跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
设计与 UI

grill

Relentless one-question-at-a-time interrogation that drives every unresolved decision out of a plan, design, or fuzzy idea BEFORE prompt-transform reformats it and any code or formal plan is written. USER-INVOKED ONLY — triggers when the user types /grill, /grill <topic>, says "grill me", "grill this plan/design", "stress-test this", "interrogate me on X", "poke holes in this", or "what am i missing". Walks the decision tree branch by branch via AskUserQuestion (one question, recommended answer first), resolves dependencies in order, pins overloaded terms, surfaces code-vs-claim contradictions from the live codebase (codegraph-elai + elai.map + ELAI-FEATURE-MAP), routes unverified external claims to grounding, and hands a resolved-decisions block to prompt-transform / planning-workflow / idea-intake. Read-only on code, works in any FSM state, never auto-fires, never transitions the FSM.

elai · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add DITlieD/ELAI-archive --skill grill

技能说明


name: grill description: Relentless one-question-at-a-time interrogation that drives every unresolved decision out of a plan, design, or fuzzy idea BEFORE prompt-transform reformats it and any code or formal plan is written. USER-INVOKED ONLY — triggers when the user types /grill, /grill , says "grill me", "grill this plan/design", "stress-test this", "interrogate me on X", "poke holes in this", or "what am i missing". Walks the decision tree branch by branch via AskUserQuestion (one question, recommended answer first), resolves dependencies in order, pins overloaded terms, surfaces code-vs-claim contradictions from the live codebase (codegraph-elai + elai.map + ELAI-FEATURE-MAP), routes unverified external claims to grounding, and hands a resolved-decisions block to prompt-transform / planning-workflow / idea-intake. Read-only on code, works in any FSM state, never auto-fires, never transitions the FSM. license: MIT compatibility: "Designed for Codex. Works on Codex with explicit $grill invocation." metadata: version: "1.0.0" author: "elai"

Grill is the ambiguity killer that runs BEFORE a plan, not after. The user has a half-formed plan, design, or idea; grill interrogates it until every decision branch is resolved, every overloaded term is pinned, and no claim contradicts what the code already does. The output is a clean decision set prompt-transform and planning-workflow can build on, not a vibe.

This exists because a plan written over unresolved ambiguity bakes the ambiguity into code, and ELAI then spends a full FSM cycle (context-compiler, explorers, executor, auditor) implementing the wrong resolution. The cheapest place to kill a wrong assumption is a question; the most expensive is a shipped, wired, audited feature that solved the wrong problem.

Where grill sits in the ELAI flow: grill (de-fuzz the idea) -> prompt-transform (reformat the now-clean task) -> grounding sweep (token-discipline.md) -> planning-workflow / idea-intake / b-plan-runner / paper-to-plan. Grill is the user-facing front-end that idea-critic (agent-to-agent, internal) and a bare AskUserQuestion (single tool call, no method) do not provide.

HARD CONSTRAINT — USER-INVOKED ONLY

NEVER auto-fire grill off a keyword or off the shape of a task. Grill runs ONLY when the user explicitly asks for it in the current message. prompt-transform is the skill that auto-fires before implementation; grill is NOT — an interrogation the user did not ask for is friction, and ELAI's whole anti-sycophancy posture is undercut if the assistant starts cross-examining unprompted. If a task looks fuzzy and you think grilling would help, OFFER it in one line ("want me to grill this before i plan it ?") and wait. Do not start interrogating.

WHEN TO INVOKE

  • user types /grill or /grill <topic>
  • user says "grill me", "grill this", "stress-test this design", "interrogate me on X", "poke holes in this plan", "what am i missing"
  • user hands a fuzzy brief and explicitly asks to be questioned before planning

When NOT to invoke:

  • the task is already spec'd (deliverables + paths + acceptance criteria present) — go straight to prompt-transform / planning, no grilling
  • the question is a pure fact lookup — that is oracle, not grill
  • the user gave a direct command to implement something concrete — do not stall them with questions, confirm the one genuine fork if any and proceed
  • a plan/paper/repo link with a clear "build this" — that is paper-to-plan / orchestrate, not grill (unless the user explicitly asks to grill it first)
  • the surface's LOOK/UX is not yet decided (no mock, brief, or reference, "i dont know what this should look like", "design this with me") — that is divergent design, run cook first (.Codex/skills/cook/SKILL.md): cook diverges on real renders the user reacts to, THEN borrows this grill engine to converge. Grilling an undecided look forces convergence before the user has reacted to anything and railroads them into the first idea, the opposite of discovery.

THE METHOD

1 MAP THE DECISION TREE FIRST (silent, GRC). Before asking anything, lay out the branches the plan depends on: the core mechanic / data model / ownership decisions, then the dependent decisions that hang off each. Do this reasoning through mcp_think (GRC is mandatory in this repo; built-in thinking is disabled — a hand-written tree is not allowed, the tree comes from an actual mcp_think call with grounding). You are walking a tree, not firing a checklist. Resolve a parent decision before its children, because the child only matters under one branch of the parent.

2 CODEBASE-FIRST, ALWAYS. Before asking the user ANY question, check whether the code already settles it. Use codegraph-elai (codegraph_explore for "how does X work" / call chains, codegraph_callers / codegraph_callees / codegraph_impact for blast radius — Rust + TS, the pre-built index, answer directly), .Codex/tools/elai.map (grep for DEF/CALL/IMPL_TRAIT/SCIP_REF), the ELAI-FEATURE-MAP.md (feature status + composition edges), or a scoped Read. A question the code already answers is a question you do not ask — you state the finding instead ("the orchestrator already routes this through CloudModeRouter::route, so i'm assuming you keep that path — yes ?"). Asking what the code settles wastes the user's attention and reads as not having looked.

3 ONE QUESTION AT A TIME. Use AskUserQuestion, single question, never a batch. Each question carries a RECOMMENDED answer as the first option (label it "(Recommended)") with your reasoning in its description, plus the real alternatives. The recommendation is grounded: from the code you just read, an established project convention (AGENTS.md hard rule, systemPatterns.md, a decisions doc), or a named tradeoff — never a guess. If the recommendation depends on external API / library / 2026-ecosystem behavior you have not verified, say so and route it to grounding (step 7), do not assert it (grounded-by-default, E-38 posture).

4 PIN

阅读完整来源 ↗