Stop Slop

Install

Clone https://github.com/hardikpandya/stop-slop into ~/.claude/skills/stop-slop and apply the skill when writing or editing prose.

This is third-party code. Review the repository files before installing.

What it does

The skill gives the agent eight prose rules: cut throat-clearing openers, emphasis crutches, adverbs and business jargon, avoid binary contrasts and dramatic fragments, use active voice and be specific. Before delivering, the agent runs a checklist for em dashes, here's-what setups, runs of equal-length sentences and punchy paragraph closers. References hold lists of banned phrases, structural cliches and before and after examples. Text is scored on five dimensions and revised if it falls below the threshold.

Who it is for. For writers and editors working with an agent who want prose without recognizable AI cliches.

Example request

Rewrite this post using stop-slop rules and score the result

Limitations

Rules are radical, such as banning all adverbs and Wh- sentence openers, which can make some genres choppy. Phrase lists are English-only. There is no install command; the folder is copied manually.

How to disable. Delete the stop-slop folder from the agent's skills directory or remove SKILL.md from project knowledge.

Security check

• The skill consists only of instructions and references

README in short

The README briefly explains that the skill teaches a model to find and remove AI writing patterns. It shows the layout: the main SKILL.md plus three references for phrases, structures and examples. It suggests adding the folder as a Claude Code skill, uploading files to a Claude project or pasting into a system prompt. A five-dimension scoring table is included. MIT licensed.

SKILL.md

---
name: stop-slop
description: Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.
metadata:
  trigger: Writing prose, editing drafts, reviewing content for AI patterns
  author: Hardik Pandya (https://hvpandya.com)
---

# 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.

Related