team-prd — Claude Code skill: what it does, how to install
team-prd is a Claude Code skill that structures product requirements documents for version 1 releases. Defines scope boundaries and testable acceptance criteria.
MIT ★ 71 updated 2026-11-13
npx skills add sametcelikbicak/opencode-team --skill team-prd -a claude-codeWhat team-prd does
The skill generates a product requirements document in Markdown according to product manager guidelines. It enforces a three-sentence summary, a single target segment, balanced scope lists, and 8 to 15 user stories.
Technical architecture is barred from the document because engineering design belongs to a separate stage. Acceptance criteria require binary testable statements, while missing metrics stay marked as open questions instead of fabricated targets.
What it helps with
- draft a version 1 product requirements document without technical noise
- define strict scope boundaries and maintain an out-of-scope list
- break features into user stories with testable acceptance criteria
- track product success metrics and unassigned open questions
Example prompts for the agent
- Create a PRD for an invoice management tool for small agencies.
- Draft version 1 scope and acceptance criteria using team-prd rules.
- Generate a product document with user stories and out-of-scope items.
How to install team-prd
1Skills CLI (Vercel)
npx skills add sametcelikbicak/opencode-team --skill team-prd -a claude-code2Manually: put the files in place
~/.claude/skills/team-prd/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/team-prd/
1Skills CLI (Vercel)
npx skills add sametcelikbicak/opencode-team --skill team-prd -a codex2Manually: put the files in place
.agents/skills/team-prd/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sametcelikbicak/opencode-team --skill team-prd -a cursor2Manually: put the files in place
.cursor/skills/team-prd/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sametcelikbicak/opencode-team skills/team-prd2Manually: put the files in place
.github/skills/team-prd/SKILL.md1Skills CLI (Vercel)
npx skills add sametcelikbicak/opencode-team --skill team-prd -a gemini-cli2Platform CLI
gemini skills install https://github.com/sametcelikbicak/opencode-team --path skills/team-prdManually: put the files in place
.devin/skills/team-prd/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about team-prd
How to install team-prd in Claude Code?
Run npx skills add sametcelikbicak/opencode-team --skill team-prd -a claude-code. The file is saved at ~/.claude/skills/team-prd/SKILL.md.
What does team-prd do?
It outputs a structured Markdown PRD covering problem definition, scope limits, user stories, success metrics, and project risks.
What output languages does team-prd support?
The skill generates the requirements document in the user's language, specifically English or Turkish.
Source text
SKILL.md · MIT
---
name: team-prd
description: Product requirements document (PRD) writing methodology. Scope, out of scope, user stories, acceptance criteria and success metrics. The playbook of the pm role.
---
# 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:
| Metric | Baseline | Target | How 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
| Mistake | The right way |
|---|---|
| Writing the solution ("store it with PostgreSQL") | Write the need ("should be able to store the invoice") |
| 40 stories | 8-15 stories, at most |
| An unmeasurable success metric | Write a number or say "to be determined" |
| Not writing out of scope | Always write it |
| Embedding technical design | Architecture is a separate stage |
| More than one target audience | Pick 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).
© sametcelikbicak · MIT · sametcelikbicak/opencode-team