write-prd

write-prd is a command for coding agents from killvxk/pm-skills-zh. It costs 20 tokens per session (1,132 once invoked), scanned A, original, MIT.

A command for creating a product requirement document, or PRD, from a feature idea, problem, request, or source document. A PRD records what should be built, for whom, why, and how success will be measured.

In plain words
What is it for?
Use it to create a PRD for a feature or problem, gather missing context through questions, and organise user needs, priorities, constraints, alternatives, and measurable outcomes.
Why use it?
It turns vague product input into a structured document that helps stakeholders and developers agree on the problem, scope, users, requirements, and success measures.

Command

Part of the pm-execution plugin — 15 skills, 10 commands shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/killvxk/pm-skills-zh/write-prd
Clone the repo
git clone --depth 1 https://github.com/killvxk/pm-skills-zh

Or install pm-execution, the plugin that ships this one along with the rest of its 15 skills, 10 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for write-prd

README.md
[![agentmods](https://agentmods.dev/badge/commands/killvxk/pm-skills-zh/write-prd.svg)](https://agentmods.dev/commands/killvxk/pm-skills-zh/write-prd)
Your own site
<a href="https://agentmods.dev/commands/killvxk/pm-skills-zh/write-prd"><img src="https://agentmods.dev/badge/commands/killvxk/pm-skills-zh/write-prd.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,132 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.01132
Opus 5 $0.00010 $0.00566
Sonnet 5 $0.00004 $0.00226
Haiku 4.5 $0.00002 $0.00113

Measured 4d ago against content hash 4e9b0ba5cfcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-prd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

pm-execution/commands/write-prd.md · 119 lines

What it actually says

/write-prd -- 产品需求文档

创建结构清晰的 PRD(产品需求文档),对齐干系人并指导开发。接受从模糊想法到详细简报的任意形式输入。

Invocation(调用示例)

/write-prd 面向企业客户的 SSO 支持
/write-prd 用户在用户引导第 3 步流失——我们需要解决这个问题
/write-prd [上传简报、调研文档或战略文件]

Workflow(工作流程)

Step 1:理解功能

接受以下任意形式的输入:

  • 功能名称("SSO 支持")
  • 问题陈述("企业客户一直要求集中式身份认证")
  • 用户诉求("用户希望将数据导出为 CSV")
  • 模糊想法("我们应该对用户引导流失做些什么")
  • 上传的文档(简报、调研报告、Slack 讨论串、邮件)

Step 2:收集背景信息

以对话方式询问——优先问最重要的问题,边聊边补充细节:

  1. 用户痛点:这解决了什么问题?谁在经历这个问题?痛苦程度如何?
  2. 目标用户:哪些用户群体?规模多大?他们现在的替代方案是什么?
  3. 成功指标:如何判断是否成功?搞定这个会带动哪些指标变化?
  4. 约束条件:技术约束、时间线、合规要求、对其他团队的依赖?
  5. 已有方案:之前尝试过吗?市场上有哪些现有解决方案?
  6. 范围偏好:完整方案还是分阶段交付?

如果用户提供了含背景信息的文档,提取可用内容,只问缺失的部分。

Step 3:生成 PRD

应用 create-prd 技能,生成 8 节文档:

## 产品需求文档:[功能名称]

**作者**: [用户]
**日期**: [今天]
**状态**: 草稿
**干系人**: [如已知]

### 1. 执行摘要
[2-3 句话:做什么、为谁做、为什么现在做]

### 2. 背景与上下文
[问题空间、前期调研、市场背景、发起缘由]

### 3. 目标与成功指标
**目标**(成功的样子):
1. [具体可衡量的目标]
2. [...]

**非目标**(明确不在范围内):
1. [我们不做什么,以及原因]
2. [...]

**成功指标**:
| 指标 | 当前值 | 目标值 | 衡量方式 |
|------|--------|--------|---------|

### 4. 目标用户与细分市场
[服务对象、用户画像、细分市场规模]

### 5. 用户故事与需求

**P0 — 必须有**:
| # | 用户故事 | 验收标准 |
|---|---------|---------|

**P1 — 应该有**:
| # | 用户故事 | 验收标准 |
|---|---------|---------|

**P2 — 可以有/未来版本**:
| # | 用户故事 | 验收标准 |
|---|---------|---------|

### 6. 解决方案概述
[高层次方案、关键设计决策、技术方案(如已知)]

### 7. 待解问题
| 问题 | 负责人 | 截止日期 |
|------|-------|---------|

### 8. 时间线与分阶段计划
[里程碑、依赖项、分阶段计划(如适用)]

Step 4:评审与迭代

生成后提供:

  • "需要我收紧范围吗?我可以挑战哪些 P1 应该降级为 P2。"
  • "需要我**对这份 PRD 做事前剖析(Pre-mortem)**吗?"
  • "需要我将其拆解为面向工程团队的用户故事吗?"
  • "需要我创建干系人更新通知来推广这份 PRD 吗?"

将 PRD 保存为 Markdown 文件到用户工作区。

Notes(注意事项)

  • 对范围要有主见——一份范围清晰的 PRD 优于一份包罗万象但模糊的 PRD
  • 如果想法太大,主动建议分阶段,只规格化第一阶段
  • 非目标和目标同样重要——它们防止范围蔓延
  • 成功指标必须具体:"改善 NPS"不好,"90 天内将 NPS 从 32 提升至 45"才好
  • 待解问题应该是真正未解决的——不要把能从上下文回答的问题也列进去
  • 如果用户提供了调研数据,将洞察融入背景章节并注明来源
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 119 lines · 20 tokens per session scan A 4e9b0ba5cfcc

Subscribe to this mod's changes

write-prd is a command published in the GitHub repository killvxk/pm-skills-zh (151 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 1,132 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.