deslop
Remove AI-generated code slop and clean up code style
49
52%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./cursor-team-kit/skills/deslop/SKILL.mdQuality
Discovery
32%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 identifies a recognizable niche (cleaning up AI-generated code) but is too terse and lacks explicit trigger guidance. It would benefit from listing specific cleanup actions and adding a 'Use when...' clause to help Claude distinguish this skill from general code formatting or refactoring skills.
Suggestions
Add a 'Use when...' clause with trigger terms like 'clean up AI code', 'remove boilerplate', 'simplify generated code', 'code slop', 'refactor AI output'.
List specific concrete actions such as 'removes unnecessary comments, simplifies verbose patterns, eliminates redundant error handling, and enforces consistent naming conventions'.
Include natural keyword variations users might say, such as 'refactor', 'simplify', 'code quality', 'verbose', 'bloated code', or 'AI-generated mess'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names a domain ('AI-generated code slop') and two actions ('remove' and 'clean up code style'), but doesn't list specific concrete actions like what kinds of slop are removed or what style cleanup entails. | 2 / 3 |
Completeness | Describes what it does (remove slop, clean up style) but has no explicit 'Use when...' clause or trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also quite thin, bringing this to a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'code slop', 'clean up', and 'code style', but misses common variations users might say such as 'refactor', 'lint', 'code quality', 'boilerplate', 'verbose code', or 'simplify code'. | 2 / 3 |
Distinctiveness Conflict Risk | The term 'AI-generated code slop' is somewhat distinctive, but 'clean up code style' is generic enough to overlap with linting, formatting, or general refactoring skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A lean, well-structured skill that efficiently communicates what to look for and what constraints to follow. Its main weakness is the lack of concrete examples (before/after code snippets showing slop patterns) and an explicit workflow with validation steps like running tests after making edits.
Suggestions
Add 1-2 brief before/after code examples illustrating common slop patterns (e.g., unnecessary try/catch, redundant comments) to increase actionability.
Add an explicit workflow sequence: 1. Check diff against main, 2. Identify slop patterns, 3. Make minimal edits, 4. Verify tests still pass, 5. Summarize changes.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line earns its place. No unnecessary explanations of what slop is or how code review works—assumes Claude's competence and jumps straight to actionable focus areas and guardrails. | 3 / 3 |
Actionability | The focus areas are concrete enough to act on (unnecessary comments, defensive checks, any casts, deep nesting), but there are no code examples showing before/after patterns of slop vs. clean code, and no specific commands for checking the diff against main. | 2 / 3 |
Workflow Clarity | The implicit workflow is: check diff → identify slop → remove it → summarize. However, the sequence is not explicitly stated, there's no validation step (e.g., run tests after edits), and for a task involving code modifications, missing verification steps cap this at 2. | 2 / 3 |
Progressive Disclosure | This is a simple, single-purpose skill under 50 lines with no need for external references. The content is well-organized into clear sections (Focus Areas, Guardrails) making it easy to scan. | 3 / 3 |
Total | 10 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- cursor/plugins
- Commit
b8f2564
- 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.