Skip to content
Agentmart
Submit a tool

ai-prose-cleaner

Detect and clean AI-typical writing patterns in documents — em dashes, filler phrases, over-formality

Skill by TheTrustedAdvisor

IndexedMIT★ 7
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/thetrustedadvisor-ai-prose-cleaner

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Detect and clean AI-typical writing patterns in documents — em dashes, filler phrases, over-formality

Use cases: writing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/ai-prose-cleaner

What's inside

Skill name
ai-prose-cleaner
Description
Detect and clean AI-typical writing patterns in documents — em dashes, filler phrases, over-formality
License
MIT
Instructions
38 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

## When to Use

- Documents sound "too AI" — em dashes, "delve", "it's worth noting", hedging stacks
- Before sending proposals, READMEs, or reports to clients/reviewers
- After AI-assisted writing that needs a human voice pass
- Batch scan agent/skill definitions for AI fingerprints
- User says "deslop prose", "clean AI writing", "humanize"

## Workflow

Delegates to @omg:ai-prose-cleaner agent, which operates in two modes:

1. **Detect (default):** Scan files, report AI patterns with line numbers, severity rating (LOW → HEAVY)
2. **Clean:** Rewrite flagged patterns in place, preserving meaning. Tier 1 patterns auto-fixed, Tier 3 structural changes suggested for manual review.

## Supported Languages

English and German AI patterns detected (Halbgeviert-Striche, "Es ist erwähnenswert", etc.)

## Trigger Keywords

clean AI writing, humanize, deslop prose, AI speech, prose cleaner

## Examples

```
@omg:ai-prose-cleaner scan docs/proposal.md
@omg:ai-prose-cleaner clean README.md
@omg:ai-prose-cleaner scan plugin/agents/*.md
```

## Quality Contract

- Every rewrite preserves factual content — only voice changes
- Report includes line numbers, pattern tier, and suggestions
- Rating scale: patterns per 1,000 words (LOW < 1, MILD 1-3, MODERATE 3-6, HEAVY > 6)

From TheTrustedAdvisor/omg, MIT.

More from TheTrustedAdvisor/omg

Signals

Stars
7
Forks
1
Open issues
0
Last commit (this folder)
Apr 16, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/TheTrustedAdvisor/omg
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from TheTrustedAdvisor

Cite this page

ai-prose-cleaner skill. Agent Mart. https://agentmart.dev/skills/thetrustedadvisor-ai-prose-cleaner (last updated 2026-10-24)