home / skills / revokslab / shipfree / rmslop

rmslop skill

safe

This skill removes AI-generated slop by diff-checking main and pruning inconsistent or unnecessary code patterns across the repository.

npx playbooks add skill revokslab/shipfree --skill rmslop

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

601 B

---
name: rmslop
description: Remove AI code slop
---

# Overview

Check the diff against main, and remove all AI generated slop introduced in this branch.

This includes:

- Extra comments that a human wouldn't add or is inconsistent with the rest of the file
- Extra defensive checks or try/catch blocks that are abnormal for that area of the codebase (especially if called by trusted / validated codepaths)
- Casts to any to get around type issues
- Any other style that is inconsistent with the file
- Unnecessary emoji usage

Report at the end with only a 1-3 sentence summary of what you changed

Overview

This skill removes AI-generated “slop” from a branch diff to keep the codebase clean and consistent. It targets unnecessary comments, abnormal defensive patterns, type casts to any, and other stylistic inconsistencies introduced by automated edits. The result is a leaner, more idiomatic code change set and a short summary of edits.

How this skill works

The skill scans the diff against main and identifies additions that look like AI-inserted noise: verbose comments, odd try/catch guards, stray any casts, emoji, and style departures from surrounding code. It either removes or normalizes those changes in-place, preserving intent and functionality. After processing, it provides a 1–3 sentence summary describing the applied cleanups.

When to use it

A branch contains many machine-generated edits or bulk refactors.
Pull request includes verbose comments or defensive checks that look out of place.
TypeScript files use casts to any to silence type issues introduced by automation.
You want a concise, human-style codebase before merging.
Reviewers request removal of inconsistent stylistic changes.

Best practices

Run after AI-assisted code generation or large automated commits to remove noise.
Keep original behavior — only remove or simplify nonfunctional additions.
Prefer minimal edits: reduce comments and guards that don’t change logic rather than refactor code flow.
Use project linting and type checks to validate no behavioral regressions were introduced.
Review the 1–3 sentence summary before merging to confirm intent.

Example use cases

A branch has repeated explanatory comments that duplicate obvious code; the skill removes them.
Automated tooling added try/catch around trusted calls; the skill strips those guards to match project norms.
A TypeScript file gained multiple 'as any' casts; the skill removes them and restores typed expressions when safe.
Commit history shows emoji and conversational notes; the skill deletes nontechnical tokens and standardizes comments.

FAQ

Will this change program behavior?

No — the focus is on stylistic and nonfunctional noise. The skill avoids edits that alter logic or contract unless a clear nonfunctional pattern is being removed.

How does it decide what's 'AI slop'?

It uses heuristics: unusual verbosity, extra defensive checks in trusted paths, 'any' casts added where types existed, emoji and inconsistent comment style compared to the file. Results are reviewed in the summary before applying.