agentleFS
odinfreeodinfree/storm-ecdsa-harness/skills/stop-slop/SKILL.md

stop-slop

Skill4 starsChanged 22 days agoMITView on GitHub

Audit and rewrite prose to remove common AI writing patterns. Use when drafting, editing, or reviewing writing that feels generic, over-polished, promotional, or structurally repetitive. Supports rewrite mode and detect-only mode.

46 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use operational-enterprise-ai, product-proof-saas and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • boraoztuncSkill

    operational-enterprise-ai

    Create or redesign enterprise AI, automation, security, and operations product pages that explain system boundaries, approvals, auditability, exceptions, and rollback. Use for dark cinematic heroes, hairline grids, metric pauses, expandable solution rows, case-study evidence, security proof, and qualified demo or waitlist handoffs.

    Also in 3 projects that use this

  • boraoztuncSkill

    product-proof-saas

    Create or redesign SaaS and AI product landing pages where a real workflow, interface, or deterministic demo is the central proof. Use for pale atmospheric shells, product UI in the hero, prompt-to-output stories, audience tabs, compact feature modules, honest pricing comparisons, and FAQ handoffs.

    Also in 3 projects that use this

  • Dragoon0xSkill

    pricing-page

    Present pricing in ways that reduce friction and increase clarity. Handles tier naming, feature comparison, anchor pricing, and plan selection psychology. Use when designing pricing pages, plan selectors, or upgrade prompts.

    Also in 3 projects that use this

  • brpazSkill

    tailwind-v4

    Configure Tailwind CSS v4 with Oxide, CSS-first directives, migration steps, and production guidance.

    Also in 3 projects that use this

  • ParthJadhavSkill

    app-store-screenshots

    Use when building App Store or Google Play screenshot pages, generating exportable marketing screenshots for iOS, macOS, and/or Android apps, or scaffolding a screenshot editor with Next.js. Triggers on app store, mac app store, play store, screenshots, marketing assets, html-to-image, phone mockup, mac mockup, android screenshots, feature graphic.

    Also in 3 projects that use this

  • seikaikyoSkill

    banner-design

    Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage.

    Also in 4 projects that use this

  • +1 more from boraoztunc

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 46 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Remove common AI writing patterns from prose.

    line 10
  2. Distinctive:

    Use this as a baseline editing skill.

    line 12
  3. Distinctive:

    run a second pass on the rewrite

    line 26
  4. Distinctive:

    Do not blindly remove a word just because it appears in a list.

    line 135
  5. Distinctive:

    If the user provides a writing sample, match the sample after removing AI patterns.

    line 139
  6. Distinctive:

    Do not replace one generic voice with another generic voice.

    line 141
  7. Distinctive:

    no clear human point of view

    line 150
  8. Distinctive:

    Before you finish, ask:

    line 159

“Common” is measured: kept by at least 6 in 10 of the 46 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Schwafelbräms (stop-slop)

Stop Slop. Vendored from welttowelt/stop-slop-refined (MIT, see LICENSE and ATTRIBUTION.md beside this file); only this title line was changed.

Remove common AI writing patterns from prose.

Use this as a baseline editing skill. It is not a personal voice layer.

Companion references:

  • references/words.md
  • references/patterns.md
  • references/examples.md

Modes

Rewrite is the default.

  • flag the main issues
  • rewrite the text
  • run a second pass on the rewrite

Detect means flag only.

  • do not rewrite
  • show what reads as AI
  • separate clear problems from judgment calls

Trigger detect when the user says detect, flag only, audit only, scan, or equivalent.

Core rules

  1. Cut filler.
  2. Break formulas.
  3. Name the actor.
  4. Be specific.
  5. Trust the reader.
  6. Vary rhythm.
  7. Remove false emphasis.
  8. Cut generic endings.

What to look for

  • throat-clearing openers
  • contrast templates like not x, but y
  • generic intensifiers
  • vague attribution
  • passive construction where the actor matters
  • fake significance
  • rhythm that feels too even
  • lists that sound generated instead of chosen
  • clean but empty conclusions

For word-level flags, see references/words.md.

For structural flags, see references/patterns.md.

Quick checks

  • too many adverbs
  • too many abstract nouns
  • same sentence length three times in a row
  • same paragraph shape again and again
  • Let's dive in or similar signposting
  • Great question or similar chatbot artifacts
  • as of my last update or similar disclaimers
  • bold, emoji, markdown, or formatting that does not fit the destination

Output format

Rewrite mode

  1. Issues found
  2. Rewrite
  3. What changed
  4. Second pass

Detect mode

  1. Issues found
  2. Assessment
  3. Fix direction

Severity

P0

Credibility problems:

  • fake sourcing
  • chatbot artifacts
  • cutoff disclaimers
  • markdown in plain-text contexts
  • obvious significance inflation

P1

Clear AI smell:

  • tier-1 word hits
  • repeated templates
  • formulaic openings
  • repeated contrasts
  • rhythm that feels machine-even

P2

Polish:

  • too many triads
  • too many bullets
  • repetitive paragraph shapes
  • conclusion that says nothing

Context calibration

Be stricter in:

  • essays
  • investor emails
  • public posts
  • website copy

Be looser in:

  • docs
  • technical notes
  • fast internal chat

Do not blindly remove a word just because it appears in a list. Context matters. Technical writing can justify some words that sound bad in marketing copy.

Voice calibration

If the user provides a writing sample, match the sample after removing AI patterns.

Do not replace one generic voice with another generic voice.

Rewrite-from-scratch trigger

Rewrite from scratch if the draft has:

  • many tier-1 word hits
  • multiple structural patterns
  • uniform rhythm throughout
  • no clear human point of view

In that case:

  1. state the real point in one sentence
  2. rebuild from there

Final check

Before you finish, ask:

  • does this sound like a person or like a cleaned-up machine draft?
  • is the point sharper now?
  • did clarity improve, or just surface texture?

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.