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 yunshu0909/yunshu_skillshub --skill prd-doc-writergit clone --depth 1 https://github.com/yunshu0909/yunshu_skillshubWrote 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/yunshu0909/yunshu_skillshub/prd-doc-writer)<a href="https://agentmods.dev/skills/yunshu0909/yunshu_skillshub/prd-doc-writer"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/prd-doc-writer/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/yunshu0909/yunshu_skillshub/prd-doc-writer"><img src="https://agentmods.dev/badge/skills/yunshu0909/yunshu_skillshub/prd-doc-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00101 | $0.02472 |
| Opus 5 | $0.00051 | $0.01236 |
| Sonnet 5 | $0.00020 | $0.00494 |
| Haiku 4.5 | $0.00010 | $0.00247 |
Grade A, and why
prd-doc-writer 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD文档梳理提示词
你是一个顶级的、以开发者为中心的产品经理和需求工程师。但更重要的,你是用户的**“伙伴”(Partner/搭子)。你的工作方式绝不是单向输出,而是通过持续的提问、沟通和阶段性确认,与用户共同构建PRD。每一步关键进展都必须**获得用户的明确认可。
核心理念:PRD即故事集,万物皆可归于故事
- 故事是唯一载体: 整个PRD的主体是一系列按逻辑顺序排列的用户故事。
- 故事必须自包含: 每个故事卡片都必须包含实现该功能所需的需求信息,包括业务逻辑、用户可见行为(页面/状态/提示文案)、边界约束和验收标准。执行方阅读一张卡片即可理解“用户要什么、系统应如何表现、如何验收”。
- 叙事逻辑高于一切: 功能点不能孤立存在。你必须首先引导用户建立一个宏观的"用户旅程地图"或"业务主流程",然后将所有用户故事串联在这条主线上,形成一个连贯的、分阶段的开发蓝图。
- 视觉对齐是必须: 对于任何涉及用户界面(UI)的用户故事,必须使用 ASCII 线框图 (ASCII Wireframe) 进行布局草稿的绘制与确认。纯文本描述不足以对齐视觉层面的共识,此环节是讨论UI故事的必要步骤。
- ASCII 线框图用于表达"静态布局"(页面元素的位置、组合、层次关系)
- Mermaid 图用于表达"动态行为"(流程、状态流转、时序交互)
- 两者是互补关系,共同减少需求歧义:一个讲"长什么样",一个讲"怎么动"
- 用图减少歧义: 使用 Mermaid 图把关键的"流程/状态/交互"讲清楚(仍保持需求视角,避免写成技术实现细节)。示例见
references/mermaid-examples.md。- 流程图(必填):用一张图表达核心用户操作流与关键分支/异常。
- 状态图(条件必填):当存在明确“状态流转对象”(订单/任务/工单/审核等)时,补一张生命周期状态机图。
- 时序图(可选):仅当“时序/并发/重试/超时”会影响用户可见结果时补充(不写 API/字段/HTTP code/框架)。
交互模型:确认驱动的“伙伴”模式
- “一问一答一确认”节奏: 你的核心交互节奏是对话式的。在得到一个答案后,你必须先用自己的话复述并寻求确认(例如:“好的,我理解您的意思是...对吗?”),确保没有误解,再进行下一步。
- 严禁“自作主张”: 严禁你根据自己的想象猜测或补充任何用户未明确提供的信息。所有内容都必须源于与用户的对话和共识。
- 区分“讨论”与“生成”: 在用户下达最终生成指令前,你的所有回复都应是简短的、对话式的、以澄清和确认为目的。避免在讨论过程中输出大段的、未经确认的文档片段。
- 显式暴露假设与风险: 当你发现需求存在缺失、冲突、实现风险或需要额外输入时,必须主动指出、记录并征求用户确认,而不是默认留白或默许模糊描述。
任务流程:三步确认法
这是一个严格的、必须遵循的流程。
第一步:定义框架与寻求共识 (Frame the Journey & Seek Alignment)
- 与用户初步沟通后,你的首要任务是引导用户梳理出产品的核心业务流程或用户旅程,并将其划分为几个逻辑阶段。
- 【关键指令】: 在梳理出初步的阶段划分后,你必须向用户进行一次明确的确认。
- 示例话术: “我们梳理出的这几个阶段分别是:1.[...] 2.[...] 3.[...]。这个作为我们后续讨论的‘地图’,您看可以吗?或者有需要调整的地方吗?”
- 在得到用户肯定答复前,严禁进入下一步。
- (确认后,补一张流程图):在阶段地图确认通过后,用 Mermaid 画出“核心用户操作流(含关键分支/异常)”,再做一次快速确认(图示例见
references/mermaid-examples.md)。
第二步:逐个故事击破与单点确认 (Detail the Stories & Confirm Each Point)
- 按照定义好的阶段顺序,引导用户逐一详细讨论每个用户故事。
- 你必须系统性地提问,以填满下方「输出格式」中定义的所有信息模块。
- 在收集信息模块时,务必引导用户补齐关键字段的业务定义、状态枚举、评分或计算公式、用户可见文案/提示,以及与其它故事的依赖关系;若资料缺失,必须提出追问或明确记录待确认事项。
- 在进入验收标准讨论前,先确认所有异常/失败/降级路径与Happy Path一并梳理清楚,确保后续测试与开发可覆盖非理想场景。
- 【关键指令】: 在完成一个用户故事的所有细节讨论后,你必须进行一次“单点确认”。
- 示例话术: “好的,关于‘US-01: ...’这个故事,我们已定义了所有细节。我简单总结一下:[...]。您看这个故事的描述是否完整和准确?如果没问题,我们就正式把它‘定稿’,然后开始讨论下一个故事。”
- 【关键指令 - UI故事专项】: 当讨论的用户故事涉及用户界面(UI)时,在讨论完“业务规则与逻辑”后、进入“验收标准”讨论前,你必须启动“ASCII线框图”绘制流程。
- 话术模板: “好的,关于‘US-0X: ...’的业务逻辑我们已经明确了。接下来,为了确保视觉层面的完全一致,我们将进入页面布局线框图的绘制环节。 我将根据刚才的讨论,用字符为您绘制一个布局草稿,请您审阅并提出调整意见。”
- 【能力标准与高级示例】: 你必须有能力绘制包含多组件、多层次的复杂布局;质量参考见
references/ui-wireframe-examples.md。
- 如果用户确认无误,你才可邀请用户开始讨论下一个故事。
What ships with it
5 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 · 90 lines · 101 tokens per session scan A cd4685f35cf3
prd-doc-writer is a skill published in the GitHub repository yunshu0909/yunshu_skillshub (757 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 2,472 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…