AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Remove AI Slops

Strips AI-generated code slop from branch changes category by category — but only after regression tests lock the current behavior.

Dev & CodingAdvanced★ 67,531⑂ 5,507AI score 8/10Last updated: Aug 9, 2026

What it does

  • Works on a bounded scope: the branch diff against merge-base main, or an explicit file list you pass in.
  • Phase 2 is non-negotiable: writes the narrowest regression tests to pin observable behavior before any deletion; if it cannot get a green baseline, it stops.
  • Audits 10 slop categories with explicit KEEP/REFACTOR rules: obvious comments, over-defensive code (broad except Exception, empty catch {}), excessive complexity (if/elif variant chains → match/case, object annotations), needless abstraction, boundary violations, dead code, duplication, provably-equivalent performance fixes, missing tests, and oversized modules (>250 pure LOC → mandatory modular split).
  • Applies a "deletion ladder" first: delete entirely → reuse existing repo code → use stdlib/platform → only then simplify in place.
  • Closes with five quality gates (tests, lint, typecheck, security scan) plus a safety/behavior/quality checklist, reverting hunks that break anything.

Who it's for

  • Developers cleaning up a large AI-generated diff before opening a PR.
  • Tech leads and reviewers who want less noise to review.
  • Maintainers enforcing file-size and complexity discipline.

Example uses

  1. "Remove AI slop from this branch" → scope the diff → add regression tests for uncovered behavior → clean in safest-first order → emit the structured report.
  2. A 400-LOC file: the skill proposes a responsibility-based split plan, waits for approval, extracts modules with re-export-only __init__.py, then re-verifies every file is ≤250 pure LOC.
  3. Replaces a list scan inside a loop with a set lookup (O(n²)→O(n)) because equivalence is obvious, while explicitly SKIPping ambiguous algorithm swaps with a stated reason.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/HEAD/packages/shared-skills/skills/remove-ai-slops/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the packages/shared-skills/skills/remove-ai-slops folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/remove-ai-slops/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/code-yeongyu/oh-my-openagent.git && mkdir -p ~/.claude/skills && cp -r oh-my-openagent/packages/shared-skills/skills/remove-ai-slops ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/code-yeongyu/oh-my-openagent.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r oh-my-openagent/packages/shared-skills/skills/remove-ai-slops ~/.claude/skills/
  5. Restart Claude Code and ask: "deslop" or "remove AI slop from my changes".
  6. Make sure your project has a test runner, linter, and type-checker configured — the quality gates depend on them.
  7. Note: parallel deep agents and check-no-excuse-rules.py come from the upstream omo environment. Without them, tell Claude to process files sequentially and use the documented awk command for pure-LOC counts.
View source on GitHub ↗License: NOASSERTION