prd by github/awesome-copilot
npx skills add https://github.com/github/awesome-copilot --skill prd设计全面、生产级的产品需求文档(PRD),以弥合业务愿景与技术实现之间的差距。此技能适用于现代软件系统,确保需求被明确定义。
在以下情况使用此技能:
在撰写 PRD 的任何内容之前,你必须通过询问用户来填补知识空白。不要假设上下文。
询问以下内容:
综合用户的输入。识别依赖关系和隐藏的复杂性。
使用下面的严格 PRD 架构生成文档。
使用具体、可衡量的标准。避免使用"快速"、"简单"或"直观"。
# 模糊(不好)
- 搜索应该快速并返回相关结果。
- 用户界面必须看起来现代且易于使用。
# 具体(好)
+ 对于 10k 条记录的数据集,搜索必须在 200 毫秒内返回结果。
+ 搜索算法在基准评估中必须达到 >= 85% 的 Precision@10。
+ 用户界面必须遵循 'Vercel/Next.js' 设计系统,并达到 100% 的 Lighthouse 无障碍访问评分。
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
输出时你必须遵循此精确结构:
作为 [用户],我想要 [操作],以便 [获益]。TBD。问题:用户难以在海量存储库中找到特定的文档片段。解决方案:一个提供带来源引用的直接答案的智能搜索系统。成功标准:
codesearch、grep、webfetch。每周安装量
11.6K
代码仓库
GitHub 星标数
26.7K
首次出现
Jan 23, 2026
安全审计
安装于
opencode11.2K
codex11.1K
gemini-cli11.1K
github-copilot11.1K
kimi-cli10.9K
cursor10.9K
Design comprehensive, production-grade Product Requirements Documents (PRDs) that bridge the gap between business vision and technical execution. This skill works for modern software systems, ensuring that requirements are clearly defined.
Use this skill when:
Before writing a single line of the PRD, you MUST interrogate the user to fill knowledge gaps. Do not assume context.
Ask about:
Synthesize the user's input. Identify dependencies and hidden complexities.
Generate the document using the Strict PRD Schema below.
Use concrete, measurable criteria. Avoid "fast", "easy", or "intuitive".
# Vague (BAD)
- The search should be fast and return relevant results.
- The UI must look modern and be easy to use.
# Concrete (GOOD)
+ The search must return results within 200ms for a 10k record dataset.
+ The search algorithm must achieve >= 85% Precision@10 in benchmark evals.
+ The UI must follow the 'Vercel/Next.js' design system and achieve 100% Lighthouse Accessibility score.
You MUST follow this exact structure for the output:
As a [user], I want to [action] so that [benefit].TBD.Problem : Users struggle to find specific documentation snippets in massive repositories. Solution : An intelligent search system that provides direct answers with source citations. Success :
codesearch, grep, webfetch.Weekly Installs
11.6K
Repository
GitHub Stars
26.7K
First Seen
Jan 23, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode11.2K
codex11.1K
gemini-cli11.1K
github-copilot11.1K
kimi-cli10.9K
cursor10.9K
97,600 周安装