unslop

An agent skill by cursor, from cursor/plugins. Tags: copy-editing, documentation, quality, review, writing.

What it does

Cut AI tells from any writing. Must always apply.

Install

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

npx skills add cursor/plugins --skill unslop

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/pstack/skills/unslop ~/.claude/skills/unslop

Safety box score

Grade A, minimal risk: 4 of 100 risk points, rated 2026-10-17. 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 is a pure text-rewriting skill. It does not ship code or remote actions, but it will change prose in files it is applied to, so the main blast radius is workspace text edits and style drift.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	The only shipped file is `SKILL.md`; there are no shell commands, scripts, or code to execute.
Network access	0 (none)	No URLs, download steps, uploads, or remote services appear in the skill text.
Filesystem reach	1 (low)	The skill explicitly says `Edit text to remove AI patterns` and `rewrite`, so it can modify files it is pointed at, but only as text in the workspace.
Secrets & credentials	0 (none)	It does not mention tokens, keys, passwords, `.env` files, browser sessions, or other credential stores.
Privilege & persistence	0 (none)	There is no request for sudo, global installs, services, or shell/OS configuration changes.
Instruction hijack surface	0 (none)	The file contains style rules only; it does not tell the agent to ignore instructions, hide anything, or follow remote content.
Irreversible actions	0 (none)	It has no send, publish, deploy, delete, or payment actions.
Transparency	0 (none)	Everything provided is plain markdown; there are no binaries, minified blobs, or fetched code.

Before installing

Read `SKILL.md` and confirm it is text-only, with no scripts or remote fetches.
Try it on a scratch copy of a document first, since it rewrites prose in place.
If future versions add scripts or linked files, review those before letting an agent run them.

Rated 2026-10-17 by an automated review of 1 file from the skill's repository.

Source

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

technical-writing — Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax.
copy-editing — When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content.
google-docs — Author and edit Google Docs with the google-docs tools - structured writing, character and paragraph styling, lists, tables, images, headers/footers.
Poteto Mode — poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
writing-for-agents — Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
get-pr-comments — Fetch and summarize review comments from the active pull request