PRD-Writer for Openclaw

A high-performance AI skill designed to transform raw ideas or fragments into comprehensive, audit-ready Product Requirement Documents.

xx235300
v3.0.0
Apr 11, 2026
0
777
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install prd-assistant

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install prd-assistant using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is PRD-Writer?

PRD-Writer is an advanced technical documentation engine within the Openclaw Skills ecosystem. It utilizes a rigorous three-phase workflow—Context Gathering, Refinement & Structure, and Reader Testing—to ensure every document meets industry standards. By integrating MoSCoW prioritization and five-party review modules (Technical, Operational, Design, Business, and Legal), it bridges the gap between initial product vision and executable engineering specifications.

This skill is particularly powerful for product managers and developers who need to visualize complex logic, as it natively supports Mermaid.js for generating user journeys and business flowcharts. Whether you are starting from a single sentence or optimizing an existing draft, PRD-Writer ensures your documentation is thorough, logical, and ready for stakeholder approval.

PRD-Writer Use Cases

  • Creating full-scale PRDs from high-level natural language descriptions.
  • Refining and structuring rough drafts or functional lists into professional documentation.
  • Visualizing business logic and user journeys using Mermaid diagrams.
  • Conducting multi-dimensional feasibility reviews including technical, legal, and ROI analysis.
  • Translating product requirements into bilingual (English/Chinese) formats for global teams.

How PRD-Writer Works

  1. Mode Selection: The agent identifies the user's intent to choose between Full, Standard, or Quick (MVP) modes.
  2. Context Gathering: A 7-dimension inquiry process collects project background, target users, core features, and technical constraints.
  3. Requirement Confirmation: The agent presents a structured checklist for the user to verify all P0/P1 requirements.
  4. Structured Generation: The skill generates 8 distinct chapters, applying MoSCoW priorities and embedding Mermaid logic.
  5. Five-Party Review: A comprehensive audit is performed across technical, operational, and legal dimensions.
  6. Reader Testing: A final validation phase where the user reviews the v0.9 draft and provides feedback for iterative refinement.

PRD-Writer Setup

To integrate this capability into your environment, follow these steps within your Openclaw Skills configuration:

# Clone the skill repository
git clone https://github.com/openclaw/prd-writer-skill.git

# Navigate to the modules directory
cd prd-writer/modules

# Ensure the HTML templates for Mermaid rendering are accessible
ls HTML_template/mermaid_template.html

Configure your local config.json to point to the PRD_Template_EN.md or PRD_Template_ZH.md depending on your primary documentation language.

PRD-Writer Data Schema & Taxonomy

PRD-Writer organizes data through a hierarchical template system and specialized review modules:

Data Component Format Description
Core Templates Markdown (.md) Structured files for English and Chinese PRD layouts.
Review Modules Directory Logic for Technical, Operational, Design, Business, and Legal audits.
Diagrams Mermaid.js Code blocks representing user journeys and flowcharts.
Attachments HTML Standalone files with embedded Mermaid CDN for offline viewing.
Metadata JSON Tracking project name, mode, language, and generation timestamp.

PRD-Writer Advanced Features

  • Multi-Agent Protocol: Seamlessly fetches external documentation via feishu_fetch_doc for Mode C analysis.
  • Automated Prioritization: Built-in MoSCoW (Must, Should, Could, Won't) logic to categorize functional requirements.
  • Visual Engine: Generates standalone HTML attachments containing rendered flowcharts for non-technical stakeholders.
  • Bilingual Output: Support for simultaneous generation of English and Chinese documentation.
  • Interactive Review Toggle: Dynamic enabling/disabling of the five-party review module based on user urgency.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*