agentleFS
koralliskorallis/agent-stack/skills/unslop/SKILL.md

unslop

Skill42 starsChanged 40 days agoApache-2.0View on GitHub

Remove AI writing tells (filler, hype, hedging stacks, chatbot phrases, decorative formatting) from any text before it is posted. Use on every PR description, SPEC, issue comment, queue body and message to the owner or a client; reviewers flag slop in PR text.

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

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 193 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before you post text anywhere, scan it for the patterns below and rewrite.

    line 8
  2. Distinctive:

    Plain word over the long one: use, not utilize or leverage.

    line 26
  3. Distinctive:

    Synonym cycling: Call one thing by one name throughout.

    line 38
  4. Distinctive:

    Em dashes: Use a period or a comma instead.

    line 39
  5. Very specific:

    Read it once as the receiver: can they act on each sentence?

    line 55

“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

Before you post text anywhere, scan it for the patterns below and rewrite. Keep the meaning and the intended tone. This applies to PR descriptions, commit messages, SPECs, issue and PR comments (including handbacks to a client), queue bodies and every message to the owner.

Content

  1. Empty -ing phrases. "highlighting…", "ensuring…", "showcasing…", "reflecting…". Delete them, or say the concrete thing.
  2. Vague attributions. "Experts believe", "it is widely known". Name the source or delete.
  3. Generic conclusions. "This lays a solid foundation", "the future looks bright". State the next step or the fact.
  4. Says how it feels, not what it does. "The flow feels much smoother" becomes "the save takes one click instead of three". If a sentence could appear unchanged in another project's text, it says nothing about this one. Cut it.

Words

  1. AI vocabulary. additionally, crucial, delve, enhance, fostering, garner, intricate, landscape, pivotal, robust, seamless, showcase, testament, underscore, vibrant. Use the plain word.
  2. Fancy verbs for "is" and "has". "serves as", "stands as", "boasts", "features".
  3. Plain word over the long one. use, not utilize or leverage. help, not facilitate. many, not numerous. if, not in the event that.
  4. Abstract metaphor nouns. substrate, vector, surface (as in "API surface"), harness (as a metaphor), north star, flywheel, paradigm. Say the concrete thing.
  5. Filler. "In order to" becomes "to". "Due to the fact that" becomes "because". "It is important to note that" goes.
  6. Hedging stacks. "could potentially possibly" becomes "may". If you know, say it. If you don't, say what you didn't check.
  7. Adverbs propping up weak verbs. "significantly improves" becomes the measured change.

Shape

  1. "Not just X, but Y" and forced groups of three. State the point with the real number of items.
  2. Synonym cycling. Call one thing by one name throughout.
  3. Em dashes. Use a period or a comma instead.
  4. Bold everywhere, emoji in headings, Title Case Headings. Sentence-case headings, no decorative emoji, bold only for a real label.
  5. Bold-label bullets that restate themselves. "Performance: performance improved" becomes a sentence.
  6. Over-compression. Arrows, dropped articles and verbless fragments make the reader decode. "Parser rejects bad date → exit 2" becomes "The parser rejects a bad date and exits with code 2."
  7. Passive voice that hides who acts. "The file is parsed" becomes "the loader parses the file".

Chat habits

  1. Chatbot phrases. "I hope this helps", "Let me know if…", "Great question", "Certainly!", "You're absolutely right". Remove them.
  2. Sycophancy or drama. "Found the smoking gun!" Report the finding.

Check before posting

Read it once as the receiver: can they act on each sentence? Cut what they can't. For documents and long PR text, also use the technical-writing skill.


Adapted from unslop in pstack by Lauren Tan (v0.15.5, commit fae2c6e, 2026-09-29), MIT licence; the licence text is in LICENSE beside this file. Changes: renumbered and condensed, a few words added to the vocabulary list, and scoped to the text our seats post.

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.