Agent skill

Write Prd

输入一个产品 idea（一句话或详细描述均可），自动生成图文并茂、结构完整的 PRD（产品需求文档），以 Markdown 格式保存到当前项目 markdown/ 目录，同时输出配套 SVG 图表文件。触发条件：用户提到"写 PRD"、"帮我写需求文档"、"生成 PRD"、"写产品需求文档"、"写商业需求文档"、"我有个产品想法"、"帮我把这个 idea 写成文档"、"PRD…

GPL-2.0Auto-check passedProduct & Project Management

Install Write Prd

skills CLI

$ npx skills add digoal/blog --skill write-prd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install digoal/blog write-prd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skills_for_claude_web/write-prd .claude/skills/write-prd && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "write-prd" agent skill from https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/write-prd into .claude/skills/write-prd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-prd", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/write-prd

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add digoal/blog --skill write-prd -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install digoal/blog write-prd --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skills_for_claude_web/write-prd .agents/skills/write-prd && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "write-prd" agent skill from https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/write-prd into .agents/skills/write-prd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-prd", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add digoal/blog --skill write-prd -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install digoal/blog write-prd --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skills_for_claude_web/write-prd .cursor/skills/write-prd && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "write-prd" agent skill from https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/write-prd into .cursor/skills/write-prd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-prd", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/digoal/blog.git --path skills/skills_for_claude_web/write-prd

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add digoal/blog --skill write-prd -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install digoal/blog write-prd --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skills_for_claude_web/write-prd .gemini/skills/write-prd && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "write-prd" agent skill from https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/write-prd into .gemini/skills/write-prd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-prd", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install digoal/blog write-prd

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add digoal/blog --skill write-prd -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skills_for_claude_web/write-prd .github/skills/write-prd && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "write-prd" agent skill from https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/write-prd into .github/skills/write-prd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-prd", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add digoal/blog --skill write-prd -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install digoal/blog write-prd --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skills_for_claude_web/write-prd .opencode/skills/write-prd && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "write-prd" agent skill from https://github.com/digoal/blog/tree/master/skills/skills_for_claude_web/write-prd into .opencode/skills/write-prd/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "write-prd", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: write-prd
GitHub stars: 8.6k
Token cost: ~2.2k tokens
SKILL.md length: 293 words
Files: 1
Skills in repo: 98
Repo updated: Sep 28, 2026
First seen: Oct 7, 2026
Licence: GPL-2.0

At a glance

Works in 4 steps: ：信息补全与 JTBD 推演 → ：搜索市场背景（使用 web_search） → ：生成 SVG 图表 → …
Tasks that involve PRD writing
SKILL.md covers 工作流总览, Step 1：信息补全与 JTBD 推演, Step 2：搜索市场背景（使用 web_search） and Step 3：生成 SVG 图表, plus 5 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Write Prd is an agent skill from digoal/blog. 输入一个产品 idea（一句话或详细描述均可），自动生成图文并茂、结构完整的 PRD（产品需求文档），以 Markdown 格式保存到当前项目 markdown/ 目录，同时输出配套 SVG 图表文件。触发条件：用户提到"写 PRD"、"帮我写需求文档"、"生成 PRD"、"写产品需求文档"、"写商业需求文档"、"我有个产品想法"、"帮我把这个 idea 写成文档"、"PRD 模板"、"产品立项文档"、"产品需求"、"功能需求文档"。即使用户只给出一句简短的产品描述如"我想做一个 XX 产品"，也应立即使用本 skill 生成 PRD。本 skill 面向产品经理、创业者、产品负责人，输出可直接用于团队评审和立项决策的专业文档，深度整合 JTBD 用户洞察框架、MoSCoW 优先级方法论和北极星指标体系。

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Product & Project Management, covering PRD writing and User stories. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.

When your agent uses it

Tasks that involve PRD writing
Tasks that involve User stories

Example prompts

“帮我写需求文档”
“生成 PRD”
“写产品需求文档”
“/write-prd”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

：信息补全与 JTBD 推演
：搜索市场背景（使用 web_search）
：生成 SVG 图表
：PRD Markdown 文件结构

What it can do on your machine

Read from SKILL.md and the folder at commit 69fb793. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Write Prd loads about 2.2k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 293 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~92
When it runs · the whole SKILL.md, loaded when a task matches: ~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from digoal/blog at commit 69fb793, republished under its GPL-2.0 licence (© digoal). 293 words, ~2,232 tokens.

Download SKILL.mdSave it as .claude/skills/write-prd/SKILL.md (or your agent's skills folder).

name: write-prd
description: 输入一个产品 idea（一句话或详细描述均可），自动生成图文并茂、结构完整的 PRD（产品需求文档），以 Markdown 格式保存到当前项目 markdown/ 目录，同时输出配套 SVG 图表文件。触发条件：用户提到"写 PRD"、"帮我写需求文档"、"生成 PRD"、"写产品需求文档"、"写商业需求文档"、"我有个产品想法"、"帮我把这个 idea 写成文档"、"PRD 模板"、"产品立项文档"、"产品需求"、"功能需求文档"。即使用户只给出一句简短的产品描述如"我想做一个 XX 产品"，也应立即使用本 skill 生成 PRD。本 skill 面向产品经理、创业者、产品负责人，输出可直接用于团队评审和立项决策的专业文档，深度整合 JTBD 用户洞察框架、MoSCoW 优先级方法论和北极星指标体系。

Write PRD Skill

将一个产品 idea 转化为完整、可直接评审的 PRD（Product Requirements Document）。

核心理念：PRD 是团队在不确定性中的共同契约。它的价值不在于格式，而在于把 WHY → WHAT → HOW → MEASURE 四个维度讲清楚。

工作流总览

用户输入 Idea
     ↓
Step 1: 信息补全 & JTBD 推演（不急于提问，先推断）
     ↓
Step 2: 搜索市场背景与竞品（web search）
     ↓
Step 3: 生成配套 SVG 图表（独立文件）
     ↓
Step 4: 生成完整 PRD Markdown 文件
     ↓
输出到 markdown/ 目录

Step 1：信息补全与 JTBD 推演

拿到用户的 idea 后，不要立刻问问题，先做推演：

1.1 JTBD 框架推断用户痛点

用以下格式在内部推断，不要直接展示给用户：

当 [目标用户] 在 [特定场景] 时， 他们需要 [完成某项工作/达到某个目标]， 但目前面临 [具体障碍]，导致 [可量化的业务/体验影响]。

1.2 五维推断清单

目标用户：谁会用这个产品？主用户 vs. 次要用户区分
核心痛点：用 JTBD 格式描述，不是"用户想要功能"，而是"用户想完成什么任务"
商业模式：产品如何盈利？服务于什么更大的商业目标？
差异化：和竞品相比，核心的差异化价值主张是什么？
成功指标：什么数字能证明这个产品成功了？（北极星指标）

1.3 推断优先于询问

如果信息足够推断，直接进入 Step 2
在 PRD 中用 [待确认] 标注推断字段
如需询问，一次性问不超过 3 个最关键的问题后再执行

Step 2：搜索市场背景（使用 web_search）

搜索以下信息，充实 PRD 背景章节：

市场规模：[产品领域] market size 2024/2025
主要竞品：[产品类型] top competitors features comparison
行业趋势：[用户痛点] trends [当前年份]
参考案例：[类似产品] success failure case study

搜索后提炼关键数据点，填入 PRD 对应章节。

Step 3：生成 SVG 图表

必须生成以下至少 2 个 SVG 图表，保存到 markdown/ 目录：

图表 A：产品功能架构图（必选）

展示核心功能模块及其层级关系。

文件名：[product-name]-architecture.svg
风格：分层色块 + 箭头，清晰展示模块间关联
必须包含：用户层、功能层、数据层（或类似的三层结构）

图表 B：核心用户旅程图（必选）

展示用户从发现问题到完成目标的完整路径，必须包含异常路径。

文件名：[product-name]-user-journey.svg
风格：横向流程 + 状态标注 + 情绪曲线（可选）
必须包含：触发点、关键节点、决策分叉、异常处理、成功终态

图表 C（视产品类型选择其一）：

竞品对比矩阵（有明确竞品时）：[product-name]-competitor-matrix.svg
数据流图（技术型/数据型产品）：[product-name]-data-flow.svg
商业模式关键要素（B端/平台类产品）：[product-name]-business-model.svg

SVG 技术规范

viewBox="0 0 860 [适当高度]"
font-family="'PingFang SC', 'Helvetica Neue', Arial, sans-serif"
使用 defs 定义 linearGradient 和 filter shadow
配色方案：
  主色：#4f46e5（靛蓝）或 #0f766e（深青）
  成功/正向：#10b981（绿）
  警告/注意：#f59e0b（琥珀）
  错误/风险：#ef4444（红）
  辅助文字：#64748b
  背景：#f8fafc 或 white
每个图表包含：标题行 + 图例（如有）+ 内容 + 底部说明
SVG 必须独立保存为文件，在 Markdown 中用 ![说明](filename.svg) 引用

Step 4：PRD Markdown 文件结构

文件命名：[product-name-en]-prd.md（英文小写，连字符分隔）

完整 PRD 模板

markdown

# [产品名称] PRD

> [一句话定位：这个产品为谁解决了什么问题，通过什么方式，预期带来什么价值]

**文档类型**：PRD（产品需求文档）
**文档状态**：草稿 / 评审中 / 已批准
**版本**：v1.0
**作者**：[PM 姓名]
**最后更新**：[日期]
**阅读时长**：约 X 分钟

---

## 一、执行摘要（Executive Summary）

[3-5句话的高管版摘要，包含：
- 我们在解决什么问题（问题规模）
- 我们的解决方案是什么（一句话）
- 成功后能带来什么商业价值（量化预期）]

---

## 二、问题定义

### 2.1 背景与现状

[市场背景，数据支撑，不超过200字。来自 Step 2 搜索结果]

### 2.2 用户痛点（JTBD 框架）

**当** [目标用户] **在** [使用场景] **时，**
他们需要 [完成某个任务/达到某个目标]，
但目前面临 [具体障碍]，
导致 [业务/用户体验影响，尽量量化]。

### 2.3 目标用户

**主要用户群体**：[描述]

**用户画像**：
- 人口属性：[年龄 / 职业 / 地域 / 数字化程度]
- 核心使用场景：[什么时候、在哪里、为什么用]
- 当前替代方案：[他们现在怎么解决这个问题]
- 最痛的三个点：[按严重程度排序]

### 2.4 市场机会

| 指标 | 数值 | 来源 |
|------|------|------|
| TAM（总可寻址市场） | | [来源] |
| SAM（可服务市场） | | [来源] |
| SOM（可获取份额） | | 推断 |
| 市场增长率 | | [来源] |

---

## 三、解决方案

### 3.1 产品定位

> 我们是 **[产品类型]**，帮助 **[目标用户]** **[核心价值主张]**，不像 **[竞品]**，我们 **[差异化]**。

### 3.2 功能架构

![功能架构图]([product-name]-architecture.svg)

*[一句话说明图的阅读方式]*

### 3.3 核心功能（MoSCoW 优先级）

> ⚠️ 注意：Must Have 应严格控制，"所有功能都是 Must"意味着 PRD 未完成取舍。

#### ✅ Must Have（MVP 必须包含，缺失则不可上线）

| 功能 | 用户故事 | 验收标准 | 优先级 |
|------|---------|---------|--------|
| [功能1] | As a [用户类型], I want [行为], so that [目的] | Given [前置条件] When [用户操作] Then [系统响应+性能指标] | P0 |

#### 🔶 Should Have（重要但 MVP 可简化版本交付）

| 功能 | 用户故事 | 优先级 |
|------|---------|--------|
| [功能] | As a [用户], I want [行为], so that [目的] | P1 |

#### 🔷 Could Have（有余力再做，不影响核心价值）

- [功能列表，简述即可]

#### ❌ Won't Have（本期明确不做——这行和上面同等重要）

| 功能 | 排除原因 |
|------|---------|
| [功能] | [资源限制 / 复杂度过高 / 非核心路径] |

### 3.4 核心用户旅程

![用户旅程图]([product-name]-user-journey.svg)

*[说明图中的关键决策节点和异常路径处理]*

### 3.5 非功能需求

| 维度 | 要求 | 验证方式 |
|------|------|---------|
| 性能 | [页面加载 ≤ Xms / P95 响应时间 ≤ Xms] | 压测 / 监控 |
| 安全 | [数据加密标准 / 合规要求] | 安全审计 |
| 可用性 | [99.X% Uptime SLA] | 监控告警 |
| 扩展性 | [支持 X 并发用户 / X QPS] | 架构评审 |
| 兼容性 | [支持的平台/浏览器版本] | 兼容性测试 |

---

## 四、竞品分析

[竞品对比，说明差异化优势。如生成了竞品矩阵 SVG，在此引用]

| 维度 | 我们 | 竞品A | 竞品B |
|------|------|-------|-------|
| 核心功能 | | | |
| 目标用户 | | | |
| 定价模式 | | | |
| 差异化 | ✅ | | |

---

## 五、成功指标

### 5.1 北极星指标（North Star Metric）

> **[唯一最重要的指标名称]**：[具体计算口径]
>
> 选择理由：[为什么这个指标能同时反映用户价值和商业价值]

### 5.2 分层指标体系

**输入指标**（你能直接影响的）：

| 指标 | 基线 | 目标值（3个月） | 观测周期 |
|------|------|--------------|---------|
| [核心功能使用率] | | | 周 |
| [核心流程完成率] | | | 周 |
| [用户留存率] | | | 月 |

**护栏指标**（不能因为优化北极星而损害的底线）：

| 指标 | 红线 |
|------|------|
| 错误率 | ≤ X% |
| 投诉率 | 不高于基线 |
| 核心链路可用性 | ≥ 99.X% |

### 5.3 实验设计

- **A/B 测试方案**：[实验组 vs. 对照组的划分逻辑]
- **最小可检测效果（MDE）**：[能检测到多大的指标变化]
- **实验周期**：[X 周，需避开节假日和大促干扰]
- **灰度策略**：5% → 20% → 50% → 100%
- **回滚条件**：[出现什么数据信号（具体数字）立即停止并回滚]

---

## 六、执行计划

### 6.1 范围边界

**In Scope（本期包含）**：
- [功能/能力列表]

**Out of Scope（本期不做——和功能清单同等重要）**：
- [明确排除的功能，及原因：资源/复杂度/战略优先级]

### 6.2 里程碑

> 里程碑 = 可验证的交付物，不是时间点

| 阶段 | 可验证交付物 | 时间节点 | 负责人 |
|------|------------|---------|--------|
| Discovery 完成 | 用研报告通过 + 竞品分析输出 | [日期] | PM |
| 设计评审通过 | 高保真原型 + 核心流程走通 | [日期] | Design |
| 技术方案确认 | 架构评审 + 技术风险识别 | [日期] | Tech Lead |
| MVP 开发完成 | 核心 P0 功能通过 UAT | [日期] | 全团队 |
| 灰度上线 | 5% 用户 + 监控正常 | [日期] | PM + Dev |
| 全量上线 | 指标验证通过 | [日期] | PM |

### 6.3 资源需求

| 角色 | 工作量（人天） | 主要职责 |
|------|-------------|---------|
| 产品经理 | | 需求管理、跨团队协调、指标追踪 |
| 设计师 | | 原型设计、交互规范 |
| 前端工程师 | | |
| 后端工程师 | | |
| 测试工程师 | | 测试方案、UAT |

---

## 七、风险评估

| 风险类型 | 具体风险描述 | 可能性 | 影响程度 | 应对方案 |
|---------|------------|--------|---------|---------|
| 技术风险 | [如：第三方 API 稳定性] | 中 | 高 | [降级方案 + SLA 协议] |
| 市场风险 | [如：竞品抢先上线] | 低 | 高 | [差异化策略] |
| 资源风险 | [如：关键工程师离职] | 低 | 中 | [文档化 + 知识转移] |
| 合规风险 | [如：数据隐私合规] | 低 | 极高 | [法务提前介入] |
| 假设失效风险 | [如：用户访谈结论有偏差] | 中 | 高 | [MVP 快速验证 + 预设回滚] |

---

## 八、干系人与审批

### 8.1 RACI 矩阵

| 事项 | PM | 工程 | 设计 | 运营 | 法务 | 管理层 |
|------|----|----|------|------|------|------|
| 需求确认 | R | C | C | C | I | A |
| 技术方案 | C | R | I | | | I |
| 设计评审 | A | C | R | C | | I |
| 上线决策 | R | C | C | C | C | A |
| 数据验收 | R | C | | C | | I |

*R=负责执行 A=最终拍板 C=需要咨询 I=需要知会*

### 8.2 审批记录

| 干系人 | 角色 | 意见摘要 | 签字日期 |
|--------|------|---------|---------|
| | | | |

---

## 九、附录

### 9.1 关键假设清单

> [待确认] 标记的字段，上线前需确认

| 编号 | 假设内容 | 验证方式 | 状态 |
|------|---------|---------|------|
| A1 | [如：用户愿意为此付费] | 用户访谈 / MVP 验证 | 待确认 |

### 9.2 术语表

| 术语 | 定义 |
|------|------|
| [专有名词] | [定义] |

### 9.3 参考文档

- [ ] 用户研究报告：[链接]
- [ ] 竞品分析报告：[链接]
- [ ] 技术可行性评估：[链接]
- [ ] 数据分析报告：[链接]
- [ ] 法务合规意见：[链接]

### 9.4 修订历史

| 版本 | 日期 | 修改内容 | 修改人 |
|------|------|---------|--------|
| v1.0 | [日期] | 初始版本 | |

写作质量核查清单

WHY 层（问题定义）

是否用 JTBD 格式（当/在/需要/面临/导致）写出用户痛点？
用户痛点是否有具体数字支撑（用研数据 or 市场数据）？
是否明确区分了"用户问题"和"解决方案"（别把功能写成痛点）？
市场机会是否覆盖 TAM/SAM/SOM 三层？

WHAT 层（功能规格）

Must Have 功能是否严格克制（不超过 5 个核心功能）？
所有 Must Have 是否有 Given/When/Then 验收标准？
验收标准是否包含性能指标（数字，不是"快速"）？
是否写了 Won't Have 并注明原因？
MoSCoW 是否有真正的分层（不全是 Must）？

HOW 层（执行计划）

用户旅程图是否覆盖了异常路径（不只是 Happy Path）？
里程碑是否是"可验证交付物"而非"时间点"？
非功能需求是否包含性能、安全、可用性、扩展性？
是否有明确的 Out of Scope？

MEASURE 层（成功指标）

是否定义了唯一的北极星指标？
是否区分了输入指标和护栏指标？
所有指标是否有基线值和目标值（数字）？
A/B 测试方案是否包含回滚条件（具体触发数字）？

图表质量

架构图是否展示了三层结构（用户/功能/数据）？
用户旅程图是否有异常路径处理？
SVG 是否单独保存为文件并在 Markdown 中正确引用？
每张图是否有标题和简短说明？

整体文档

执行摘要能否让不懂背景的人 1 分钟内理解核心价值？
所有 [待确认] 字段是否在文档中明确标注？
是否有清晰的 RACI 和审批链条？
风险评估是否覆盖技术、市场、资源、合规、假设失效五个维度？

特殊场景处理

场景 A：用户只给了一句话 idea

直接推演所有信息，用 [待确认] 标注推断字段，生成完整文档后告知用户哪些需要补充确认。

场景 B：用户给了详细描述

提取关键信息直接填充模板，搜索市场数据补充背景章节，无需打断流程问问题。

场景 C：用户要求简版 PRD（1-2页）

只生成以下核心章节：

JTBD 问题定义（必须）
Must Have 功能 + 验收标准（必须）
北极星指标（必须）
里程碑（必须）
省略：竞品分析、RACI、附录

场景 D：B 端产品 PRD

竞品分析部分增加"购买决策链分析"（谁付钱/谁决策/谁使用）
成功指标加入客户成功指标：NPS / Churn Rate / ARR
用户旅程区分"购买旅程"和"使用旅程"两条线

场景 E：内部工具 PRD

简化市场分析（替换为"内部现状分析"）
增加"效率提升量化"章节（ROI 测算）
指标侧重内部 ROI 和工时节省

场景 F：Agile 团队 PRD

强调"活文档"属性：标注当前 Sprint 范围
功能章节按 Epic → Story 层级组织
里程碑对应 Sprint 而非月份

输出文件清单

生成完成后，markdown/ 目录应包含：

markdown/
├── [product-name]-prd.md              ← 主文档
├── [product-name]-architecture.svg   ← 功能架构图（必选）
├── [product-name]-user-journey.svg   ← 用户旅程图（必选）
└── [product-name]-*.svg              ← 其他可选图表

触发示例

以下均应触发本 Skill：

"帮我写一份 PRD，产品是一个帮助设计师管理灵感的 App"
"我想做一个企业内部的知识库系统，帮我出一份需求文档"
"有个 idea：给餐厅做一个 AI 点餐助手，帮我写成 PRD"
"写个 PRD 模板"
"产品立项需要一份产品需求文档，我们要做 XX"
"帮我把这个产品想法整理成文档，方便跟团队对齐"
"我想做个 XX，帮我写 PRD"
"用 JTBD 框架帮我写需求文档"

Files

Just SKILL.md in skills/skills_for_claude_web/write-prd of digoal/blog.

Open the folder on GitHubat commit 69fb793

Compare with similar skills

Write Prd next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Write Prd compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Write Prd this skilldigoal/blog	8.6k	—	~2.2k	Automated safety check: Pass	GPL-2.0	10 days ago
Ralph Tui Create Beadssubsy/ralph-tui	2.5k	1 repos	~2.6k	Automated safety check: Pass	MIT	1 mo ago
Ralph Tui Create Beads Rustsubsy/ralph-tui	2.5k	1 repos	~2.8k	Automated safety check: Pass	MIT	1 mo ago
Ralph Tui Create JSONsubsy/ralph-tui	2.5k	1 repos	~2.6k	Automated safety check: Pass	MIT	1 mo ago
To Prdywwynm/EverythingDone	144	11 repos	~777	Automated safety check: Pass	GPL-3.0	24 days ago
Ralphjulianromli/opencode-template	144	1 repos	~1.1k	Automated safety check: Pass	None	8 mo ago

Similar skills

Ralph Tui Create Beads
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.
2.5k GitHub starsUsed in 1 repo~2.6k tokens
Product & Project ManagementAuto-check passed
Ralph Tui Create Beads Rust
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).
2.5k GitHub starsUsed in 1 repo~2.8k tokens
Product & Project ManagementAuto-check passed
Ralph Tui Create JSON
subsy/ralph-tui
Convert PRDs to prd.json format for ralph-tui execution. An agent skill from subsy/ralph-tui.
2.5k GitHub starsUsed in 1 repo~2.6k tokens
Product & Project ManagementAuto-check passed
To Prd
ywwynm/EverythingDone
Turn the current conversation context into a PRD and publish it to the project issue tracker.
144 GitHub starsUsed in 11 repos~777 tokens
Product & Project ManagementAuto-check passed
Ralph
julianromli/opencode-template
Autonomous agent loop for completing features. An agent skill from julianromli/opencode-template.
144 GitHub starsUsed in 1 repo~1.1k tokens
Product & Project ManagementAuto-check passed
Use Case Writer
phucnt-bazone-vietnam/use-case-writer
Generate Use Case specifications in English Markdown following the IT BA standard 13-field template (Karl Wiegers / IIBA).
142 GitHub stars~4.1k tokensUpdated 4 mo ago
Product & Project ManagementAuto-check passed

More from digoal/blog

All 98 skills in this repo

Article Fact Checker
digoal/blog
三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…
8.6k GitHub stars~939 tokensUpdated 10 days ago
Auto-check passed
Find Postgres Bug
digoal/blog
Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…
8.6k GitHub stars~4k tokensUpdated 10 days ago
Auto-check passed
Digoal
digoal/blog
Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…
8.6k GitHub stars~2.2k tokensUpdated 10 days ago
Auto-check passed
Paper Interpretation
digoal/blog
从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读，并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…
8.6k GitHub stars~1.5k tokensUpdated 10 days ago
Auto-check passed
Product Multi Role Analysis
digoal/blog
Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…
8.6k GitHub stars~1.8k tokensUpdated 10 days ago
Auto-check passed
Blog Cover Poster
digoal/blog
Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.
8.6k GitHub stars~1.4k tokensUpdated 10 days ago
Auto-check passed

Questions about Write Prd

What does Write Prd do?

When should I use Write Prd?

Write Prd fits situations like: tasks that involve PRD writing; tasks that involve User stories.

How do I install Write Prd in Claude Code?

Run `npx skills add digoal/blog --skill write-prd -a claude-code`. Or copy the skill folder (skills/skills_for_claude_web/write-prd in digoal/blog) into .claude/skills/write-prd in your project. Claude Code loads it when a task matches its description.

How do I install Write Prd in Codex?

Run `npx skills add digoal/blog --skill write-prd -a codex`. Or copy the skill folder (skills/skills_for_claude_web/write-prd in digoal/blog) into .agents/skills/write-prd in your project. Codex loads it when a task matches its description.

Can I use Write Prd in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add digoal/blog --skill write-prd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/write-prd, .gemini/skills/write-prd, .github/skills/write-prd and .opencode/skills/write-prd in your project.

What does Write Prd need to run?

SKILL.md names no scripts, command-line tools or credentials: Write Prd is instructions for the agent only.

Does Write Prd access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Write Prd safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Write Prd use?

Write Prd is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Write Prd use?

About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Write Prd?

Skills that share tags, products or a category with Write Prd: Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Ralph Tui Create Beads Rust (subsy/ralph-tui, 2.5k stars), Ralph Tui Create JSON (subsy/ralph-tui, 2.5k stars) and To Prd (ywwynm/EverythingDone, 144 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Write Prd?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,587 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on September 28, 2026.

Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Write Prd

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Write PRD Skill

工作流总览

Step 1：信息补全与 JTBD 推演

1.1 JTBD 框架推断用户痛点

1.2 五维推断清单

1.3 推断优先于询问

Step 2：搜索市场背景（使用 web_search）

Step 3：生成 SVG 图表

图表 A：产品功能架构图（必选）

图表 B：核心用户旅程图（必选）

图表 C（视产品类型选择其一）：

SVG 技术规范

Step 4：PRD Markdown 文件结构

完整 PRD 模板

写作质量核查清单

WHY 层（问题定义）

WHAT 层（功能规格）

HOW 层（执行计划）

MEASURE 层（成功指标）

图表质量

整体文档

特殊场景处理

场景 A：用户只给了一句话 idea

场景 B：用户给了详细描述

场景 C：用户要求简版 PRD（1-2页）

场景 D：B 端产品 PRD

场景 E：内部工具 PRD

场景 F：Agile 团队 PRD

输出文件清单

触发示例

Files

Compare with similar skills

Similar skills

More from digoal/blog

Related

Questions about Write Prd