CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ai-slop-cleaner

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

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ai-slop-cleaner/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 delivers an unusually well-sequenced cleanup workflow with explicit validation and rollback guidance, and the review checklists are concrete enough to act on directly. Its weaknesses are mild redundancy across the usage/posture sections and inline niche content (UI checklist, Ralph integration) that belongs in separate reference files.

Suggestions

Move the UI/Design Reviewer Checklist and Ralph Integration sections into reference files (e.g., references/ui-review.md, references/ralph-integration.md) and link them from the body.

Merge the overlapping trigger guidance in 'Scoped File-List Usage', 'Usage', and 'Good Fits' into a single section to cut redundant tokens.

Add one short before/after code example to make the smell classifications concrete for the writer pass.

DimensionReasoningScore

Conciseness

The body is mostly imperative and dense, but redundancy adds tokens: 'OMC Execution Posture' repeats guarantees restated in the Workflow, and trigger guidance appears three times across 'Scoped File-List Usage', 'Usage', and 'Good Fits'. This matches anchor 3 (mostly efficient but could be tightened) rather than 4, where only minor trimming would be needed.

3 / 5

Actionability

Concrete, executable guidance throughout: a 6-step workflow, four ordered smell-focused passes, a 5-point review checklist with specifics (e.g., flag '11-12px Korean body text', 'Tailwind-like #3B82F6'), and named quality gates. It falls short of anchor 5 only for minor gaps such as no example before/after cleanup diff or concrete gate commands.

4 / 5

Workflow Clarity

The workflow is clearly sequenced (protect behavior → plan → classify → passes → gates → report) with explicit validation checkpoints ('Re-run targeted verification after each pass') and a feedback loop ('If a gate fails, fix the issue or back out of the risky cleanup'), matching anchor 5 exactly.

5 / 5

Progressive Disclosure

Sections are well-organized with clear headers and no nested references, but the ~155-line body inlines niche content — the UI/Design Reviewer Checklist and the Ralph/OMC integration sections — that would be better split into one-level-deep reference files. This matches anchor 4 (good structure, minor organization gaps) rather than 5.

4 / 5

Total

16

/

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 is appropriately concise and names a distinctive niche, but it omits any 'when to use' trigger guidance and only gestures at the full capability set. Adding an explicit 'Use when...' clause with natural trigger phrases like 'deslop' or 'clean up AI slop' would lift completeness and trigger term quality.

Suggestions

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

Enumerate 1-2 more concrete capabilities (e.g., dead-code deletion, duplicate consolidation, test reinforcement) to raise specificity.

Include natural user synonyms such as 'deslop' and 'cleanup' alongside 'AI slop' for better trigger coverage.

DimensionReasoningScore

Specificity

The description names the domain ('AI-generated code slop') and 1-2 concrete actions ('regression-safe, deletion-first workflow', 'optional reviewer-only mode'), but does not comprehensively list the skill's capabilities (e.g., dead-code removal, duplicate consolidation, test reinforcement). It matches anchor 3 rather than 4 because it stops short of listing several specific actions.

3 / 5

Completeness

The 'what' is clear (regression-safe, deletion-first slop cleanup with a reviewer-only mode), but there is no 'Use when...' clause or equivalent explicit trigger guidance in the description, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

'AI-generated code slop' and 'Clean' are relevant natural keywords, but common variations users would actually say — 'deslop', 'clean up this code', 'too many wrappers', 'dead code' — are missing from the description. This sits between anchor 3 (some relevant keywords, missing variations) and anchor 4, closer to 3.

3 / 5

Distinctiveness Conflict Risk

'AI-generated code slop' is a distinctive niche trigger unlikely to fire for unrelated skills, with only minor overlap risk against generic refactor/cleanup skills. Not anchor 5 because the phrase 'clean code' could still collide with general code-cleanup or formatting skills.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.