菜单
Use when the user wants a plan, decision, or idea sharpened through questioning before acting on it, or when another skill needs the interview primitive. Triggers on: "grill me", "grill this plan", "stress-test this design with questions", "interview me about this".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when the user wants a high-stakes decision debated by independent perspectives and synthesized into a verdict — five advisors (Contrarian, First Principles, Expansionist, Outsider, Executor) answer independently, peer-review anonymously, then a chairman synthesizes. Triggers on: "council this", "convene the council", "run a council on", "rerun the council", "I want the council to debate this", "five independent perspectives", "have advisors weigh in and peer-review each other".
Use when the user wants a plan, proposal, or conclusion adversarially challenged in one pass — auto-picks the strongest critique mode (socratic, dialectic, pre-mortem, red-team, evidence audit) and delivers the 3–5 strongest challenges plus a synthesis. Triggers on: "court-jester this", "poke holes in this plan", "red-team this design", "run a pre-mortem", "argue the other side", "does the evidence actually support this conclusion", "challenge this proposal".
Use when interacting with a Gitea instance or its `tea` CLI — listing or filing issues, managing pull requests, labels, milestones, releases, repos, or calling the Gitea REST API. Triggers on: "tea" CLI commands, "Gitea", "tea issues", "tea pr", "tea api", blocked-by/issue dependencies, "file this on the tracker", or a repo whose remote points at a Gitea host. Excludes GitHub's `gh` CLI.
Use when documentation must stay truthful as software changes — writing or revising a spec, ADR, runbook, or API/config reference, splitting user-facing docs by purpose, or reconciling documentation drift. Triggers on: "write a spec", "ADR", "runbook", "which docs must change", "documentation drift", "missing acceptance criteria", "spec interview", "update the API reference".
Use when the project's domain model is being changed — terms pinned down, design decisions landing, vocabulary conflicting — or when another skill needs to maintain the domain model while decisions land. Triggers on: "pin down the terminology", "ubiquitous language", "record this decision", "add it to the glossary", "domain model".
Interactive QA session: the user reports bugs or issues conversationally, the agent clarifies, explores the codebase in the background for domain language, and files durable, user-focused issues on the project tracker. Triggers on: "QA session", "let's do QA", "file an issue for this", "report a bug", "log these bugs", "bug triage", or when the user describes problems they want captured as tracker issues rather than fixed immediately.
| name | grilling |
| description | Use when the user wants a plan, decision, or idea sharpened through questioning before acting on it, or when another skill needs the interview primitive. Triggers on: "grill me", "grill this plan", "stress-test this design with questions", "interview me about this". |
| license | MIT (adapted from mattpocock/skills) |
Interview me relentlessly about every aspect of this — a plan, a decision, an idea — until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
Ask the questions one at a time, waiting for feedback on each question before continuing. Asking multiple questions at once is bewildering.
If a fact can be found by exploring the environment (filesystem, tools, etc.), look it up rather than asking me — dispatch a sub-agent for the lookup so the interview doesn't block on it. The decisions, though, are mine — put each one to me and wait for my answer.
Do not act on it until I confirm we have reached a shared understanding.
