agentleFS
VladButacuVladButacu/agentkit/skills/prose/SKILL.md

prose

Skill0 starsChanged 5 days agoMITView on GitHub

Use when drafting or revising any prose a person will read, including documentation, website copy, blog posts, articles, case studies, emails, letters and applications. Always applies both passes: evidence discipline and voice fidelity.

15 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use design.

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.
  • Microsoft AzureSkill

    design

    Design rules and conventions for the API Center Portal. Use when editing detail pages, card components, badges, layout, navigation, sidebars, or headers. Covers badge styling, metadata placement, page navigation patterns, and layout alignment.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 1

    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:

    Ask one precise question only when a missing fact or choice would materially change the message.

    line 20

“Common” is measured: kept by at least 6 in 10 of the 13 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

Prose

Two passes, always both, in this order: the evidence pass decides what each sentence may claim, the voice pass decides how it sounds. Read references/evidence.md before the first pass and references/voice.md before the second.

Inputs before drafting

From the request and the supplied material, establish both:

  • The author, the actual recipient, their relationship, the decision or understanding the text should support, and the author's expressed feelings, intensity and characteristic words.
  • The facts: what happened or what the reader can do, how it differs from the alternative, what proof exists, and what stays local, manual, uncertain or limited.

Ask one precise question only when a missing fact or choice would materially change the message. Do not invent experience, feelings, customers, metrics or outcomes to fill a gap.

Pass 1: evidence

Work through references/evidence.md: the fact sheet, the claim hierarchy, sentence jobs, the substitution and consequence tests, the section substance audit, and the artifact rules. For websites, landing pages and product pages also read references/website-copy.md; for articles, blog posts and case studies also read references/blog-writing.md. references/slop-patterns.md holds the prohibited patterns and repairs.

Lint

Save the draft to a UTF-8 text file and run from this skill's directory:

python scripts/unslop_lint.py <file>

Resolve every ERROR. Review every WARN in context; do not evade a warning by swapping a synonym into the same empty sentence. Run it again after revisions. A passing lint result is necessary but not sufficient.

Pass 2: voice

Work through references/voice.md: establish the voice, repair the thought and the paragraph relationships, preserve the person, make the language easy to follow, then run its final review checklist. The voice pass comes after linting, never before.

When the passes collide

Evidence constrains what may be claimed; voice constrains how it may sound. An explicit feeling is source material, not an unsupported claim: keep it at the strength the author gave it. A fact that hurts the tone stays; a wording that betrays the author goes. A lint score never overrides the author's stated feeling, a necessary connective sentence, an ordinary sign-off or a precise technical word. Voice never licenses an unsupported claim, an invented anecdote or a fabricated metric.

Deliver

Return one committed version unless alternatives were requested. Keep any explanation brief and outside the artifact. Do not claim a literal read-aloud test or an independent review unless it happened. Stop when the text works; do not rewrite merely to produce another version.

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.