agentleFS
Sign inStart free
Sach1ngSach1ng/PM-operating-OS/skills/prd-writer/SKILL.md

prd-writer

Skill3 starsChanged 19 days agoMITView on GitHub

Draft structured PRDs with problem, goals, use cases, and RACI. For AI/agent surfaces, add jobs, autonomy, failure behavior, and evals as acceptance criteria.

35 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use user-research.

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.
  • AnthropicSkill

    user-research

    Plan, conduct, and synthesize user research. Trigger with "user research plan", "interview guide", "usability test", "survey design", "research questions", or when the user needs help with any aspect of understanding their users through research.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 25 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write a PRD that a team can implement and test.

    line 8
  2. Distinctive:

    Do not invent strategy that is not in those files.

    line 24
  3. Very specific:

    Use cases with acceptance criteria (P0/P1/P2)

    line 36
  4. Very specific:

    Write or update knowledge/products/<product>/evals.md.

    line 53
  5. Distinctive:

    Ask only for what files do not already contain (one short batch).

    line 57
  6. Distinctive:

    Not everything is P0.

    line 64

“Common” is measured: kept by at least 6 in 10 of the 25 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

PRD Writer

Write a PRD that a team can implement and test. For AI surfaces, evals are part of the spec — not an appendix you skip.

When to use

  • User asks for a PRD, spec, or requirements doc
  • Formalizing an idea into something buildable

Before drafting

Read, in order:

  1. knowledge/products/<product>/brief.md
  2. evals.md if it exists
  3. memory/decisions/ for rejected options
  4. Org context in knowledge/_template/ or knowledge/examples/ only if needed

Do not invent strategy that is not in those files. If context is missing, say so.

Standard PRD

Follow references/prd-template.md:

  1. Header + RACI
  2. Current state
  3. Customer and business problem statements
  4. Ideal state
  5. Goals / metrics
  6. Features
  7. Use cases with acceptance criteria (P0/P1/P2)
  8. NFRs
  9. Evidence
  10. Milestones
  11. Open questions

If the surface is AI

Also follow references/ai-prd.md:

  • Jobs, not model capabilities
  • Autonomy table (alone / confirm / forbidden)
  • Failure behavior (stuck, missing evidence, never guess)
  • Evals as acceptance criteria — every P0 maps to an eval
  • Cost, latency, loop cap
  • What launch copy is allowed to claim

Write or update knowledge/products/<product>/evals.md. Use the eval-brief skill if the golden set does not exist yet.

Workflow

  1. Ask only for what files do not already contain (one short batch).
  2. Draft in markdown in workspace/drafts/ unless the user names another path.
  3. Flag any requirement with no metric or eval as open, not P0.

Rules

  • Specific beats vague. "Be helpful" is not a requirement.
  • Not everything is P0.
  • Link evidence. If there is none, write Missing.
  • Rejected alternatives belong in a decision record, not a buried FAQ.

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