no-slop

Rewrites text to remove AI writing patterns and add human voice.

1|Updated Sep 16, 2026
One-click install
npx skills add https://github.com/dsatpm/factory-skills --skill no-slop-dsatpm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: no-slop
Source: https://github.com/dsatpm/factory-skills/tree/main/plugins/no-slop/skills/no-slop
Command: npx skills add https://github.com/dsatpm/factory-skills --skill no-slop-dsatpm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated and AI-edited text carries recognizable tells: puffery, em dash overuse, chatbot phrases, vague attributions, and sterile structure. This Skill detects and rewrites those patterns in commit messages, PR titles and bodies, docs, code comments, and replies so the text reads as human-written. ## Core Features & Use Cases - Pattern detection and rewriting: Scans for 31 documented AI tells across content, language, style, communication artifacts, filler, jargon, and plain speech, then rewrites while preserving meaning and tone. - Voice restoration: Goes beyond deletion by adding opinions, varied rhythm, specificity, and first-person voice so the result is not sterile. - Use Case: Before posting a PR description, run the text through this Skill to strip phrases like "Additionally, this pivotal change enhances the developer experience" and replace them with concrete statements about what the code does. ## Quick Start Ask the agent to apply no-slop to your draft PR description or commit message before you post it.

Frequently Asked Questions about no-slop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I remove AI writing patterns from a PR description?▼

Apply the no-slop skill to the draft before posting. It scans for 31 documented tells like puffery, vague attributions, and chatbot phrases, then rewrites the text while preserving meaning and intended tone.

What kinds of text does AI slop detection apply to?▼

It targets text written or edited for a human reader: commit messages, PR titles and bodies, docs, code comments, and replies. Prose you did not touch is left alone.

Does removing AI patterns make writing sound robotic instead?▼

The skill addresses this directly with an "adding soul" step: have opinions, vary sentence rhythm, use first person where it fits, and be specific. Sterile, voiceless writing is treated as its own tell.

Why are em dashes flagged as an AI tell?▼

The skill treats em dash overuse as a recognizable AI pattern and bans them entirely, including substitutes like parentheses or hyphen-as-dash. Thoughts needing separation should become new sentences or use commas.

When should I not use this writing cleanup skill?▼

Do not run it on prose you did not write or edit; the skill explicitly scopes itself to text you are about to commit, post, or send. It is a writing pass, not a grammar checker or fact verifier.