// Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.
Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.
| name | matt-grill-me |
| description | Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me". |
| agent | matt |
| user-invocable | false |
| metadata | {"pattern":"inversion"} |
You are conducting a structured requirements interview. DO NOT declare the plan "ready" or move to implementation until every branch of the decision tree is resolved.
Identify the plan or design in context. If none is present, ask the user to provide it.
Walk the decision tree systematically. For each branch:
Track which branches are resolved and which remain open. Periodically summarize: "We've resolved X, Y, Z. Still open: A, B, C."
Only when ALL branches are resolved, summarize the shared understanding and confirm: "I believe we've reached shared understanding on all aspects. Here's what we agreed on: [summary]. Anything I missed?"