agentleFS
sametcelikbicaksametcelikbicak/opencode-team/skills/team-prd/SKILL.md

team-prd

Skill69 starsChanged 19 days agoMITView on GitHub

Product requirements document (PRD) writing methodology. Scope, out of scope, user stories, acceptance criteria and success metrics. The playbook of the pm role.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Do not make up numbers. If you do not know the target, say "target to be determined" and mark it as an open question.

    line 66

≈ “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 a PRD

What a PRD is for

A PRD is not a document, it is a contract. Its purpose: everyone agrees on what will and will not be done in version 1.

That is why the most valuable section is Out of Scope. When someone says "let's also do this", the out-of-scope list is consulted.

1. Summary

3 sentences. Who, which problem, how we solve it. Do not write an introductory paragraph.

2. Problem and target audience

  • Problem: the measurable pain the user experiences today.
  • Target audience: one primary segment. Not "small businesses", but "agencies with 5-20 employees".
  • Why now: a timing rationale.

3. Scope / Out of scope

Two lists, of equal length.

In scope items:

  • One sentence, starting with a verb ("The user can upload an invoice")
  • Each item is an observable behavior
  • Testable ("visible" / "not visible" can be answered)

Out of scope items:

  • Things that will not be done in version 1
  • A "for now" rationale (under which condition it is reconsidered)
  • This list is a later negotiation tool

The out-of-scope items that are written down are the things everyone says "maybe" to. If you do not write them down, they will be added later.

4. User stories and acceptance criteria

Format:

Story: As a <role> I want <behavior>, so that <value>.

Acceptance criteria:
- [ ] <testable statement>
- [ ] <testable statement>

An acceptance criterion must be testable. Not "the user will be happy". "The list loads in under 2 seconds at 500 rows" can be answered with yes or no — that one is.

Split a story that contains more than one "and". A story with two acceptance criteria is sometimes two stories.

Number of stories: 8-15. More means surprise; fewer covers the scope incompletely.

5. Success metrics

Measurable conditions for the product to be considered successful. For each one:

MetricBaselineTargetHow it is measured
Weekly active users???

Do not make up numbers. If you do not know the target, say "target to be determined" and mark it as an open question. Writing an estimated target and presenting it as real becomes a source of later discussion.

6. Risks and open questions

  • Risk: what happens, probability, impact, mitigation
  • Open question: a question without an answer, waiting for a decision. Who will answer it?

Common mistakes

MistakeThe right way
Writing the solution ("store it with PostgreSQL")Write the need ("should be able to store the invoice")
40 stories8-15 stories, at most
An unmeasurable success metricWrite a number or say "to be determined"
Not writing out of scopeAlways write it
Embedding technical designArchitecture is a separate stage
More than one target audiencePick a single segment

Output format

Markdown. Sections: Summary / Problem and target audience / Scope / Out of scope / User stories + acceptance criteria / Success metrics / Risks and open questions.

In the user's language (Turkish or English).

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.