This is a Chinese language prompt engineering skill that turns Claude into a methodical interviewer for planning projects. It walks you through decisions one question at a time, branching down a design tree until you've covered all dependencies. The approach is deliberate: it explores your codebase for facts on its own but waits for you to make each decision before moving forward. It won't execute until you confirm mutual understanding. Honestly, the interrogative style might feel slow if you already know what you want, but it's solid for projects where requirements are fuzzy or you need to think through tradeoffs systematically. The 690 installs and clean security audits suggest people are finding it useful for structured planning sessions.

skills.sh installs
4.7K
GitHub stars
5.7K
last updated
Aug 21, 2026

Install

$ npx -y skills add vinvcn/mattpocock-skills-zh-cn --skill grilling --agent claude-code

Installs into .claude/skills of the current project.

Files

持续访谈用户,直到达成共同理解。把这件事映射成一棵 design tree:每个 decision 都分支到挂在它下面的那些 decisions。

按 rounds 逐轮处理这棵树。frontier 是那些 prerequisites 已经敲定的 decisions,也就是你现在就可以问、无需猜测还没听到的答案的那些问题。在一轮里问完整条 frontier:给每个问题编号并附上你的推荐答案。然后等用户回答,再进入下一轮。

每一轮的格式如下:

❓ **Q1** - **<问题标题>**:<问题正文,可能有多段,包括多个选项>

➡️ <你的推荐答案>

---

❓ **Q2** - **<问题标题>**:<问题正文,可能有多段,包括多个选项>

➡️ <你的推荐答案>

每个问题的措辞都要让回答 “yes” 就是接受你的推荐答案。

每一轮用户给出的回答都会重塑这棵树:敲定的 decisions 会把 frontier 向外推,并解锁依赖它们的问题。重新计算 frontier,然后问下一轮。其答案依赖本轮中另一个仍未解决的问题,属于 更晚的 一轮,而不是本轮。

寻找 facts 是你的工作,绝不是用户的。当一个 frontier 问题需要来自 environment(filesystem、tools 等)的 fact 时,派一个使用全新 context window 的 sub-agent 去查,不要问用户任何你自己能查到的东西。不要被它阻塞:一次正在进行的探索是一个尚未敲定的 prerequisite,所以只有它下游的问题才需要等 sub-agent 回报,现在先问 frontier 的其余部分。decisions 属于用户:逐个交给他,并等待。

当 frontier 为空时,会话才算结束:design tree 的每个分支都访问过,没有留下任何被默默假设的东西。在用户确认我们已经达成共同理解之前,不要采取行动。

Sponsors

Details

Repository
github.com/vinvcn/mattpocock-skills-zh-cn
Category
Productivity & Planning
First seen
Jul 14, 2026

More from vinvcn/mattpocock-skills-zh-cn

All 39
1agricidaniel avatarads-budgetagricidaniel/claude-adsPlan and review paid-media budgets, bidding, pacing, marginal return, forecasts, CPA, ROAS, MER, LTV:CAC, constraints, and allocation across supported platforms4.2Kskills.sh installs
2ailabs-393 avatartravel-plannerailabs-393/ai-labs-claude-skillsThis skill should be used whenever users need help planning trips, creating travel itineraries, managing travel budgets, or seeking destination advice. On first4.1Kskills.sh installs
3anthropics avataruser-researchanthropics/knowledge-work-pluginsPlan, conduct, and synthesize user research. Trigger with "user research plan", "interview guide", "usability test", "survey design", "research questions", or w4.1Kskills.sh installs
4coralogix avatarcx-cost-optimizationcoralogix/cx-cliUse this skill when the user asks to "check data usage", "list TCO policies", "reduce Coralogix costs", "optimize observability spend", "lower our logging bill"4Kskills.sh installs
5github avatareval-driven-devgithub/awesome-copilotImprove AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate applica3.9Kskills.sh installs
6everyinc avatarce-doc-revieweveryinc/compound-engineering-pluginReview requirements, plans, or specs with role-specific lenses. Use when the user wants to improve an existing planning document.3.8Kskills.sh installs