deslop
Remove AI-generated code slop from the current branch. Use after writing code to clean up unnecessary comments, defensive checks, and inconsistent style.
80
70%
Does it follow best practices?
Impact
96%
1.31xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/deslop/SKILL.mdQuality
Discovery
67%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 adequately explains what the skill does and when to use it, earning full marks for completeness. However, it could be more specific about the concrete actions performed and include more natural trigger terms that users would actually say when needing this functionality. The niche of 'AI-generated code slop' is reasonably distinct but could still conflict with general code cleanup tools.
Suggestions
Add more natural trigger terms users might say, such as 'clean up code', 'remove boilerplate', 'fix AI-generated code', 'refactor messy code', or 'code cleanup'
List more specific concrete actions like 'removes TODO comments', 'eliminates redundant null checks', 'standardizes naming conventions' to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('AI-generated code slop') and lists some actions ('clean up unnecessary comments, defensive checks, and inconsistent style'), but doesn't comprehensively list all concrete actions or capabilities. | 2 / 3 |
Completeness | Clearly answers both what ('Remove AI-generated code slop... clean up unnecessary comments, defensive checks, and inconsistent style') and when ('Use after writing code') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'code slop', 'comments', 'defensive checks', but misses common variations users might say like 'clean up code', 'remove boilerplate', 'fix AI code', 'refactor', or 'code cleanup'. | 2 / 3 |
Distinctiveness Conflict Risk | The focus on 'AI-generated code slop' is somewhat distinctive, but terms like 'inconsistent style' and 'unnecessary comments' could overlap with general code formatting or linting skills. | 2 / 3 |
Total | 9 / 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.
This skill is concise and well-scoped for its purpose, but lacks the concrete examples and explicit workflow steps that would make it more actionable. The categories of 'slop' are clearly defined, but showing before/after examples would significantly improve Claude's ability to identify and fix issues consistently.
Suggestions
Add concrete before/after examples for each slop category (e.g., show an unnecessary comment vs. an appropriate one, or an excessive try/catch vs. the cleaned version)
Specify the git command to check the diff (e.g., `git diff main...HEAD` or `git diff main`)
Add a validation step to ensure removed code doesn't break tests or functionality before finalizing changes
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing only the essential information Claude needs. No unnecessary explanations of concepts Claude already knows, and every line serves a purpose. | 3 / 3 |
Actionability | Provides clear categories of what to look for (comments, defensive checks, casts to any, style inconsistencies), but lacks concrete examples of what 'slop' looks like or specific commands/code for checking diffs. The instruction to 'check the diff against main' is vague about how. | 2 / 3 |
Workflow Clarity | The workflow is implicit (check diff -> identify slop -> remove -> report), but lacks explicit sequencing and validation steps. For a task involving code modifications, there should be verification steps to ensure changes don't break functionality. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines, the content is appropriately structured. No need for external references or complex organization given the straightforward task. | 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
- brianlovin/claude-config
- Commit
1a9819e
- 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.