ai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
48
51%
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 ./skills/ai-slop-cleaner/SKILL.mdQuality
Discovery
40%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 carves out a distinctive niche around cleaning AI-generated code with a specific methodology, which is its main strength. However, it lacks explicit trigger guidance ('Use when...'), relies on somewhat jargon-heavy terms that users may not naturally use, and doesn't enumerate the concrete actions the skill performs.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to clean up, refactor, or simplify AI-generated code, remove code slop, or review LLM output for unnecessary complexity.'
Include more natural trigger terms users would say, such as 'refactor', 'clean up code', 'remove boilerplate', 'simplify', 'code review', 'LLM-generated code'.
List specific concrete actions the skill performs, e.g., 'Removes dead code, eliminates redundant abstractions, simplifies over-engineered patterns, and runs regression checks before and after changes.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names a domain ('AI-generated code slop') and describes a methodology ('regression-safe, deletion-first workflow', 'reviewer-only mode'), but doesn't list specific concrete actions like 'remove dead code, simplify abstractions, eliminate redundant comments'. | 2 / 3 |
Completeness | It describes what it does at a high level but has no explicit 'Use when...' clause or equivalent trigger guidance, and the 'what' is also somewhat vague. Per rubric guidelines, missing 'Use when' should cap completeness at 2, and the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'code slop', 'AI-generated', 'deletion-first', and 'reviewer-only mode', but misses common natural user phrases like 'clean up code', 'refactor', 'remove boilerplate', 'simplify code', or 'code review'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'AI-generated code slop', 'regression-safe', 'deletion-first workflow', and 'reviewer-only mode' creates a very distinct niche that is unlikely to conflict with general code refactoring or review skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured process skill with strong workflow clarity and explicit validation checkpoints throughout. Its main weaknesses are moderate verbosity (some sections explain things Claude already knows or could be externalized) and a lack of concrete executable examples—the guidance is instructional rather than demonstrated with before/after code snippets. The UI/Design Reviewer Checklist, while useful, feels like it belongs in a separate reference file rather than inline.
Suggestions
Add a concrete before/after code example showing a small slop cleanup (e.g., dead code removal or duplicate consolidation) to improve actionability.
Extract the UI/Design Reviewer Checklist into a separate reference file (e.g., UI_REVIEW_CHECKLIST.md) and link to it from the main skill to improve progressive disclosure and conciseness.
Trim the 'OMC Execution Posture' section to only include constraints that are specific to this skill rather than general good practices Claude already follows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some sections that could be tightened. The 'When to Use' / 'When Not to Use' sections overlap with the intro, the 'OMC Execution Posture' bullets repeat principles Claude already knows (e.g., 'stay concise'), and the UI/Design Reviewer Checklist is quite detailed inline content that could be separated. However, most content is domain-specific and earns its place. | 2 / 3 |
Actionability | The workflow steps are concrete and well-sequenced with specific smell categories and pass ordering, but there are no executable code examples, no concrete test snippets, and the guidance remains at the instructional level. Commands like `/oh-my-claudecode:ai-slop-cleaner <target>` are shown but the actual cleanup actions are described rather than demonstrated with before/after examples. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced with explicit validation checkpoints: protect behavior first with regression tests, write a cleanup plan before editing, run one smell-focused pass at a time with verification after each, run quality gates, and close with an evidence-dense report. The feedback loop (fix or back out if gates fail) is explicitly stated, and the review mode provides a clear writer/reviewer separation with specific review criteria. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and headers, but the UI/Design Reviewer Checklist is a substantial inline block that could be a separate reference file. With no bundle files provided, there's no progressive disclosure to external references. The skill is somewhat long (~130 lines of substantive content) and could benefit from splitting detailed checklists and the Ralph integration details into separate files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Yeachan-Heo/oh-my-claudecode
- Commit
3e94567
- 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.