remove-ai-slops

Remove AI-generated code smells (slop) from branch changes or an explicit file list. Locks behavior with regression tests FIRST, then runs categorized cleanup via parallel `deep` agents in batches of 5, then verifies with quality gates. Covers 10 slop categories including performance equivalences, excessive complexity (object annotations, if/elif variant chains), and oversized modules (250+ pure LOC with mandatory modular refactoring). MUST USE when the user asks to "remove slop", "clean AI code", "deslop", "clean up AI-generated code", "remove AI slop", or wants to clean up AI-generated patterns from recent changes. Triggers - "remove ai slops", "clean ai code", "deslop", "cleanup AI generated", "remove AI slop", "clean up AI-generated code", "strip slop", "ai-slop cleanup".

Quality

84%

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

Quality

Content

77%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.

A highly actionable, well-sequenced workflow with strong validation/feedback loops for a destructive batch operation. Its weaknesses are conciseness (a verbose harness-compatibility preamble) and progressive disclosure (a long monolithic file with no references split out).

Suggestions

Move the Codex Harness Tool Compatibility table and the v1/v2 surface distinctions into a references/harness-compat.md file, keeping only a one-line pointer and 'this section wins' note inline to cut padding.

Extract the full Categories catalog and the Output Format template into references/ files, leaving a concise summary plus a clearly signaled link so the SKILL.md body stays a lean overview.

Trim the repeated 'If a code block below conflicts with this section, this section wins' clauses to a single statement; the threefold repetition adds tokens without new information.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the Codex Harness Tool Compatibility preamble (tool-translation table, repeated 'this section wins' caveats, v1/v2 surface distinctions) and duplicated Phase 4 surface detail are padding that Claude largely does not need for the slop-removal core.	3 / 5
Actionability	Fully executable: exact bash (`git diff $(git merge-base main HEAD)..HEAD --name-only`), a copy-paste `task(...)` invocation template, a precise `awk` LOC measurement, and a concrete quality-gates table cover the common cases.	5 / 5
Workflow Clarity	Phases 0-6 are clearly sequenced with explicit validation checkpoints (Phase 2 green-baseline-or-STOP, Phase 5 gates + critical-review checklist, Phase 6 fix->retry with 3-strike escalation) appropriate for a destructive/batch skill.	5 / 5
Progressive Disclosure	Single-file ~360-line body with no bundle files; the categories catalog, harness-compatibility table, and output template are candidates for one-level-deep reference files but are instead inlined under section headers.	3 / 5
	Total	16 / 20 Passed

Description

91%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.

A strong, trigger-rich description that clearly states capability and when-to-use with concrete natural-language phrases. It is slightly diluted by mechanism detail (batch size, agent category) that is not strictly capability.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Locks behavior with regression tests FIRST', 'categorized cleanup via parallel deep agents in batches of 5', 'verifies with quality gates', 'mandatory modular refactoring') and 10 named categories, though some mechanism detail dilutes the pure capability list.	4 / 5
Completeness	Explicitly answers both what (remove AI slop from branch changes/file list with test-first locking and quality gates) and when ('MUST USE when the user asks to ... or wants to clean up AI-generated patterns from recent changes') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural terms and synonyms users would actually say: 'remove slop', 'clean AI code', 'deslop', 'clean up AI-generated code', 'strip slop', 'ai-slop cleanup'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (AI-slop removal from recent changes) with distinct triggers and minimal conflict risk; only minor overlap risk with general cleanup/refactoring skills.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: code-yeongyu/lazycodex
Path: plugins/omo/skills/remove-ai-slops/SKILL.md
Commit: 10f9558

Reviewed: 10 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.