Skip to main content
skill CX Codex

write-prd — Claude Code skill: what it does, how to install

Generates structured 8-section product requirements documents with INVEST user stories and Gherkin acceptance criteria in Markdown.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add yonatangross/orchestkit --skill write-prd -a claude-code
Open on GitHub

What write-prd does

The skill takes a feature or product name and generates a structured PRD-[product-name].md file. The output covers eight sections: summary, contacts, background, objective, market segments, value propositions, solution, and release plan. Before writing, it triggers an AskUserQuestion prompt to let you choose between a full PRD, a lightweight spec, or isolated user stories.

Under the hood, work runs through sequential subtasks managed by TaskCreate. The agent searches past project context using MCP memory tools (mcp__memory__search_nodes) and drafts acceptance criteria in Gherkin format. A built-in Go/No-Go scoring gate grades viability, approving releases at 7.0 or above. The author specifies compatibility with Claude Code 2.1.277+, which affects background process execution in older versions.

What it helps with

  • generate structured product requirements across 8 template sections
  • draft INVEST user stories with Gherkin acceptance criteria
  • map value propositions against customer jobs, pains, and gains
  • score feature viability through a Go/No-Go decision framework

Example prompts for the agent

  • write a PRD for the SSO invite flow
  • create a product requirements document for billing
  • generate user stories and acceptance criteria for the dashboard

How to install write-prd

1Skills CLI (Vercel)

npx skills add yonatangross/orchestkit --skill write-prd -a claude-code

2Manually: put the files in place

~/.claude/skills/write-prd/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/write-prd/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about write-prd

How do I install write-prd in Claude Code?

Run npx skills add yonatangross/orchestkit --skill write-prd -a claude-code in your terminal.

What does write-prd produce?

It creates a Markdown file named PRD-[product-name].md containing eight core sections, INVEST stories, and acceptance tests.

How does the Go/No-Go decision gate work?

The framework uses strict score thresholds: 7.0 or higher is a Go, 5.0 to 6.9 is conditional, and anything below 5.0 rejects the feature.

Source text

SKILL.md · MIT
---
name: write-prd
license: MIT
compatibility: "Claude Code 2.1.277+."
description: "Write PRD — Product Requirements Documents with structured 8-section templates, user stories, acceptance criteria, and value proposition validation. Use when writing PRDs, defining product requirements, creating user stories with INVEST criteria, or building go/no-go decision frameworks."
context: fork
# user-typed commands stay interactive; CC >= 2.1.218 backgrounds forks by default (#3093)
background: false
agent: product-strategist
user-invocable: true
argument-hint: "product name or feature"
disable-model-invocation: false
metadata:
  category: document-asset-creation
  version: "2.0.1"
  author: "OrchestKit"
  complexity: "medium"
  tags: "prd, requirements, user-story, acceptance-criteria, invest, value-proposition, go-no-go"
allowed-tools: "Read Write Edit Glob Grep Bash WebFetch WebSearch AskUserQuestion TaskCreate TaskUpdate Agent mcp__memory__search_nodes mcp__memory__create_entities mcp__memory__add_observations mcp__memory__create_relations"
triggers:
  keywords: [prd, "product requirements", "requirements document", "requirements for", "define the requirements", "user stories", "acceptance criteria", "product spec", "formal spec"]
  examples:
    - "write a PRD for the SSO invite flow"
    - "create a product requirements document for billing"
    - "i need user stories and acceptance criteria for the dashboard"
  anti-triggers: [implement, build, brainstorm, explore, review]
---

# PRD — Product Requirements Document

Translate product vision and research into clear, actionable engineering specifications. Produces `PRD-[product-name].md` output files following an 8-section structure.

**Output file naming:** `PRD-[product-name].md` (e.g., `PRD-sso-invite-flow.md`)

## Argument Resolution

```python
PRODUCT = "$ARGUMENTS"  # Product name or feature, e.g., "SSO invite flow"
```

## STEP 0: Scope Clarification

```python
AskUserQuestion(
  questions=[{
    "question": "What type of PRD?",
    "header": "PRD Scope",
    "options": [
      {"label": "Full PRD (Recommended)", "description": "All 8 sections with research, stories, and release plan"},
      {"label": "Lightweight spec", "description": "Summary, objectives, user stories only"},
      {"label": "User stories only", "description": "INVEST stories with acceptance criteria"},
      {"label": "Update existing PRD", "description": "I have a PRD file to iterate on"}
    ],
    "multiSelect": false
  }]
)
```

## Task Management

```python
# 1. Create main task IMMEDIATELY
TaskCreate(subject="Write PRD: {PRODUCT}", description="8-section PRD with user stories and acceptance criteria", activeForm="Writing PRD for {PRODUCT}")

# 2. Create subtasks for each phase
TaskCreate(subject="Scope clarification", activeForm="Clarifying PRD scope")                       # id=2
TaskCreate(subject="Research and memory check", activeForm="Researching prior PRDs")               # id=3
TaskCreate(subject="Draft 8-section PRD", activeForm="Drafting PRD sections")                      # id=4
TaskCreate(subject="Write user stories and acceptance criteria", activeForm="Writing user stories") # id=5
TaskCreate(subject="Write output file", activeForm="Writing PRD file")                             # id=6

# 3. Set dependencies for sequential phases
TaskUpdate(taskId="3", addBlockedBy=["2"])  # Research needs scope first
TaskUpdate(taskId="4", addBlockedBy=["3"])  # Drafting needs research context
TaskUpdate(taskId="5", addBlockedBy=["4"])  # Stories need draft structure
TaskUpdate(taskId="6", addBlockedBy=["5"])  # Output needs all sections done

# 4. Update status as you progress
TaskUpdate(taskId="2", status="in_progress")  # When starting
TaskUpdate(taskId="2", status="completed")    # When done — repeat for each subtask
```

## Memory Integration

```python
# Search for prior PRDs and product decisions
mcp__memory__search_nodes(query="{PRODUCT} PRD requirements")

# After PRD is written, store key decisions
mcp__memory__create_entities(entities=[{
  "name": "PRD-{product-slug}",
  "entityType": "document",
  "observations": ["PRD written for {PRODUCT}", "Key objectives: ..."]
}])
```

## The 8-Section PRD Template

Load `Read("references/prd-template.md")` for the full template with all 8 sections (Summary, Contacts, Background, Objective, Market Segments, Value Propositions, Solution, Release), priority levels, and NFR categories.

## User Stories & Acceptance Criteria

Load `Read("references/user-stories-guide.md")` for INVEST criteria, story format, Gherkin acceptance criteria, and Definition of Ready/Done.

## Value Proposition Canvas

Load `Read("references/value-prop-canvas-guide.md")` for the canvas template and fit check process. Every Value Map item must correspond to a Job, Pain, or Gain.

## Go/No-Go Gate Criteria

Load from rules: `Read("rules/strategy-go-no-go.md")` for stage gate criteria and scoring thresholds (Go >= 7.0 | Conditional 5.0-6.9 | No-Go < 5.0).

## Rules (Load On-Demand)

- [research-requirements-prd.md](rules/research-requirements-prd.md) — INVEST user stories, PRD template, priority levels, DoR/DoD
- [strategy-value-prop.md](rules/strategy-value-prop.md) — Value proposition canvas, JTBD framework, fit assessment
- [strategy-go-no-go.md](rules/strategy-go-no-go.md) — Stage gate criteria, scoring, build/buy/partner decision matrix

## References

- [output-templates.md](references/output-templates.md) — Structured JSON output schemas for PRD, business case, and strategy artifacts
- [value-prop-canvas-guide.md](references/value-prop-canvas-guide.md) — Detailed value proposition canvas facilitation guide

## Output

After generating the PRD, write it to disk:

```python
Write(f"PRD-{product_slug}.md", prd_content)
TaskUpdate(status="completed")
```

> **Plan-mode filenames (CC 2.1.111+):** If this skill enters plan mode (via `EnterPlanMode`) before writing the PRD, CC 2.1.111 names the resulting plan file after the prompt stem rather than random words. To get a clean filename, include the product slug in the plan-mode prompt (e.g. `EnterPlanMode("PRD: authentication-rework")` → `plans/prd-authentication-rework.md`). Before 2.1.111, plan filenames were `plans/swift-cobra.md` etc. — review and rename as needed.

## Chain: Next Steps

After PRD is approved, decompose its acceptance criteria into a runnable goal, then implement:

```
prd-to-goal PRD-{product-slug}.md   # → one copy-pasteable `/goal until …, or stop after N turns` line
implement PRD-{product-slug}.md
```

`prd-to-goal` reduces the Go/No-Go gate + acceptance criteria below into a single AND-joined boolean assertion, so the PRD drives an autonomous `/goal` run rather than a manual read-through.

## Related Skills

- `ork:user-research` — Build user understanding (personas, journey maps, interviews) before writing the PRD
- `ork:prd-to-goal` — Reduce this PRD's acceptance criteria to a single `/goal until …, or stop after N turns` line
- `ork:implement` — Execute the implementation plan from the PRD
- `ork:brainstorm` — Explore solution alternatives before committing to PRD scope
- `ork:assess` — Rate PRD quality and completeness

---

**Version:** 2.0.0

© OrchestKit · MIT · yonatangross/orchestkit

Similar skills

Everything for Writing and docs →

From the same set10

devops-deployment A skill for CI/CD setup, containerization and infrastructure as code, with patterns for GitHub Actions, Docker, Helm and Terraform. CX Codex +1 1,600installs rag-retrieval A skill with ready-made retrieval-augmented generation patterns: hybrid search, HyDE, reranking, pgvector. Useful when you are wiring a RAG pipeline and want working recipes. CX Codex +1 1,500installs ui-components Supplies component library rules for shadcn/ui and Radix Primitives. It guides agents on v4 styles, OKLCH theming, CVA variants, and Zod form validation. CX Codex +1 1,500installs agent-orchestration A skill of patterns for autonomous agent loops, multi-agent coordination and multi-scenario runs. Useful when you build agent pipelines and pick a framework. CX Codex +1 1,400installs zustand-patterns A reference for Zustand 5.x state management: slices, middleware, Immer, useShallow, persistence and devtools. Useful when you want to drop Redux without the boilerplate. CX Codex +1 1,400installs domain-driven-design A skill for tactical DDD: entities, value objects, aggregates and bounded contexts. Useful once business logic outgrows plain CRUD. CX Codex +1 1,300installs security-patterns A skill of security patterns for authentication, input validation, injection defense and PII masking. Useful when you build auth flows or close OWASP Top 10 gaps. CX Codex +1 731installs langgraph A skill with 41 rules for LangGraph 1.x in Python: state schemas, node timeouts, routing, supervisors, checkpoints. Useful when you build a pipeline or a multi-agent system. CX Codex +1 359installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor