deslop

Simplify and refine recently modified code while preserving functionality. Use when asked to "deslop", "clean up code", "simplify code", or after making changes that could benefit from refinement.

Quality

64%

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

Quality

Content

62%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 well-structured, largely actionable code-simplification skill with a strong executable truffler example and clear sectioning. It is held back by role-play padding Claude does not need and by the absence of an explicit functionality-preservation validation checkpoint in the workflow, which is important for a code-mutating skill.

Suggestions

Remove the 'You are an expert... years as an expert software engineer' role preamble and redundant 'Choose clarity over brevity' restatements to tighten token efficiency.

Add an explicit validation checkpoint to the Refinement Process (e.g., 'Run tests/lint to confirm behavior is unchanged before finalizing') to lift workflow clarity above 3 for destructive code edits.

Replace the high-level 'Apply Project Standards' bullets with a pointer to the actual codebase guidelines or a concrete config reference so the guidance is fully executable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete bullet guidance, but padded with concepts Claude already knows (e.g., 'You are an expert code simplification specialist... years as an expert software engineer', 'A balance that you have mastered') and restated directives like 'Choose clarity over brevity' that echo earlier bullets.	3 / 5
Actionability	Provides a concrete, executable truffler command with full arguments and flags, plus specific inline consolidation rules; the remaining guidance is largely imperative and concrete, with only the project-standards section being somewhat high-level relative to the specific codebase context.	4 / 5
Workflow Clarity	The numbered Refinement Process lists steps and the truffler section includes a re-run-to-confirm checkpoint, but the overall workflow lacks explicit validation that functionality is preserved (e.g., running tests/lint) before finalizing destructive edits to recently-modified code, capping clarity at 3 for a code-mutating skill.	3 / 5
Progressive Disclosure	This is a short, single-purpose skill with no bundle files in references/, scripts/, or assets/; content is well-organized under clearly labeled numbered sections, so per the simple-skill exception it earns the top score without external file references.	5 / 5
	Total	15 / 20 Passed

Description

66%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.

A solid, concise description that clearly states both the capability and trigger conditions in third person with natural user-facing phrases. It could enumerate more concrete refactoring actions and add synonyms like 'refactor' to push specificity and trigger coverage to the top level.

Suggestions

Add 1-2 concrete refactoring actions to the description (e.g., 'collapse pass-through wrappers, inline single-use functions, remove dead code') to raise specificity.

Include synonyms like 'refactor' or 'tidy up' in the trigger phrase list to broaden natural term coverage.

Make the 'when' trigger slightly more concrete by naming a session-level cue (e.g., 'after finishing a feature branch') in addition to the existing phrasing.

Dimension	Reasoning	Score
Specificity	Names the domain ('Simplify and refine recently modified code') and one concrete action ('preserving functionality') but does not enumerate multiple specific refactoring actions like collapse wrappers, inline single-use functions, or remove dead branches, leaving coverage incomplete.	3 / 5
Completeness	It clearly answers 'what' ('Simplify and refine recently modified code while preserving functionality') and 'when' ('Use when asked to deslop, clean up code, simplify code, or after making changes'), with both present and the 'when' mostly explicit, falling just short of fully concrete trigger grounding.	4 / 5
Trigger Term Quality	Quotes natural trigger phrases a user would actually say ('clean up code', 'simplify code', 'deslop') plus a behavioral trigger ('after making changes'), which is good keyword coverage though it lacks synonyms like 'refactor' or 'tidy'.	4 / 5
Distinctiveness Conflict Risk	The 'deslop' name and specific triggers ('clean up code', 'simplify code') carve a clear niche distinct from generic refactor skills, with only minor overlap risk against a general code-review or formatting skill.	4 / 5
	Total	15 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: millionco/react-doctor
Path: .agents/skills/deslop/SKILL.md
Commit: 83466a8

Reviewed: 5 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.