Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
brycewang-stanford avatar

Stop Slop

  • 36 installs
  • 3.2k repo stars
  • Updated August 4, 2026
  • brycewang-stanford/awesome-agent-skills-for-empirical-research

This is a copy of stop-slop by hardikpandya - installs and ranking accrue to the original listing.

stop-slop is a Claude skill that removes predictable AI writing patterns from prose when drafting, editing, or reviewing text.

About

A prose-editing skill that removes predictable AI writing patterns from text. Writers use it when drafting, editing, or reviewing content to eliminate filler phrases, formulaic structures, passive voice, and vague declaratives. It provides eight core rules, a quick pre-delivery checklist, and a five-dimension scoring rubric with a revise threshold.

  • Removes predictable AI writing patterns from prose
  • Provides concrete rules: cut filler, break formulaic structures, use active voice
  • Includes a quick checklist and a 1-10 scoring rubric across five dimensions

Stop Slop by the numbers

  • 36 all-time installs (skills.sh)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

stop-slop capabilities & compatibility

Capabilities
copyediting · content review
Use cases
copywriting
From the docs

What stop-slop says it does

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.
SKILL.md
Eliminate predictable AI writing patterns from prose.
SKILL.md
Below 35/50: revise.
SKILL.md
npx skills add https://github.com/brycewang-stanford/awesome-agent-skills-for-empirical-research --skill stop-slop

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs36
repo stars3.2k
Last updatedAugust 4, 2026
Repositorybrycewang-stanford/awesome-agent-skills-for-empirical-research

What it does

Detect and remove predictable AI writing tells from prose while drafting, editing, or reviewing text.

Who is it for?

Editing prose to sound human and cut AI writing tells.

Skip if: Code, data analysis, or non-prose tasks.

When should I use this skill?

Drafting, editing, or reviewing text for AI patterns.

What you get

Direct, human-sounding prose scored above the revise threshold across five dimensions.

  • edited prose
  • AI-pattern findings
  • writing score

By the numbers

  • 8 core rules
  • 5-dimension scoring rubric
  • revise threshold of 35/50

Files

SKILL.mdMarkdownGitHub ↗

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.

2. Break formulaic structures. Avoid binary contrasts, negative listings, dramatic fragmentation, rhetorical setups, false agency. See 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:

DimensionQuestion
DirectnessStatements or announcements?
RhythmVaried or metronomic?
TrustRespects reader intelligence?
AuthenticitySounds human?
DensityAnything cuttable?

Below 35/50: revise.

Examples

See references/examples.md for before/after transformations.

License

MIT

Related skills

FAQ

What patterns does it target?

Filler phrases, binary contrasts, negative listings, passive voice, vague declaratives, em dashes, and pull-quote-style lines.

How does scoring work?

It rates prose 1-10 across directness, rhythm, trust, authenticity, and density; below 35/50 means revise.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.