deslop

An agent skill by cursor, from cursor/plugins. Tags: cleanup, code-quality, development, refactoring, review.

What it does

Remove AI-generated code slop and clean up code style

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add cursor/plugins --skill deslop

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/cursor-team-kit/skills/deslop ~/.claude/skills/deslop

Safety box score

Grade A, minimal risk: 7 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a code-cleanup prompt: it inspects the branch diff against `main` and edits repository files to remove stylistic or structural “AI slop.” It does not include scripts, network access, privilege changes, or instructions to touch secrets, so the main risk is limited to unintended code edits in the working tree.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	`SKILL.md` contains only guidance text; there are no shell commands, scripts, or code execution instructions.
Network access	0 (none)	No download, upload, API call, or remote-host communication is described in the skill files.
Filesystem reach	1 (low)	The skill is meant to modify repository files in the current branch, e.g. "remove AI-generated slop introduced in the branch" and make "minimal, focused edits".
Secrets & credentials	0 (none)	The skill does not mention tokens, keys, passwords, `.env` files, keychains, or other secret material.
Privilege & persistence	0 (none)	There is no sudo, global install, service registration, shell startup edit, or OS configuration change mentioned.
Instruction hijack surface	0 (none)	The file does not ask the agent to ignore instructions, follow remote content, hide actions, or otherwise change its behavior beyond normal code cleanup.
Irreversible actions	1 (low)	It autonomously rewrites code in the branch, but it does not publish, deploy, merge, send messages, or perform irreversible external actions.
Transparency	0 (none)	There are no binaries, generated blobs, or decoded-at-runtime content; the skill file is fully readable text.

Before installing

Confirm you want the agent to edit files in your current branch, not just comment on them.
Run it first on a throwaway branch or small diff to verify the cleanup stays behavior-preserving.

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository: cursor/plugins (all skills from this repository)
Path: cursor-team-kit/skills/deslop/SKILL.md
Branch: main
Collection: cursor
Updated: 2026-09-23

principle-laziness-protocol — Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading.
principle-subtract-before-you-add — Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.
principle-migrate-callers-then-delete-legacy-apis — Apply when introducing a new internal API while old callers still exist.
typescript-best-practices — TypeScript best practices. Use when reading or editing any .ts or .tsx file.
safe-refactor — Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
skill-reviewer — Reviews and improves Claude Code skills against official best practices.