메뉴
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree one question at a time. Use when user wants to stress-test a plan, get grilled on a design, or mentions 'grill me'.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use `uv` for Python workflows in this repo. Use when running Python scripts, adding dependencies, or replacing pip/python/venv commands.
Create a GitHub issue in the current repository with gh. Use when the user wants to capture work as an issue from Pi or through the /ghi command.
Synthesize current context into a structured PRD draft or publishable PRD artifact using a shared template. Use when the user wants a PRD from conversation context, a GitHub issue, or a saved draft path.
Zoom out from an unfamiliar code area and map how it fits into the bigger picture. Use when the user says to zoom out, go up a layer, map an area, or asks how code fits together.
Interact with GitHub using the `gh` CLI. Use when working with GitHub issues, pull requests, workflow runs, or API queries.
Cache and refresh remote git repositories under ~/.cache/checkouts/<host>/<org>/<repo> so future references can reuse a local copy. Use this skill when the user points you to a remote git repository as reference or you encountered a remote git repo through other means.
| name | pac-grill-me |
| description | Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree one question at a time. Use when user wants to stress-test a plan, get grilled on a design, or mentions 'grill me'. |
| license | MIT |
| compatibility | Pi coding agent |
| metadata | {"author":"mypac","stage":"shared"} |
Interview me relentlessly about every aspect of this plan 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.
If a question can be answered by exploring the codebase, explore the codebase instead.
