agentleFS
Sign inStart free
orbyn-devorbyn-dev/orbyn-fullstack-skills/skills/unslop/SKILL.md

unslop

Skill4 starsChanged 10 days agoMITView on GitHub

Edit agent prose, chat replies, PR and issue text and documentation for short, clear factual communication while preserving the requested voice and evidence. Use orbyn-content-design for interface copy and social-content for posts.

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, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 192 edited versions we read keep these.

  • 5

    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:

    Before shortening anything, mark what must survive: exact names, measured quantities, release state, caveats, attribution, uncertainty and …

    line 16
  2. Distinctive:

    Keep terminology consistent with the owning product or API contract.

    line 25
  3. Distinctive:

    Read the complete result as a whole, for meaning.

    line 30
  4. Distinctive:

    Follow the consuming project's instructions and requested scope.

    line 44
  5. Distinctive:

    Do not rewrite user-authored product content as a side effect of UI simplification.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 192 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

Chat replies, PR descriptions, issues and checklists are short by default: answer first, fragments and bullets, only what the reader needs to act. Follow short by default for the rules and word targets.

Edit the passage

  1. Identify the reader, the requested outcome and the statements whose wording carries technical or evidential meaning.
  2. Before shortening anything, mark what must survive: exact names, measured quantities, release state, caveats, attribution, uncertainty and the user's writing style or intended voice.
  3. For a tutorial, how-to, reference or explanation, apply the conditional document purpose method before polishing sentences.
  4. Edit one passage around its main point. Lead with the concrete result or action. Use familiar words and verbs, one main idea per paragraph and paragraph breaks that follow the reasoning. Add headings only when they help navigation. Keep terminology consistent with the owning product or API contract.
  5. Replace vague claims with supported actions or outcomes. Remove filler, repetition, duplicated setup, inflated claims, forced contrasts and decorative formatting. Do not manufacture metrics or a numerical benefit, and do not remove evidence to make prose sound stronger.
  6. Read the complete result as a whole, for meaning. A checklist of forbidden words cannot prove clear writing, and word-count reduction alone is not a quality measure.
  7. Return the requested edited copy. Add an evidence note only where a factual gap affects publication.

Two cases to watch:

  • “The export is ready” may be shorter but false if only HTML source was generated; retain the missing PDF inspection.
  • A user's intentional humor or informal phrasing is not automatically filler.

Scope and owners

Follow the consuming project's instructions and requested scope; use the portable defaults only where guidance is missing.

  • Product copy and labels: use content design. Do not rewrite user-authored product content as a side effect of UI simplification.
  • Social posts: use social-content for post strategy, author voice, platform adaptation and carousel copy; this skill supplies the prose pass.
  • Visuals: use social-preview for rendered feed mockups, attached visuals and visual composition. Editing a caption does not require generating visual assets.
  • Source comments: they explain non-obvious constraints and leave the next line to the code. When writing or reviewing them, read source comments.

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