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 chaunsin/agent-skills --skill prdgit clone --depth 1 https://github.com/chaunsin/agent-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/chaunsin/agent-skills/prd)<a href="https://agentmods.dev/skills/chaunsin/agent-skills/prd"><img src="https://agentmods.dev/badge/skills/chaunsin/agent-skills/prd/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/chaunsin/agent-skills/prd"><img src="https://agentmods.dev/badge/skills/chaunsin/agent-skills/prd.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 | $0.00033 | $0.01890 |
| Opus 5.5 | $0.00013 | $0.00756 |
| Sonnet 5.5 | $0.00007 | $0.00378 |
| Haiku 4.5 | $0.00003 | $0.00189 |
Grade A, and why
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 24d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD 生成
作为一个资深的产品经理，从用户视角、使用习惯，根据用户想法生成相应的prd产品文档。
使用场景
- 需求、分析、设计、PRD文档编写。
- 启动新产品线，增加新功能，功能修改，功能删除、下线等。
- 促销活动，节日活动，用户增长。
- 将模糊的想法、答案转化为具体的产品规范。
- 在开始编码实施之前，方案确定。
不应该使用场景
- 修改代码注释。
- 更改项目配置内容。
- 非产品需求内容。
核心原则
- 产品定位: 明确产品定位受众用户，根据实际业务、领域场景而设计，进而决策出领域规则，行业规范，具体功能，交互逻辑，样式风格等。例如: 是client端、backend端、web、app、cms、支付、电商、web3、AI、ERP等等
- 产品特色: 产品鲜明功能明确，具有核心竞争力，相比其他竞品优势，解决了哪些痛点。
- 有理有据: 设计要有理有据，避免空穴来风，不能单一独立。
- 概念统一: 项目描述、用词、术语、概念要一致，不要创造词，以及新的概念，增加理解认知复杂度。
- 逻辑闭环: 数据流转、生命周期完整，逻辑要闭环。
- 直觉习惯: 设计要符合常规逻辑与交互，不能反人类，走极端，增加心智与交互体验。
- 避免重复: 功能不能出现重复，目前项目是否存在类似功能， 如有是否需要在原有基础上调整修改。
- 风格一致: 系列产品血脉要一致，UI、样式、风格、交互、习惯要保证一脉相承统一。
- 了解历史与背景: 了解产品历史与背景，当功能升级、修改、下线、迁移是否造成以下影响
- 用户流失、日活降低、付费减少、积怨等负面情绪？
- 业务生命周期是否完整，每个阶段状态是否有相应的逻辑处理，逻辑是否闭环？
- 新功能与老业务逻辑是否冲突？
- 新功能对代码数据层面是否造成缺失、冲突、重复等潜在问题？
- 用户诉求与反馈: 在合理且保证核心价值利益范围下，从用户内心想法角度出发设计产品，对用户提出的一些建议、诉求，通过合理客观评估后做出相应的设计与调整，寻找用户与平台互利的平衡点。例如: 抽奖系统大多数人反馈抽不到奖，作为运营、老板来说不能亏损，要盈利，因此只能让部分人抽到奖，控制在合理的概率产出，而不是让所有人都中奖。
步骤一:收集信息(可选)
结合工程上下文，对已有的功能实现，或PRD文档内容与规则(包含潜在规则、默认规则、行业规则)，补充到新需求文档中。收集方式如下:
- 用户提供得prompt描述、信息载体、文档、图片、链接地址、可访问资源等。
- 已存在的PRD文档或关联性大的内容。
- 知识库，docs/、plan/、 spec/、wiki/、MCP、memory检索
- 参考当前已有的项目实现，优先读取CLAUDE.md、AGENTS.md、DESIGN.md、README.md等文档内容，或分析现有代码仓库实现。
- 联网搜索，当收集到的信息不足、了解最新技术方案与技术调研利用Context7、 WebSearch/WebFetch 等工具集思广义。
对收集得信息进行分析并归纳与总结，找出模糊点以矛盾点。
步骤二:澄清需求
注: 仅当产品需求决策存在歧义时才提出问题，一次只提一个问题。
根据收集到的信息，找出需求模糊点，矛盾点，需澄清的问题。提问格式以及参考内容如下:
**Q1. 此功能的主要目标是什么**
A. 提升用户上手体验
B. 提高用户留存率
C. 减轻技术支持负担
D. 其他：<请具体说明>
**Q2. 目标用户是谁？**
A. 仅新用户(推荐)
B. 仅现有用户
C. 所有用户
D. 仅管理员用户
**Q3. 其范围是怎样的？**
A. 最小可行版本(推荐)
B. 全功能实现
C. 仅后端/API
D. 仅用户界面
步骤三:文档格式
根据 reference/template.md 模板文件创建prd文档。
步骤四:保存
引导用户保存文档
**SPEC 保存在哪里?**
A. docs/prd/spec-<number>-<feature-name>.md (alongside PRD, 推荐)
B. docs/prd-<feature-name>.md
C. 自定以目录位置或说明
步骤五:回顾与迭代
- 是否存在需要澄清的模糊点
- 文档内容是否完整，是否包含或缺少相应章节内容。
What ships with it
1 file 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.
- 24d ago Changed · +1 lines 4985996e4b9a
- 1mo ago First seen · 135 lines · 33 tokens per session scan A a1eb8bf27e12
prd is a skill published in the GitHub repository chaunsin/agent-skills (2 stars, last pushed 25d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,890 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-11.
Other skills, from other repositories
yida-agent-center
An agent-management tool for Yida, a business workflow platform. It manages temporary substitutes who handle or submit approval processes for current employees or departed employees.
yida-voc
A template for organising user feedback (VOC, or voice of the customer) about problems, requests, and performance issues in the Yida platform.
product-planner
Plan a product from idea to sprint tasks in one run: idea-validator, prd-generator, tad-generator, tasks-generator, resuming from existing files. Don't use for one document alone (PRD, TAD, tasks) or only validating an idea.
webflow-mcp:review-comments
Review open comment threads on a Webflow site and triage each one.
yida-prd
A planning guide that turns confirmed user needs into a product requirements document, or PRD—a written description of what an application should contain and do.
yida-flow-node-config
A reference guide for configuring nodes in workflow and integration automation. It covers triggers, human tasks, routing, data changes, notifications, and extension steps without creating or publishing the workflow.