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.
npx skills add CookiesHaha/ash-claude-skills --skill lark-workflow-prd-to-userstorygit clone --depth 1 https://github.com/CookiesHaha/ash-claude-skillsWrote 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.
[](https://agentmods.dev/skills/cookieshaha/ash-claude-skills/lark-workflow-prd-to-userstory)<a href="https://agentmods.dev/skills/cookieshaha/ash-claude-skills/lark-workflow-prd-to-userstory"><img src="https://agentmods.dev/badge/skills/cookieshaha/ash-claude-skills/lark-workflow-prd-to-userstory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cookieshaha/ash-claude-skills/lark-workflow-prd-to-userstory"><img src="https://agentmods.dev/badge/skills/cookieshaha/ash-claude-skills/lark-workflow-prd-to-userstory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00103 | $0.05019 |
| Opus 5 | $0.00051 | $0.02509 |
| Sonnet 5 | $0.00021 | $0.01004 |
| Haiku 4.5 | $0.00010 | $0.00502 |
Grade A, and why
lark-workflow-prd-to-userstory 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD → User Story → 需求矩阵 → 飞书项目 工作流
CRITICAL — 开始前 MUST 用 Read 工具读取以下文件:
references/userstoryrule.md— User Story 通用书写规则(INVEST、P0、格式约束、跨项目复用)references/template-mapping.md— 字段/角色/模板映射的 通用契约 + 项目实例../lark-shared/SKILL.md— lark-cli 认证与权限处理
PRD 三件套定位
write-a-prd ────► prd-sync ────► [本 skill: prd-to-userstory]
(创建) (同步) (拆 Story + 同步到 Base / 飞书项目)
本 skill 是「需求落地」环节,独立可用:
- 上游可以是 write-a-prd + prd-sync 串联产出(自带 [HANDOFF] 块和 frontmatter),也可以是任何符合「§5 功能清单」结构的 PRD(手写/历史 PRD)
- 通过
template-mapping.md的「项目实例」段落注入差异,主流程不变
本 skill 与具体产品线(PST / CPQ / WLS / 其他)解耦。
适用场景
- "把 PRD 同步到需求矩阵和飞书项目"
- "从 PRD 的功能清单生成 user story"
- "按版本批量创建需求"
- "对齐 {项目} 需求矩阵 v{版本} 与飞书项目 {项目}-{版本}"
输入
| 参数 | 示例 | 说明 |
|---|---|---|
| 项目代号 | PST / CPQ / WLS 等 |
决定加载 template-mapping.md 中的哪个项目实例。可从 PRD frontmatter.project 读取;都没有时用 AskUserQuestion |
| PRD 版本号 | 26.5.1.0 |
飞书项目对应版本工作项需提前建好,名为 {项目}-{版本号}。可从 PRD frontmatter.target_version 读取 |
| PRD 来源 | 本地目录 prd/2026/5/ 或飞书 wiki URL |
二选一;本地优先。若前置 skill 输出了 [HANDOFF],自动读取 local_path |
如上述信息从 [HANDOFF] / frontmatter 都拿不到,用 AskUserQuestion 询问,不要猜。
前置条件
# 飞书 Base + 文档(user 身份)
lark-cli auth login --domain bitable,docs,drive
# 飞书项目 MCP 已配置(mcp__FeishuProjectMcp__*)
# 飞书云文档 MCP 已配置(mcp__feishu__*,仅在跨 wiki 读取 PRD 时使用)
另需在 references/template-mapping.md 中提前配好目标项目的实例(首次跑某个项目时,约 5 分钟一次性维护工作)。
工作流
{项目代号, PRD 版本号, PRD 来源}
│
▼
Step 0 加载项目实例配置(template-mapping.md 中的 PROJECTS[{项目}])
│
▼
Step 0.5 从 [HANDOFF] / frontmatter 自动填充缺失参数
│
▼
Step 1 扫描 PRD 来源 ──► 让用户确认本次同步的 PRD 文件
│
▼
Step 2 Read PRD ──► 提取 §5 功能清单 + 引用的 §4 需求详细设计章节
├─ 按 mapping.title_prefix_rules 自动判别标题前缀
▼
Step 3 生成 P0 User Story 草稿(依据 references/userstoryrule.md)
├─ 父子去重:识别覆盖关系,AskUserQuestion 让用户确认合并策略
├─ 输出标准化 checkpoint 表,用户确认后才进入 Step 4
▼
Step 4 写入需求矩阵 Base 表(mapping.base.*)
├─ +record-search 检查同名记录避免重复
├─ +record-create 批量创建(字段名按 mapping.base.fields 映射)
▼
Step 5 同步到飞书项目(mcp__FeishuProjectMcp__)
├─ 5a 验证版本工作项存在
├─ 5b 批量 create_workitem
├─ 5c 设置当前用户为产品经理(必须,否则 5d 无权写)
├─ 5d 设置规划版本字段
├─ 5e 勾选节点开关
▼
Step 6 双向对齐核对 ──► 输出最终对照表
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 405 lines · 103 tokens per session scan A c27b41482abd
lark-workflow-prd-to-userstory is a skill published in the GitHub repository CookiesHaha/ash-claude-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 5,019 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
after-action-report
Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event.…
stakeholder-communication
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…
mass-ulw
Drives dependency-ordered child work through the native workflow tool, one run per phase with retry/amend/send recovery. Use when the user asks for mass-ulw, a DAG of tasks, or fan-out work where some tasks must wait on others.
beta-program-management
Running closed and open betas that produce real signal. Beta participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional…
okr-design
OKR design as actually shipped, not as conference-talk theory. Outcome statements that drive decisions, key results that measure the right thing, scoring discipline, mid-quarter recalibration, and the difference between sandbagged OKRs (always 100%) and aspirational OKRs (always 30%) and stretch OKRs (genuine ambition…
roadmap-planning
Build a multi-quarter roadmap from a backlog of ideas, requests, and ongoing initiatives. Use this skill when planning the next quarter, sequencing dependent work, balancing build vs improve vs maintain, or making the case for what NOT to do. Triggers on roadmap, quarterly planning, what should we build next…