deslop
Remove AI-generated code slop and clean up code style
62
52%
Does it follow best practices?
Impact
Pending
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 conveys a recognizable concept ('code slop') but is too terse and lacks both specific actions and explicit trigger guidance. It would benefit from listing concrete cleanup operations 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 slop', 'simplify generated code', 'refactor verbose code', 'code quality'.
List specific concrete actions such as 'removes unnecessary comments, simplifies over-engineered patterns, fixes poor naming conventions, eliminates redundant boilerplate'.
Include natural keyword variations users might say, such as 'refactor', 'simplify', 'boilerplate removal', 'ChatGPT code', 'LLM-generated code'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names a domain ('AI-generated code slop') and a general action ('remove' and 'clean up code style'), but doesn't list specific concrete actions like what cleaning up entails (e.g., removing unnecessary comments, simplifying verbose patterns, fixing naming conventions). | 2 / 3 |
Completeness | It partially answers 'what does this do' but has no 'Use when...' clause or equivalent explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'code slop' and 'clean up code style' that users might say, but misses common variations like 'refactor', 'simplify', 'boilerplate', 'verbose code', 'AI-generated mess', 'code cleanup', or 'code quality'. | 2 / 3 |
Distinctiveness Conflict Risk | The concept of 'AI-generated code slop' is somewhat distinctive, but 'clean up code style' is broad enough to overlap with general linting, formatting, or 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 concise, well-structured skill that clearly communicates its purpose and constraints. Its main weakness is the lack of concrete examples showing what slop looks like versus acceptable code, and the absence of explicit workflow steps with validation (e.g., running tests after edits to confirm behavior is unchanged).
Suggestions
Add 1-2 brief before/after code examples showing a sloppy pattern and its cleaned-up version to improve actionability.
Add an explicit workflow sequence: e.g., 1. Run 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 style works—assumes Claude's competence and provides only the specific patterns to look for and constraints to follow. | 3 / 3 |
Actionability | The focus areas are specific enough to act on, but the skill lacks concrete examples of what slop looks like vs. clean code, and doesn't provide specific commands (e.g., how to check the diff against main). It describes patterns rather than showing before/after examples. | 2 / 3 |
Workflow Clarity | The implicit workflow is: check diff → identify slop → remove it → summarize. However, the sequence is not explicitly stated, and there are no validation checkpoints (e.g., run tests after changes, verify behavior is unchanged). For a task involving code edits, 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) that are 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
7dd9fea
- 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.