agentleFS
ehnruizehnruiz/claude-skills/skills/plain-writing/SKILL.md

plain-writing

Skill3 starsChanged 29 days agoMITView on GitHub

Draft text a person will send or post under their own name, in plain language that does not read as machine-written. Use when drafting or editing a chat message, an email, a pull request description, a comment, a wiki page, an announcement or a post on the user's behalf, or when the user says a draft "sounds like AI", is too long, or is too stiff. For a ticket, use `ticket-write` to write one and `ticket-trim` to shorten one.

7 other projects use a version of this.

Adopted by

Most recently taken up by

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 6 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:

    When the user writes as a manager or a lead:

    line 14
  2. Distinctive:

    Keep the spelling convention of the user and the place it is posted.

    line 25

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

Plain writing

The draft goes out under the user's name, so it should sound like them on a good day: direct, warm and short. If the user's CLAUDE.md or memory describes their voice, follow that first. This skill covers what such notes usually leave out.

Lead with the point

Open with the decision, the ask or the status. Then give only the context the reader needs to act on it. Skip restating the request and any warm-up line.

When the user writes as a manager or a lead:

  • Give every ask an owner and a date.
  • Thank people by name for a specific piece of work.
  • Disagree plainly and politely: what happened, why it matters, what is expected, what happens next.

Sentences

  • Plain sentences with concrete nouns and verbs. Short over long.
  • Straight apostrophes and quotes (' and ").
  • Match the channel: a few lines for chat, longer but still plain for a page or a pull request.
  • Keep the spelling convention of the user and the place it is posted.
  • Light humor fits informal team messages. Leave it out everywhere else.

Patterns to cut

These make text read as machine-written and get in the way of the content:

  • Em-dashes used for an aside or for emphasis. Use a comma, parentheses or a new sentence.
  • A colon or semicolon used for a dramatic pause.
  • Contrast set-ups such as "not A, not B, just C" or "this isn't X, it's Y".
  • Adjectives that add flavor without information: "elegant", "clean", "robust", "seamless", "powerful".
  • A list padded to three items when there are two.
  • Openers such as "Great question" and hedges added for show.
  • A closing summary that repeats the body.

Check before showing

Reread the draft against the list above and cut every match. If you are unsure how the user would phrase something, make it shorter. Personal and family details stay out unless the user wrote them in.

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.