Prd

Use when turning a product or AI feature idea into a measurable Product Requirements Document with user stories, technical specifications, acceptance criteria, evaluation, risks, and rollout phases.

9 stars 3 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add sandbaseai/workbuddy-skill --skill prd
Manual install
git clone --depth 1 https://github.com/sandbaseai/workbuddy-skill.git /tmp/workbuddy-skill
mkdir -p ~/.claude/skills
cp -r /tmp/workbuddy-skill/skills/prd ~/.claude/skills/prd

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 产品需求文档(PRD)

把模糊的产品或 AI 功能想法转换成业务、设计、工程、评测和运营都能执行的需求契约。PRD 的目标不是填满模板,而是让问题、范围、成功标准、约束、风险和决策责任可验证、可追踪。

## 激活与证据边界

适用于新产品/功能启动、需求澄清、AI 能力规格、验收标准设计和实施前统一范围。开始前记录文档受众、决策人、版本和允许使用的资料范围。

- 至少提出两个关键澄清问题;如果用户暂时无法回答,写成 `TBD` 或明确假设,不要猜测技术栈、预算、法规、用户规模或发布日期。
- 将信息分成 `Confirmed`(有来源或用户确认)、`Assumption`(待确认)、`Unknown`(尚无证据)和 `Decision`(需要负责人选择)。不要把推断写成事实。
- 只读取授权的产品、用户研究、分析、设计、代码和政策资料;最小化个人数据,报告中脱敏,不复制客户内容、凭据或私有提示词。
- 工具、API、数据库、实验、付费调用和生产写入必须在需求中标注用途、权限、成本和授权人;PRD 本身不代表已经批准实施。
- 所有指标写明单位、时间窗口、分母、基线、目标、数据来源和统计口径。避免只写“快”“智能”“易用”“现代”。

## Phase 1:发现问题

先询问并记录:

1. 核心用户和具体痛点是什么,为什么现在解决?
2. 成功如何衡量,当前基线和期望改善是多少?
3. 目标市场、平台、地区、语言、时间、预算和技术约束是什么?
4. 已有方案、替代方案和不做这件事的代价是什么?
5. 哪些内容已经决定,哪些需要产品、工程、安全、法务或数据负责人确认?

将答案与来源绑定;把无法回答的问题放入 Assumptions/Unknowns,并说明会阻塞哪项决策。

## Phase 2:分析与定界

- 画出从触发到结果的用户流程,标出成功、空结果、错误、取消、权限不足和恢复路径。
- 定义目标用户、反目标用户、用户故事、非目标和明确的 MVP 边界。每个用户故事都必须有可观察的完成条件。
- 盘点依赖:API、数据集、身份、存储、模型、人工审核、供应商、迁移、运营和支持;为每项标注 owner、状态和替代方案。
- 对 AI 功能额外定义输入/输出、工具调用、引用或来源要求、拒答条件、人工升级、评测集、质量阈值、延迟、成本和漂移监测。
- 用影响/成本/风险或 RICE 等明确方法排序,不以“大家都觉得重要”作为优先级证据。

## Phase 3:按固定 Schema 起草
Read the full skill on GitHub

Details

Skill name
prd
Path
skills/prd/SKILL.md
License
MIT
Repo updated
8 September 2026

FAQ

What does the Prd skill do?

Use when turning a product or AI feature idea into a measurable Product Requirements Document with user stories, technical specifications, acceptance criteria, evaluation, risks, and rollout phases.

How do I install the Prd skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add sandbaseai/workbuddy-skill --skill prd. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Prd popular?

It lives in sandbaseai/workbuddy-skill, which has 9 GitHub stars and 3 forks.

Related skills

Access Control Security Best Practices

9

sandbaseai/workbuddy-skill

Design, review, implement, and verify least-privilege access controls across users, services, tenants, resources, and administrative workflows.

Security

Accessibility Review

9

sandbaseai/workbuddy-skill

Use when reviewing a web interface or interaction for semantic, keyboard, focus, screen-reader, ARIA, and contrast accessibility risks.

Frontend & Design

Acquire Codebase Knowledge

9

sandbaseai/workbuddy-skill

Use when the user asks to map, document, or onboard into an existing codebase and needs evidence-backed architecture, structure, conventions, integrations, testing, and concerns documentation.

Software Development

Prompt Injection Defense

9

sandbaseai/workbuddy-skill

Use when threat-modeling or hardening an AI agent, RAG system, assistant, or tool workflow against direct, indirect, stored, cross-agent, or multimodal prompt injection.

AI, LLMs & Agents

Parallel Agent Dispatch

9

sandbaseai/workbuddy-skill

Use when two or more work items are genuinely independent and can be investigated concurrently without shared mutable state or sequential dependencies.

AI, LLMs & Agents

Prompt Optimizer

9

sandbaseai/workbuddy-skill

Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for any LLM model inside a chat interface — NOT the API. Use this skill whenever the user wants to write, rewrite, optimize, improve, sharpen, or polish a prompt for chat. Trigger phrases include "rewrite this prompt", "make this a better prompt", "optimize this prompt", "turn this into a prompt", "help me prompt this", "draft a prompt that...", "I want to ask...", or whenever the user pastes a draft prompt and asks for improvements. Also trigger when the user describes a task they plan

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.