菜单
Run a relentless one-question-at-a-time planning interview that sharpens vocabulary and journals durable reasoning into the Flatbread Effort Graph. Use when a plan is fuzzy and needs an Effort Graph trail instead of ADRs.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Journal reasoning (decisions, findings, issues, constraints, risks) into a Flatbread Effort Graph and recall it with bounded reads. Use when starting or resuming a thread of work, recording a decision or finding, resolving an issue, checking what is blocking or still open on an effort, or when the user mentions effort graph, journaling, blocking decisions, or agent memory.
Sharpen a project's vocabulary and planning through one-question-at-a-time grilling, then journal Decisions, Constraints, Findings, Issues, and Risks into the Flatbread Effort Graph. Use when a plan needs durable reasoning instead of ADRs.
Fable 5 orchestrator-executor pattern for big tasks
Decompose a user's task into a DAG of subtasks and execute them with Cursor SDK local subagents in topological order, rendering live streaming status to a canvas. Each task has a complexity (HIGH/MED/LOW) that maps to a model. Use when the user asks to fan out work, decompose a task into a DAG, run subagents in parallel, or break a large task into a dependency graph.
DEPRECATED ALIAS — the DAG task runner has been promoted to the workspace package @flatbread/proof. Use the `proof` skill (.cursor/skills/proof/SKILL.md) for new work; this entry only exists to redirect agents that still reference the old name.
Guide schema-breaking Flatbread migrations across core schema generation, resolver arguments, generated TypeScript, CLI behavior, examples, docs, and coordinated monorepo releases. Use when a change may alter IDs, refs, filters, root query names, generated types, config shape, publish scripts, or example app behavior.
| name | grill-with-efforts |
| description | Run a relentless one-question-at-a-time planning interview that sharpens vocabulary and journals durable reasoning into the Flatbread Effort Graph. Use when a plan is fuzzy and needs an Effort Graph trail instead of ADRs. |
| disable-model-invocation | true |
Run a one-question-at-a-time grilling session using effort-modeling.
Offer a recommended answer for each decision, wait for the user's response, and resolve dependent choices in order. Explore the codebase for facts, but leave choices to the user. Do not implement the plan until shared understanding is confirmed.
