grill-me
Interactive assumption-surfacing Q&A that stress-tests a plan through relentless questioning until every decision is resolved. Use when user wants to challenge a plan, validate decisions from conversation/context, or mentions "grill me". For doc-grounded variant, use grill-with-docs.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 292
- Forks
- 23
01 前言 Front Matter
- name
- grill-me
- model
- sonnet
- effort
- standard
- description
- Interactive assumption-surfacing Q&A that stress-tests a plan through relentless questioning until every decision is resolved. Use when user wants to challenge a plan, validate decisions from conversation/context, or mentions "grill me". For doc-grounded variant, use grill-with-docs.
02 资源文件 1
- 参考文档REFERENCE.md2.3 KB
03 SKILL.md 正文
Grill Me
Use this vs grill-with-docs:
grill-mesurfaces assumptions from the conversation and context alone — no documentation fetching. Usegrill-with-docs(the doc-grounded variant) when the plan relies on a specific library or external API and every challenge must cite a real doc URL.
Two modes. Default is Design. Switch to Docs by saying "grill me with docs" or when the plan relies on a specific library or external API.
HARD GATE — Do NOT accept a design until every hard decision has been stress-tested. "Seems right" is not a decision. Grilling must identify and resolve tensions before build begins.
Design mode (default)
Interview relentlessly about every aspect of this plan until reaching shared understanding. Walk each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer. Ask one question at a time.
If a question can be answered by exploring the codebase, explore it instead.
Facts vs. Decisions Boundary
Distinguish between facts and decisions:
- Facts — things discoverable by exploring the codebase, reading docs, or checking APIs. Do not ask the user to confirm facts; find them yourself.
- Decisions — choices that require user input (trade-offs, preferences, priorities). Always present options and ask the user to choose.
Never "grill yourself" — if the answer is in the code, go find it. Only ask questions where the user's judgment is needed.
Docs mode
Ground every challenge in real documentation — no assumption about a library's behavior goes unchecked. See REFERENCE.md for the full process.
Short form:
- List every external library, third-party API, and framework behavior relied upon.
- Fetch the actual docs for each (
WebFetchthe official API reference). - Challenge each plan assumption against the real docs: correct method signature? right version? deprecated?
- Report confirmed ✓, corrected ✗ (with the real behavior), and uncertain →
spike-prototype. - Update the plan for each confirmed discrepancy.
Confirmation Gate
HARD GATE — Do NOT enact the plan or generate specifications until the user explicitly confirms shared understanding. Wait for explicit approval (e.g., "looks good", "confirmed", "proceed") before transitioning to any implementation, spec-writing, or task-slicing step.
04 同仓库更多 Skills
skill-verify-fail-open-fixture
Negative-path fixture for run-skill-verify.sh — must never PASS.
negative-path
暂无简介
write-document
Write, organize, and sync high-integrity technical documents using the BMAD methodology. Ensures every document is Bold, Minimal, Actionable, and Durable. Use when creating architectural docs, technical guides, or organizing the specs/ directory.
wire-observability
Add structured JSON logging, observability commands, and idempotent setup scripts to a project. Use when a project needs production-readiness instrumentation, when user wants structured logging, or as a production-readiness gate at any phase of development.
wire-ci
CI pipeline setup with bundled, forge-neutral templates and local validation. Detects the forge from the git remote, generates workflows for supported forges, and skips honestly for the rest. The CI equivalent of wire-observability.
visual-dashboard
Start a browser-based dashboard that visualizes architecture, implementation plans, and project status. Persists artifacts in .bigpowers/dashboard/. Reads specs/state.yaml, release-plan.yaml, epics, and planning-status via HTTP API or opencode panel.