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

88%

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%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, validated multi-phase workflow, but it is verbose and ships everything inline with no reference files, so progressive disclosure and conciseness trail the rest.

Suggestions

Reconcile the category count — the body says "these nine categories" and "10 slop categories" in the same section; pick one and number the list consistently.

Move the Codex Harness Tool Compatibility table and the full output-format template into reference files (e.g. references/codex-tool-compat.md, references/report-template.md) and link to them from the body to cut inline tokens.

Tighten the duplicated tool-surface instructions (the 'If a code block below conflicts with this section, this section wins' clause is repeated several times).

Dimension	Reasoning	Score
Conciseness	Mostly actionable domain content rather than concepts Claude already knows, but the body runs ~360 lines with a long duplicated Codex tool-compatibility preamble and an internal inconsistency ("nine categories" vs "10 slop categories") that adds noise without earning tokens.	2 / 3
Actionability	Provides copy-paste-ready executable guidance: exact `git diff $(git merge-base main HEAD)..HEAD --name-only`, a full `task(...)` invocation template, an `awk` LOC-measure command, a quality-gate table with pass conditions, and a concrete output-format template.	3 / 3
Workflow Clarity	Phases 0–6 are clearly sequenced with explicit validation checkpoints (green tests before cleanup, quality gates, critical-review checklist) and feedback loops (Phase 6 fix-verify-repeat, three-strike escalation) appropriate to destructive/batch operations.	3 / 3
Progressive Disclosure	No bundle files exist and all content is inline in a single monolithic file; well-sectioned, but material like the full Codex tool-compat table and the output template could be one-level-deep reference files instead of inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 specific, trigger-rich, and answers both what and when with an explicit MUST USE clause in third person. It is somewhat verbose for a description field, but each clause carries concrete information.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Locks behavior with regression tests FIRST", "runs categorized cleanup via parallel `deep` agents in batches of 5", "verifies with quality gates" — plus specific category examples rather than vague language.	3 / 3
Completeness	Explicitly answers both what (the lock-test-first cleanup workflow) and when ("MUST USE when the user asks to..."), satisfying the explicit-trigger guidance.	3 / 3
Trigger Term Quality	Covers natural phrasings a user would actually say ("remove slop", "clean AI code", "deslop", "strip slop", "clean up AI-generated code") across both prose and an explicit Triggers list.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (AI-slop removal from branch changes/file lists) with distinct trigger phrases unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 895b70c

Reviewed: 4 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.