Stop Slop
Polish landing pages, docs, emails, and launch copy so solo builders ship prose that reads human—not like generic AI filler.
Overview
Stop Slop is a journey-wide agent skill that removes predictable AI writing patterns from prose—usable whenever a solo builder needs to edit drafts before committing copy to a page, email, or doc.
Install
npx skills add https://github.com/hardikpandya/stop-slop --skill stop-slopWhat is this skill?
- 8 core rules: cut filler phrases, break formulaic structures, active voice, specificity, reader-in-the-room tone
- Reference lists for banned phrases and structural AI tells (references/phrases.md, references/structures.md)
- Quick pre-delivery checklist: rhythm variety, no em dashes, no pull-quote phrasing
- Trust the reader: drop throat-clearing, softening, and false agency constructions
- Usable on drafts from agents or your own writing before you publish or paste into a CMS
- 8 core editorial rules plus a pre-delivery quick-check list
- Dedicated reference files for phrases and formulaic structures
Adoption & trust: 2.8k installs on skills.sh; 9.4k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Agent-generated and rushed human drafts often share the same throat-clearing phrases, false contrasts, and pull-quote sentences that make your product sound interchangeable.
Who is it for?
Solo builders polishing landing copy, docs, emails, or social posts after an AI first draft or before publish.
Skip if: Teams that only need code review, factual legal/compliance wording without tone edits, or finished copy already signed off by a human editor.
When should I use this skill?
Writing prose, editing drafts, reviewing content for AI patterns
What do I get? / Deliverables
You deliver tighter, specific, human-voiced prose that passes a built-in quick-check list instead of shipping obvious AI tells.
- Revised prose with AI tells removed
- Optional pass notes aligned to the quick-check list
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Rewrite hero and feature bullets on a waitlist page after your agent spits out symmetric contrasts and empty adverbs.
Tighten README and onboarding doc intros so they name concrete behaviors instead of vague structural claims.
Clean launch announcement and Product Hunt blurbs before you post publicly.
Pass newsletter and changelog drafts through the eight rules before sending to subscribers.
How it compares
Use as an editorial checker on prose, not instead of SEO keyword research or fact-checking workflows.
Common Questions / FAQ
Who is stop-slop for?
Solo and indie builders who write or edit customer-facing prose with AI assistants and want it to sound direct and human before they ship.
When should I use stop-slop?
Use it when drafting, editing, or reviewing text—e.g. validate landing hero copy, build README or doc intros, launch blog or changelog posts, grow lifecycle emails, or operate support replies—any time prose feels formulaic or over-polished.
Is stop-slop safe to install?
It is prose-editing guidance with no shell or network requirements in the skill itself; review the Security Audits panel on this Prism page before you add any skill to your agent environment.
SKILL.md
READMESKILL.md - Stop Slop
# Stop Slop Eliminate predictable AI writing patterns from prose. ## Core Rules 1. **Cut filler phrases.** Remove throat-clearing openers, emphasis crutches, and all adverbs. See [references/phrases.md](references/phrases.md). 2. **Break formulaic structures.** Avoid binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, false agency. See [references/structures.md](references/structures.md). 3. **Use active voice.** Every sentence needs a human subject doing something. No passive constructions. No inanimate objects performing human actions ("the complaint becomes a fix"). 4. **Be specific.** No vague declaratives ("The reasons are structural"). Name the specific thing. No lazy extremes ("every," "always," "never") doing vague work. 5. **Put the reader in the room.** No narrator-from-a-distance voice. "You" beats "People." Specifics beat abstractions. 6. **Vary rhythm.** Mix sentence lengths. Two items beat three. End paragraphs differently. No em dashes. 7. **Trust readers.** State facts directly. Skip softening, justification, hand-holding. 8. **Cut quotables.** If it sounds like a pull-quote, rewrite it. ## Quick Checks Before delivering prose: - Any adverbs? Kill them. - Any passive voice? Find the actor, make them the subject. - Inanimate thing doing a human verb ("the decision emerges")? Name the person. - Sentence starts with a Wh- word? Restructure it. - Any "here's what/this/that" throat-clearing? Cut to the point. - Any "not X, it's Y" contrasts? State Y directly. - Three consecutive sentences match length? Break one. - Paragraph ends with punchy one-liner? Vary it. - Em-dash anywhere? Remove it. - Vague declarative ("The implications are significant")? Name the specific implication. - Narrator-from-a-distance ("Nobody designed this")? Put the reader in the scene. - Meta-joiners ("The rest of this essay...")? Delete. Let the essay move. ## Scoring Rate 1-10 on each dimension: | Dimension | Question | |-----------|----------| | Directness | Statements or announcements? | | Rhythm | Varied or metronomic? | | Trust | Respects reader intelligence? | | Authenticity | Sounds human? | | Density | Anything cuttable? | Below 35/50: revise. ## Examples See [references/examples.md](references/examples.md) for before/after transformations. ## License MIT # Changelog ## 2026-01-13 ### Added **Phrases (references/phrases.md)** - Throat-clearing: "Here's what I find interesting", "Here's the problem though" - Performative emphasis: "creeps in", "I promise", "They exist, I promise" - Telling instead of showing: "This is genuinely hard", "This is what leadership actually looks like" **Structures (references/structures.md)** - Binary contrasts: "Not X. But Y.", "It's not this. It's that.", "stops being X and starts being Y" - Rhythm patterns: staccato fragmentation, dashes for dramatic pause, hedging as reassurance - Word patterns: absolute words (always, never, everyone, etc.), AI-overused intensifiers (deeply, truly, fundamentally, inherently, simply, literally, inevitably) ## 2026-01-12 - Restructured skill following Claude Code best practices (PR #1) - Split into SKILL.md and references/ folder ## 2025-01-12 - Initial release # Stop Slop A skill for removing AI tells from prose. <img width="3840" height="2160" alt="G-Yg4RVbIAAhVxW" src="https://github.com/user-attachments/assets/902afc15-1f40-4a9d-af24-8cd67afb8ebf" /> ## What this is AI writing has patterns. Predictable phrases, structures, rhythms. This skill teaches Claude (or any LLM) to catch and remove them. ## Skill Structure ``` stop-slop/ ├── SKILL.md # Core instructions ├── references/ │ ├── phrases.md