to-prd
vinvcn/mattpocock-skills-zh-cn
Convert conversation context into a structured PRD and publish to your project issue tracker.
What is to-prd?
This skill synthesizes your current conversation context and codebase understanding into a Product Requirements Document (PRD) without user interviews. It explores the repository, identifies testing seams, and publishes the PRD to your issue tracker with appropriate triage labels.
- Analyzes current conversation context and codebase state to generate comprehensive PRDs
- Explores repository structure and applies project domain glossary and ADRs
- Identifies optimal testing seams, preferring existing ones over new additions
- Drafts complete user stories covering all feature aspects
- Documents implementation decisions including modules, interfaces, and architectural choices
- Specifies testing decisions and prior art references
How to install to-prd
npx skills add https://github.com/vinvcn/mattpocock-skills-zh-cn --skill to-prd- Issue tracker and triage label vocabulary must be configured (run /setup-matt-pocock-skills if not already set up)
- Access to project repository for codebase exploration
- Existing conversation context about the feature or problem
How to use to-prd
- 1.Explore the repository to understand current codebase state if not already done
- 2.Review the conversation context and identify key requirements
- 3.Confirm the proposed testing seams align with project expectations
- 4.The skill generates a PRD using the standard template with Problem Statement, Solution, User Stories, Implementation Decisions, Testing Decisions, Out of Scope, and Further Notes sections
- 5.The PRD is automatically published to your issue tracker with the ready-for-agent triage label
Use cases
- Convert a feature discussion into a formal PRD ready for development
- Document architectural decisions and testing strategy for a new feature
- Generate comprehensive user stories from context without conducting user interviews
- Create issue tracker entries that capture both problem statement and solution approach
- Establish testing seams and implementation boundaries before coding begins
- Product managers documenting feature requirements
- Development teams converting discussions into formal specifications
- Architects defining implementation decisions and testing strategies
- Teams using issue tracker-based project management
to-prd FAQ
No. This skill synthesizes only what you already know from conversation context and codebase understanding. It does not conduct user interviews.
Run /setup-matt-pocock-skills to configure your issue tracker and triage label vocabulary before using this skill.
It prioritizes using existing seams, but can propose new ones at the highest level if necessary. You should confirm these seams align with expectations before publication.
The PRD is posted to your project issue tracker with the ready-for-agent label applied, ready for development work to begin.
Generally avoid specific file paths or code snippets as they become outdated quickly. Only include prototype snippets if they precisely encode a decision (like state machines or schemas) and keep them brief.
Full instructions (SKILL.md)
Source of truth, from vinvcn/mattpocock-skills-zh-cn.
name: to-prd description: 将当前 conversation context 转成 PRD 并发布到项目 issue tracker。Use when user wants to create a PRD from the current context.
这个 skill 使用当前 conversation context 和 codebase understanding 产出 PRD。不要访谈用户，只综合你已经知道的内容。
Issue tracker 和 triage label vocabulary 应该已经提供给你；如果没有，运行 /setup-matt-pocock-skills。
Process
-
如果还没有探索 repo，先探索它以理解 codebase 当前状态。在 PRD 中始终使用项目 domain glossary vocabulary，并遵守相关 ADRs。
-
草拟你准备在哪些 seams 上测试这个 feature。优先使用现有 seams，而不是新增 seams。使用尽可能高层的 seam。如果确实需要新增 seams，尽可能在最高层提出。
与用户确认这些 seams 是否符合预期。
- 使用下面模板写 PRD，并发布到项目 issue tracker。应用
ready-for-agenttriage label；不需要额外 triage。
Problem Statement
用户正在面对的问题，从用户视角描述。
Solution
问题的解决方案，从用户视角描述。
User Stories
一份很长的编号 user stories 列表。每条 user story 使用以下格式：
- As an <actor>, I want a <feature>, so that <benefit>
这份 user stories 列表应该非常完整，覆盖 feature 的所有方面。
Implementation Decisions
已作出的 implementation decisions 列表。可以包括：
- 将 build/modify 的 modules
- 将 modify 的 module interfaces
- 来自 developer 的技术澄清
- Architectural decisions
- Schema changes
- API contracts
- Specific interactions
不要包含具体 file paths 或 code snippets。它们可能很快过时。
例外：如果 prototype 产出的 snippet 比 prose 更精确地编码了某个决策（state machine、reducer、schema、type shape），可以内联到相关 decision 中，并简短说明它来自 prototype。只保留决策密集部分，不要放完整 working demo。
Testing Decisions
已作出的 testing decisions 列表。包括：
- 什么是好测试的描述（只测试 external behavior，不测试 implementation details）
- 哪些 modules 会被测试
- 测试的 prior art（即 codebase 中类似类型的 tests）
Out of Scope
本 PRD 范围外事项的描述。
Further Notes
关于 feature 的其他 notes。
</prd-template>Related skills
More from vinvcn/mattpocock-skills-zh-cn and the wider catalog.
triage
Triage issues through state machines with category and state roles for bug and enhancement management.
ubiquitous-language
从当前 conversation 提取 DDD-style ubiquitous language glossary，标记 ambiguities 并提出 canonical terms。保存到 UBIQUITOUS_LANGUAGE.md。Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".
write-a-skill
Create well-structured agent skills with progressive disclosure and bundled resources.
writing-beats
Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.
writing-fragments
Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate", or "raw material" for writing.
writing-shape
Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.