agentleFS
Sign inStart free
mnapolimnapoli/skills/unslop/SKILL.md

unslop

Skill21 starsChanged 41 days agoMITView on GitHub

Detect and remove AI-sounding writing patterns from English text, then rewrite it with a genuine human voice. Use when asked to unslop, humanize, de-AI, or clean up English prose (docs, reports, READMEs, articles, artifacts, or conversation replies). For French text, use unslop-fr instead.

197 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use principle-never-block-on-the-human, greploop-apps 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.
  • jaydubya818Skill

    principle-never-block-on-the-human

    Apply when safe reversible implementation details can proceed inside scope.

    Also in 45 projects that use this

  • jaydubya818Skill

    greploop-apps

    Run greploop through @greptile-apps when the normal trigger rejects a large PR. Use only with the companion greploop skill.

    Also in 5 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 30 projects that use this

  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 26 projects that use this

  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 15 projects that use this

  • +7 more from jaydubya818

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 193 edited versions we read keep these.

  • 2

    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:

    Add voice: opinions where the author has one, concrete specifics, varied rhythm.

    line 14
  2. Distinctive:

    Use first person where appropriate.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 193 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

Unslop (English)

Identify and eliminate artificial language patterns from writing, while preserving meaning and injecting genuine voice and specificity. Heavily inspired by Cursor's unslop skill.

Process

  1. Scan the text for the patterns below.
  2. Rewrite while preserving meaning, facts, and tone. Never change data, numbers, names, or claims.
  3. Add voice: opinions where the author has one, concrete specifics, varied rhythm.
  4. Audit the result for remaining patterns, including in titles and headings — they are not exempt.

Adding soul

  • State opinions rather than neutral lists.
  • Vary sentence rhythm deliberately. Short sentences are good, as long as they are real sentences a human would say — not telegraphic fragments or symbol chains ("=", "vs", "→", "x1.5") in prose.
  • Acknowledge nuance and complexity when it exists.
  • Use first person where appropriate.
  • Allow structural imperfection; perfect parallelism reads as generated.
  • Be concrete and specific. Name the thing.

Patterns to detect and fix

Content

  1. Puffery — "pivotal moment", "evolving landscape", "indelible mark" → cut, state facts.
  2. Name-dropping without context → pick one source and explain it.
  3. Hollow -ing phrases — "highlighting", "ensuring", "showcasing" → delete or provide the actual mechanism.
  4. Promotional adjectives — "nestled", "vibrant", "breathtaking", "stunning" → neutral language.
  5. Vague attributions — "Experts believe", "Industry reports suggest" → name the source or remove the claim.
  6. Generic obstacles — "Despite challenges... thrives" → substitute specific details.

Language

  1. AI vocabulary — crucially, delve, interplay, pivotal, tapestry, testament, seamless, robust, leverage → plain equivalents.
  2. Inflated copulas — "serves as", "stands as", "boasts", "features" → "is" or "has".
  3. "Not just X, but Y" → state the point directly.
  4. Forced rule of three → use the natural grouping size, even if it's two or four.
  5. Synonym cycling — calling the same thing by three names → choose one term and repeat it.
  6. False ranges — "from X to Y" on mismatched scales → list the topics directly.

Style

  1. Em dash overuse → rely on periods and commas.
  2. Colon overuse as mid-sentence connector → rewrite as standalone sentences.
  3. Excessive boldfacing — bold scattered inside sentences for emphasis → remove. Structural bold is fine: a bold lead phrase opening a list item, bold labels, bold key figures.
  4. Header-restating lists — "Performance: Performance improved..." → convert to prose or fix the lead.
  5. Title Case Headings → sentence case.
  6. Decorative emojis in headings and bullets → remove.
  7. Curly quotes → straight quotes.

Communication artifacts

  1. Chatbot phrases — "I hope this helps!" → delete.
  2. Cutoff disclaimers — "While specific details are limited..." → source the claim or remove it.
  3. Sycophancy — "Great question!" → respond directly.

Filler

  1. Verbose phrases — "In order to" → "To"; "Due to the fact that" → "Because".
  2. Over-hedging — "could potentially possibly" → "may".
  3. Generic conclusions — "The future looks bright" → state specific facts, or end without a conclusion.

Jargon

  1. Abstract metaphor nouns — substrate, wedge, vector, nexus, harness, endgame, flywheel → concrete terms.

Plain speech

  1. Feelings over mechanisms — "stays close at hand" → explain the actual function or cut.
  2. Dense sentences → break into one idea per sentence.
  3. Passive voice — "queries are validated" → "the compiler validates queries".
  4. Weak verbs + adverbs — "runs quickly" → "is fast", or cite numbers; "utilize" → "use".

What to keep

  • Data tables and enumerable lists: they are data presentation, not slop.
  • The author's own terminology and domain terms.
  • Structural bold: a bold lead phrase on a list item, bold labels, bold key figures. Only scattered emphasis bold inside sentences is slop.
  • Short sentences. Terseness is not slop; formulas and fragments are.

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.

Check your setup, free