Agent skill

Deslop

by automagik-dev in automagik-dev/genie

Clean up the prose, code or interface already in scope — protect its meaning, voice and behaviour, remove what only adds reading work, and return findings instead of edits when a review was asked for.

MITAuto-check passedWriting & Content

Install Deslop

skills CLI
$ npx skills add automagik-dev/genie --skill deslop -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install automagik-dev/genie deslop --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/automagik-dev/genie.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/deslop .claude/skills/deslop && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deslop
GitHub stars
346
Token cost
~979 tokens
SKILL.md length
578 words
Files
5 (incl. references)
Skills in repo
19
Repo updated
First seen
Licence
MIT

At a glance

Clean up the prose, code or interface already in scope — protect its meaning, voice and behaviour, remove what only adds reading work, and return findings instead of edits when a review was asked for.

  • Tasks that involve Humanizing AI text
  • SKILL.md covers Bound the scope, Protect before you remove, Tells are clues, never quotas and The three parts, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Deslop is an agent skill from automagik-dev/genie. Clean up the prose, code or interface already in scope — protect its meaning, voice and behaviour, remove what only adds reading work, and return findings instead of edits when a review was asked for.

Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `agents/openai.yaml`, `references/code.md` and `references/design.md`).

It sits in Writing & Content, covering Humanizing AI text. The repository describes itself as: Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated worktrees, and reviews code before you see it. The licence is MIT.

When your agent uses it

  • Tasks that involve Humanizing AI text

Example prompts

  • “/deslop”

What it can do on your machine

Read from SKILL.md and the folder at commit 097207e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deslop loads about 979 tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 52 tokens; SKILL.md has 578 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~979
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from automagik-dev/genie at commit 097207e, republished under its MIT licence (© automagik-dev). 578 words, ~979 tokens.

Download SKILL.mdSave it as .claude/skills/deslop/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
deslop
description
Clean up the prose, code or interface already in scope — protect its meaning, voice and behaviour, remove what only adds reading work, and return findings instead of edits when a review was asked for.
category
lifecycle
mutates
repo

Deslop

Reduce the work of reading, maintaining and safely changing what is in front of you, without losing what it guarantees. Lines, sentences, files, wrappers, dependencies and tests have no target count, and a pass that changes nothing is a valid result.

Bound the scope

The subject is what the request already names: this draft, this document, this diff, the code just touched and the callers it reaches. A repository-wide sweep is separate work with its own request. Ordinary drafting and ordinary implementation include checking what you touch; neither authorizes unrelated cleanup, and neither reopens a decision the caller already made.

Name the mode in one line before the first change, and take the narrowest mode the request supports:

ModeYou returnDone when
Draft or implementThe artifactThe requested scope is covered and its own checks pass
CleanupThe edited artifact and what changedEvery change names a benefit, and every protected invariant still holds
ReviewFindings, nothing editedEvery finding carries a location, the burden it imposes, and the smallest useful fix

A request to look at something is a review. Rewriting on a review request destroys the evidence the caller asked for.

Protect before you remove

List what must survive before proposing a single removal, and keep the list where the caller can read it.

In prose, protect names, quantities, claims, citations, requirements and causal links, along with the author's stance and degree of certainty. In code, protect the requested behaviour, the existing contracts, and whatever an apparently redundant construct is there to defend.

Removing something whose purpose you cannot state is a guess wearing a diff. When the reason for a construct stays unclear after you have looked for it, the honest output is a low-confidence finding, not a deletion.

Tells are clues, never quotas

The references below name what tends to signal avoidable work. Each one is a reason to look, never a verdict. A contrast may explain a real distinction, passive voice may focus on the right subject, an adverb may qualify a claim, and an extra layer may hold a boundary. Judge the instance in front of you.

No deletion quota, no detector score, no punctuation ban, no compulsory stylistic change. Swapping one stock phrase for another, or chopping prose and flattening call graphs so the work looks done, fails the same way the original did.

Show full SKILL.md (184 more words)Show less

The three parts

Load only the part the request needs:

  • references/writing.md — prose: messages, documents, reports, copy, pull request bodies.
  • references/code.md — code: the touched implementation, its callers and its tests.
  • references/design.md — interfaces, only for a project that has one: the rendered screen, its states, and the tokens and components behind it.

Prose judged against the live product belongs to the docs skill, a prompt to refine, a skill to authoring. A blocking review gap is repair work for the fix skill, not for this one.

Before you stop

Read the result once against the original. In prose, check numbers, named entities, degree of certainty and who said what. In code, run the checks that actually cover the changed behaviour and quote their exit codes.

Report what changed, the benefit each change bought, the checks you ran, and what you deliberately left alone and why. Never argue a change from the size of the diff: a shorter diff is not evidence of performance, correctness, or saved effort. Stop when the artifact serves its purpose instead of polishing it into a different voice or a different architecture.

© automagik-dev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in skills/deslop of automagik-dev/genie.

  • SKILL.md
  • agents/openai.yaml
  • references/code.md
  • references/design.md
  • references/writing.md

Open the folder on GitHubat commit 097207e

Compare with similar skills

Deslop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deslop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deslop this skillautomagik-dev/genie346—~979Automated safety check: PassMIT
Unslop FileMohamedAbdallah-14/unslop1551 repos~2.7kAutomated safety check: WarnMIT
evlog Content Writingevloghq/evlog1.9k—~2.9kAutomated safety check: PassMIT
HumanizerAzure-Samples/interview-coach-agent-framework17338 repos~5.8kAutomated safety check: PassMIT
Avoid AI Writingconorbronsdon/avoid-ai-writing4.9k3 repos~8.1kAutomated safety check: PassMIT
User-Facing Text Cleanupguillaumemeyer/watermarks-remover24k—~3.5kAutomated safety check: PassMIT

Similar skills

  • Unslop File

    MohamedAbdallah-14/unslop

    Humanize natural-language memory files (CLAUDE.md, todos, preferences, docs) by removing AI-isms and adding burstiness while preserving every code block, URL, path, command, and heading exactly.

    155 GitHub starsUsed in 1 repo~2.7k tokens
    Writing & ContentAuto-check: warnings
  • Rules for writing and reviewing evlog docs, blog posts, READMEs, skills and AGENTS.md files, with separate review and rewrite roles, a house voice and a catalog of AI-sounding tells.

    1.9k GitHub stars~2.9k tokensUpdated today
    Writing & ContentAuto-check passed
  • Humanizer

    Azure-Samples/interview-coach-agent-framework

    Official

    Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.

    173 GitHub starsUsed in 38 repos~5.8k tokens
    Writing & ContentAuto-check passed
  • Avoid AI Writing

    conorbronsdon/avoid-ai-writing

    Audit and rewrite content to remove AI writing patterns ("AI-isms").

    4.9k GitHub starsUsed in 3 repos~8.1k tokens
    Writing & ContentAuto-check passed
  • User-Facing Text Cleanup

    guillaumemeyer/watermarks-remover

    Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.

    24k GitHub stars~3.5k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Install Anti Slop

    trycompai/crm

    Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository.

    11k GitHub starsUsed in 1 repo~881 tokens
    Writing & ContentAuto-check passed

More from automagik-dev/genie

All 19 skills in this repo
  • Learn

    automagik-dev/genie

    Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.

    346 GitHub stars~720 tokensUpdated today
    Auto-check passed
  • Brainstorm

    automagik-dev/genie

    Explore an ambiguous idea with the user, settle scope and success criteria, and produce an independently reviewed design for wish.

    346 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Report

    automagik-dev/genie

    Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.

    346 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Wish

    automagik-dev/genie

    Deliver one decided task end to end — admit it, work it in one worktree, gate, independent review, bounded repair, a merge-ready PR — or plan a multi-group wish when it is bigger than one task.

    346 GitHub stars~3.7k tokensUpdated today
    Auto-check passed
  • Work

    automagik-dev/genie

    Execute an approved wish in dependency order with scoped workers, independent review, bounded repairs, and verified completion.

    346 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Authoring

    automagik-dev/genie

    Write or revise a Genie skill so it survives the shipped contract — frontmatter, house size, starter card, and runtime-neutral voice.

    346 GitHub stars~1k tokensUpdated today
    Auto-check passed

Questions about Deslop

What does Deslop do?

Clean up the prose, code or interface already in scope — protect its meaning, voice and behaviour, remove what only adds reading work, and return findings instead of edits when a review was asked for. Deslop is an agent skill from automagik-dev/genie. Clean up the prose, code or interface already in scope — protect its meaning, voice and behaviour, remove what only adds reading work, and return findings instead of edits when a review was asked for.

When should I use Deslop?

Deslop fits situations like: tasks that involve Humanizing AI text.

How do I install Deslop in Claude Code?

Run `npx skills add automagik-dev/genie --skill deslop -a claude-code`. Or copy the skill folder (skills/deslop in automagik-dev/genie) into .claude/skills/deslop in your project. Claude Code loads it when a task matches its description.

How do I install Deslop in Codex?

Run `npx skills add automagik-dev/genie --skill deslop -a codex`. Or copy the skill folder (skills/deslop in automagik-dev/genie) into .agents/skills/deslop in your project. Codex loads it when a task matches its description.

Can I use Deslop in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add automagik-dev/genie --skill deslop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deslop, .gemini/skills/deslop, .github/skills/deslop and .opencode/skills/deslop in your project.

What does Deslop need to run?

SKILL.md names no scripts, command-line tools or credentials: Deslop is instructions for the agent only.

Does Deslop access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deslop safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deslop use?

Deslop is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deslop use?

About 979 tokens (SKILL.md is roughly 3.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.2k tokens, read only when the agent opens those files.

What are the alternatives to Deslop?

Skills that share tags, products or a category with Deslop: Unslop File (MohamedAbdallah-14/unslop, 155 stars), evlog Content Writing (evloghq/evlog, 1.9k stars), Humanizer (Azure-Samples/interview-coach-agent-framework, 173 stars) and Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deslop?

automagik-dev (a GitHub organization) maintains it in automagik-dev/genie, which has 346 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 10, 2026.

Source: automagik-dev/genie on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.