agentleFS
Sach1ngSach1ng/PM-operating-OS/skills/writing-clearly/SKILL.md

writing-clearly

Skill3 starsChanged 19 days agoMITView on GitHub

Help PMs write clear, concise prose for PM artifacts. Use for PRDs, status updates, Slack posts, emails, and documentation.

3 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

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    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 asked "help me make this clearer" or "tighten this up"

    line 16
  2. Distinctive:

    Put the conclusion or ask first

    line 29
  3. Distinctive:

    Don't bury the lead in the last paragraph

    line 30
  4. Distinctive:

    Prefer short words over long (use vs.

    line 33
  5. Distinctive:

    Prefer active voice (we will ship vs.

    line 34
  6. Distinctive:

    Use numbers, dates, names instead of "soon," "many," "several"

    line 38
  7. Distinctive:

    Use headers, bullets, and short paragraphs

    line 42
  8. Distinctive:

    Remove filler (e.g., "in order to" → "to")

    line 47
  9. Distinctive:

    If a sentence doesn't add value, cut it

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Writing Clearly

Help PMs write clear, concise prose for PM artifacts. Applies principles of plain language, structure, and scannability to make communications effective and easy to act on.

When to Use

  • Writing or editing a PRD
  • Drafting status updates or stakeholder comms
  • Composing Slack posts or emails
  • Creating documentation or runbooks
  • When asked "help me make this clearer" or "tighten this up"

Process / Template

1. Identify the Artifact and Audience

  • What are you writing? (PRD, update, post, doc)
  • Who will read it? (engineers, leadership, customers)
  • What do they need to do? (decide, build, understand, act)

2. Apply Clear Writing Principles

Lead with the main point

  • Put the conclusion or ask first
  • Don't bury the lead in the last paragraph

Use plain language

  • Prefer short words over long (use vs. utilize, help vs. facilitate)
  • Prefer active voice (we will ship vs. it will be shipped)
  • Cut jargon unless the audience expects it

Be specific

  • Use numbers, dates, names instead of "soon," "many," "several"
  • Replace vague terms with concrete ones

Structure for scannability

  • Use headers, bullets, and short paragraphs
  • One idea per paragraph
  • Front-load key info in each sentence

Cut ruthlessly

  • Remove filler (e.g., "in order to" → "to")
  • Remove redundancy
  • If a sentence doesn't add value, cut it

3. Use the Right Format

ArtifactKey Moves
PRDClear problem statement, explicit requirements, scannable sections
Status updateTL;DR first, bullets, metrics, explicit asks
Slack/emailShort paragraphs, one ask per message
Doc/runbookStep-by-step, headers, examples

4. Edit in Passes

  • Pass 1 — Structure: does the order make sense?
  • Pass 2 — Clarity: can a reader understand it in one pass?
  • Pass 3 — Brevity: what can be cut?

5. Validate

  • Can the reader answer: What? Why? What do I do?
  • Would a busy executive get it in 2 minutes?
  • Are there ambiguous pronouns or missing context?

Output

Clear, concise prose that:

  • Communicates the intended message
  • Is easy to scan and act on
  • Respects the reader's time
  • Fits the format (PRD, Slack, email, doc)

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.