ai-slop-cleaner

Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

Quality

67%

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 ./skills/ai-slop-cleaner/SKILL.md

Quality

Content

81%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.

The body is a well-sequenced, validation-heavy workflow with concrete passes, classifications, and explicit review checklists, scoring highly on workflow clarity and actionability. The main improvement opportunities are trimming the overlap between the When to Use / Good Fits and Ralph sections, and moving the UI/design checklist into a reference file if the bundle grows.

Dimension	Reasoning	Score
Conciseness	The body is imperative and evidence-dense ('Prefer deletion over addition', 'Keep diffs small, reversible, and smell-focused') with no explanation of concepts Claude already knows. Minor redundancy keeps it below anchor 5: 'When to Use' overlaps 'Good Fits', and 'Scoped File-List Usage' overlaps 'Ralph Integration'.	4 / 5
Actionability	Concrete, executable guidance throughout: four named cleanup passes, six defined smell categories, explicit usage commands ('/oh-my-claudecode:ai-slop-cleaner <target> --review'), and a specific review checklist. Below anchor 5 because verification steps name tools ('lint, typecheck, unit/integration tests') rather than giving copy-paste commands, and above anchor 3 since nothing is pseudocode or vague.	4 / 5
Workflow Clarity	A clear six-step sequence with explicit validation checkpoints and feedback loops: regression tests before editing, 'Re-run targeted verification after each pass', quality gates with error recovery ('If a gate fails, fix the issue or back out the risky cleanup'), plus a reviewer checklist. The deletion-heavy work is fully covered by validation, so no cap applies.	5 / 5
Progressive Disclosure	No bundle files exist and all content is inline in a well-sectioned ~145-line body with no dead or buried references. Below anchor 5 because the skill exceeds 50 lines and the UI/Design Reviewer Checklist is self-contained enough to belong in a separate reference file; above anchor 3 because structure and navigation are good.	4 / 5
	Total	17 / 20 Passed

Description

53%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.

The description communicates a clear, distinctive purpose with concrete workflow attributes, but it lacks any explicit 'when to use this' trigger guidance and misses the natural trigger synonyms ('deslop', 'anti-slop') that the body itself uses. Adding a 'Use when...' clause with those trigger phrases would lift both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user says deslop, anti-slop, or AI slop, or asks to clean up noisy, repetitive, or over-abstracted AI-generated code.'

Include the natural synonyms already used in the body ('deslop', 'anti-slop') in the description so the skill triggers on the phrases users actually say.

Name one or two concrete outcomes of the workflow (e.g., 'removes dead code and duplicate logic, consolidates needless wrappers') to raise action specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('AI-generated code slop') with 1-2 concrete actions ('regression-safe, deletion-first workflow', 'optional reviewer-only mode'), but does not list several distinct specific actions. It is above anchor 2 because the workflow attributes are concrete, and below anchor 4 because the action coverage is not comprehensive.	3 / 5
Completeness	The 'what' is clear (clean AI-generated code slop via a deletion-first, regression-safe workflow), but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the judging guidelines. The body contains trigger guidance, but the description field itself does not.	3 / 5
Trigger Term Quality	'clean' and 'AI-generated code slop' are natural phrases, but the description omits common variations the body itself relies on, such as 'deslop', 'anti-slop', and 'dead code'/'duplicates'. This sits between anchor 3 (missing common variations) and anchor 4, closer to 3 since more than a few natural terms are absent.	3 / 5
Distinctiveness Conflict Risk	The anti-slop framing ('AI-generated code slop', deletion-first, reviewer-only mode) carves a mostly distinct niche with only minor overlap risk against generic refactor/cleanup skills. Not 5 because a plain 'clean up this code' request could plausibly match broader cleanup skills too.	4 / 5
	Total	13 / 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: Yeachan-Heo/oh-my-claudecode
Path: skills/ai-slop-cleaner/SKILL.md
Commit: dc7ba1d

Reviewed: 3 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.