pr-faq
Skill2 starsChanged 5 months agoMITView on GitHub
PR/FAQ模板——Amazon Working Backwards文档。模板生成SKILL,可独立使用。
In this repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- code-reviewSkill
- design-reviewSkill
- main-workflowSkill
- okrSkill
- release-checklistSkill
- release-reviewSkill
- requirement-clarificationSkill
- requirement-reviewSkill
- retro-meetingSkill
- retro-reviewSkill
- six-pagerSkill
- software-project-governanceSkill
- stage-architectureSkill
- stage-cicdSkill
- stage-developmentSkill
- stage-infraSkill
- stage-initiationSkill
- stage-maintenanceSkill
- stage-operationsSkill
- stage-releaseSkill
- stage-researchSkill
- stage-selectionSkill
- stage-testingSkill
- tech-reviewSkill
- test-reviewSkill
The file
Files
PR/FAQ 模板 — Amazon Working Backwards
本模板用于立项阶段,在写任何代码之前先定义用户价值。基于 Amazon Working Backwards (PR/FAQ) 实践。
使用时机
立项阶段,在定义技术方案之前。触发信号:用户说"我们要做一个..."。
Press Release(新闻稿)
用 1 页纸从用户视角描述项目成功后的样子。不用技术语言,用用户语言。假设项目已完成,你在向世界宣布它。
标题
[产品/功能名称] — [一句话价值主张]
副标题
目标用户是谁,解决什么问题,为什么现在做
问题陈述
当前用户面临的问题是:
1. [痛点 1 — 具体场景]
2. [痛点 2 — 具体场景]
3. [痛点 3 — 具体场景]解决方案
[产品名称] 让用户能够 [核心能力]。
与现有方案不同,它 [差异化优势]。用户证言
"[目标用户] 说:'在使用 [产品名称] 之前,我 [旧的痛苦]。现在,我 [新的体验]。'"如何开始
用户只需 [最简路径,≤3 步] 即可开始使用。FAQ(常见问题)
外部 FAQ(用户会问什么)
| # | 问题 | 回答 |
| 1 | 这个产品和 [竞品 X] 有什么区别? | [差异化回答] |
| 2 | 为什么不用 [替代方案 Y]? | [为什么不选] |
| 3 | 它需要什么前置条件? | [环境/技能/权限要求] |
| 4 | 数据安全吗? | [安全/隐私措施] |
| 5 | 费用是多少? | [定价/免费说明] |
内部 FAQ(团队会担心什么)
| # | 问题 | 回答 |
| 1 | 技术上最大的风险是什么? | [技术风险 + 缓解] |
| 2 | 需要多少资源? | [人力/时间/基础设施] |
| 3 | 如果失败会怎样? | [失败场景 + 回滚方案] |
| 4 | 为什么现在做而不是以后? | [时机论证] |
| 5 | 这个决定可逆吗? | [可逆性标注: 可逆/不可逆 + 原因] |
质量标准
- Press Release 用用户语言,非技术语言。读给目标用户听,他们能理解吗?
- 外部 FAQ ≥ 3 条,内部 FAQ ≥ 3 条
- 至少 1 条"为什么用户不用竞品/替代方案"的清晰论证
- PR/FAQ 中承诺的用户价值在测试/运营阶段可逐条验证
- 与技术方案分离——先定义"用户得到什么",再定义"怎么做"
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

