Sharpen the distinctiveness of the cleanup clause, e.g., "clean up AI-typical code style patterns" instead of the generic "clean up code style".

Dimension	Reasoning	Score
Specificity	"Remove AI-generated code slop and clean up code style" names the domain with two actions, but does not enumerate the specific slop patterns (comments, defensive checks, `any` casts) that the body covers. It matches anchor 3 (domain plus 1-2 concrete actions) rather than 4, which requires several specific actions listed.	3 / 5
Completeness	Explicitly answers both: what ("Remove AI-generated code slop and clean up code style") and when ("Use when asked to 'deslop', clean up AI-generated code, or review a branch diff for slop before merging") with concrete trigger phrases. Matches the anchor-5 example pattern exactly.	5 / 5
Trigger Term Quality	Includes strong natural terms users would actually say: "deslop", "clean up AI-generated code", "slop", "review a branch diff... before merging". Not 5 because a few natural variations (e.g., "remove AI slop", "tidy the diff") are missing.	4 / 5
Distinctiveness Conflict Risk	"deslop" is a distinct niche trigger, but "clean up code style" has minor overlap risk with general lint/format/cleanup skills. Mostly distinct, so anchor 4 rather than 5.	4 / 5
	Total	16 / 20 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: joe-bell/cva
Path: .agents/skills/deslop/SKILL.md
Commit: 638844f

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.