メニュー
Interview user about a plan or design until decisions satisfy stated goal. Use when user wants to stress-test a plan, explore real options, get grilled on design, or mentions "grill me".
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Interview user, then set up agent-friendly repository guidance and tooling: sane .gitignore, repo-specific AGENTS.md, and optional mise.toml with runtime and check tasks. Use when user wants to start a new repo, prepare repo automation, create AGENTS.md guidance, or set up repo tooling from requirements.
Analyze Auto Guardian bash audit logs and propose safe deterministic allow/block rule improvements. Use when reducing guardian LLM calls or reviewing command approval patterns.
Severe git-status-driven review of current changes for maintainability, architecture, and AI-slop risk. Use for ruthless review, nuclear review, pre-merge quality gate, or when local changes may deserve broader refactoring instead of small patch acceptance.
Design UIs in Pencil (.pen files) and generate production code from them. Use when working with .pen files, designing screens or components in Pencil, or generating code from Pencil designs. Triggers on tasks involving Pencil, .pen files, design-to-code workflows, or UI design with the Pencil MCP tools.
Compress any skill to minimal tokens — rewrites SKILL.md, all references/, and scripts/ comments. Strips verbose prose, filler, redundancy while preserving technical accuracy and functionality. Use when user says "caveman-ify this skill", "compress skill", "shrink skill", or invokes /caveman-ify.'
Create standalone HTML artifacts for plans, prototypes, explainers, code reviews, reports, and custom editing interfaces. Use when the user asks for an HTML file/artifact, visual plan/spec, interactive prototype, explainer page, PR/code review artifact, report, or throwaway editor.
| name | grill-me |
| description | Interview user about a plan or design until decisions satisfy stated goal. Use when user wants to stress-test a plan, explore real options, get grilled on design, or mentions "grill me". |
Interview me about this plan until we reach shared understanding for stated interview goal. Walk down relevant branches of design tree, resolving dependencies between decisions one-by-one. For each question, present real viable options before any recommendation.
Before first interview question, clarify with user what end goal of interview session is. Goal defines what user and agent are trying to come together on, and acts as exit condition so interview does not sprawl into every possible edge case.
Then copy templates/decisions.md to .working/interviews/<name>/decisions.md. Use concise kebab-case <name> from plan. Replace top heading and goal text with clarified goal. Treat this file as interview source of truth.
Ask the questions one at a time.
If a question can be answered by exploring the codebase, explore the codebase instead.
For each question:
.working/interviews/<name>/decisions.md with decisions, changed assumptions, and still-open questions..working/interviews/<name>/decisions.md under Open Questions so one-at-a-time flow does not lose them.If user agrees to deeper analysis in new chat, read references/handoff.md and create a handoff document from current discussion. Do not read references/handoff.md unless handoff is relevant.