stop-slop

Removes predictable AI writing patterns from prose during drafting and editing.

3|Updated Jul 28, 2026
One-click install
npx skills add https://github.com/marcmarti9/agentit --skill stop-slop-marcmarti9
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: stop-slop
Source: https://github.com/marcmarti9/agentit/tree/main/skills/stop-slop
Command: npx skills add https://github.com/marcmarti9/agentit --skill stop-slop-marcmarti9

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI-generated and AI-assisted prose is full of recognizable tells: throat-clearing openers, binary contrasts, dramatic fragmentation, adverbs, passive voice, and vague declaratives. This Skill gives you a concrete rule set and checklists to strip those patterns out so text reads as direct, human writing. ## Core Features & Use Cases - Pattern Detection Rules: Eight core rules covering filler phrases, formulaic structures, passive voice, false agency, rhythm, and quotable lines. - Reference Catalogs: Detailed lists of phrases to cut (jargon, adverbs, meta-commentary) and structures to avoid (binary contrasts, negative listing, rhetorical setups), plus before/after transformation examples. - Scoring Rubric: A 1-10 rating across five dimensions (Directness, Rhythm, Trust, Authenticity, Density) with a 35/50 revision threshold. - Use Case: You drafted a blog post with an AI assistant and it sounds generic. Run it through this Skill to flag every "Here's the thing", em dash, and "not X, it's Y" construction, then rewrite each flagged sentence directly. ## Quick Start Review the attached draft and remove all AI writing patterns, then score it on the five quality dimensions.

Frequently Asked Questions about stop-slop

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

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

Apply the eight core rules: cut filler phrases and adverbs, break formulaic structures like binary contrasts, use active voice with named human actors, be specific, and vary sentence rhythm. Then run the quick checks list before delivering the prose.

What are common AI writing tells to avoid?▼

Common tells include throat-clearing openers like "Here's the thing", "not X, it's Y" contrasts, dramatic one-word fragments, em dashes, three-item lists, vague declaratives like "The implications are significant", and inanimate objects performing human verbs.

How is prose quality scored with this approach?▼

Rate the text 1-10 on five dimensions: Directness, Rhythm, Trust, Authenticity, and Density. A total below 35 out of 50 means the draft needs revision before delivery.

When should I not use these writing rules?▼

The rules target expository prose like essays, posts, and documentation. They are less suited to dialogue, poetry, or genres where fragmentation and rhetorical devices are intentional stylistic choices rather than AI artifacts.

Does this skill work for editing business jargon?▼

Yes. The phrases reference includes a jargon replacement table mapping terms like "navigate", "unpack", "lean into", and "deep dive" to plain-language alternatives, plus lists of filler phrases and meta-commentary to delete.