What is write-stories?

A command that breaks a feature idea or product specification into structured work items. It supports user stories, job stories, and WWA items, each with acceptance criteria that describe when the work is complete.

Use it to decompose a feature, PRD, research finding, or spoken idea into 5–15 prioritized stories in the format your team uses.

It turns a broad request into smaller, testable tasks that a team can plan and review.

write-stories — Command for Claude Code by killvxk: A command that breaks a feature idea or product…

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-stories

Clone the repo

git clone --depth 1 https://github.com/killvxk/pm-skills-zh

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/killvxk/pm-skills-zh/write-stories.svg)](https://agentmods.dev/commands/killvxk/pm-skills-zh/write-stories)

Your own site

<a href="https://agentmods.dev/commands/killvxk/pm-skills-zh/write-stories"><img src="https://agentmods.dev/badge/commands/killvxk/pm-skills-zh/write-stories.svg" alt="Measured on agentmods" height="20"></a>

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,110 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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.01110
Opus 5	$0.00013	$0.00555
Sonnet 5	$0.00005	$0.00222
Haiku 4.5	$0.00003	$0.00111

Measured 6d ago against content hash b712a9ae6087, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

write-stories 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 6d 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-stories.md · 113 lines

What it actually says

/write-stories -- 待办事项生成器

将功能拆解为结构清晰的待办事项。根据团队偏好选择三种格式之一，每条均附有完整的验收标准。

Invocation（调用示例）

/write-stories user 允许用户将报告导出为 PDF 和 CSV
/write-stories job 任务截止日期通知系统
/write-stories wwa 移动端深色模式
/write-stories [上传 PRD 或功能规格]      # 询问格式偏好
/write-stories                              # 询问功能和格式

Formats（格式）

用户故事（User Stories）

格式：「作为 [用户类型]，我想要 [功能]，以便 [收益]」应用 user-stories 技能：

遵循 3C 原则：Card（简短卡片）、Conversation（上下文对话）、Confirmation（验收标准）
根据 INVEST 标准验证：Independent（独立）、Negotiable（可协商）、Valuable（有价值）、Estimable（可估算）、Small（小）、Testable（可测试）
在相关处包含设计链接或原型参考

工作故事（Job Stories）

格式：「当 [情境] 时，我想要 [动机]，以便 [结果]」应用 job-stories 技能：

聚焦情境和背景，而非用户角色
基于调研中观察到的真实用户场景
适合使用 JTBD（Jobs-to-be-Done，用户待办任务）理论的团队

WWA（为什么-做什么-验收标准）

格式：为什么 [战略背景] → 做什么 [可交付内容] → 验收标准 [标准] 应用 wwas 技能：

包含战略推理（我们为什么要构建这个）
产出独立、有价值、可测试的条目
适合需要业务背景的跨职能团队

Workflow（工作流程）

Step 1：接收功能描述

接受任意形式：PRD（产品需求文档）、功能描述、用户调研发现或口头想法。如果提供了 PRD，提取需求进行拆解。

Step 2：确定格式

如果调用时未指定格式，询问：

"你的团队使用哪种格式？用户故事、工作故事还是 WWA？"
如果不确定，推荐默认使用用户故事

Step 3：拆解功能

将功能拆解为 5-15 个独立故事（小到足以在一个 Sprint 内完成）
确保每个故事独立有价值（本身能交付用户价值）
按依赖关系和优先级排序
每个故事编写 3-5 条验收标准
标注需要设计输入或技术预研的故事

Step 4：生成故事

## 待办清单：[功能名称]

**格式**: [用户故事 / 工作故事 / WWA]
**故事总数**: [数量]
**预估总工作量**: [如可估算]

### 故事列表

#### 故事 1：[简短标题]
**[所选格式的故事描述]**

验收标准：
- [ ] [标准 1]
- [ ] [标准 2]
- [ ] [标准 3]

优先级：[P0/P1/P2] | 工作量：[S/M/L] | 依赖项：[无或列举]

---
[对每个故事重复以上格式]

### 故事地图
[视觉排序：必须有 → 应该有 → 可以有]

### 技术备注
[横切关注点：API 变更、数据迁移、基础设施]

### 待解问题
[实现前需要明确的事项]

保存为 Markdown 格式。

Step 5：提供后续建议

"需要我为这些故事生成测试场景吗？"
"需要我为开发和测试创建虚拟数据吗？"
"需要我为这些故事估算 Sprint 容量吗？"
"需要我转换为其他格式（用户故事 ↔ 工作故事 ↔ WWA）吗？"

Notes（注意事项）

一个故事 = 一个可部署的价值单元——如果它需要另一个故事才能有用，应该合并
验收标准应该是 QA 无需额外解释就能测试的
错误处理和边界情况应该有各自独立的故事，而不是正常流程故事里的一个要点
如果功能较大（15 个以上故事），建议按史诗或阶段分组
标注任何需要技术预研（在可估算之前需要先进行技术调查）的故事

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.

6d ago First seen · 113 lines · 25 tokens per session scan A b712a9ae6087

Subscribe to this mod's changes

write-stories is a command published in the GitHub repository killvxk/pm-skills-zh (151 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 1,110 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.

Planning Project management

write-stories