메뉴
Solve ambiguous, high-stakes, or multi-variable questions with a labelled problem tree. Use for open-ended life, business, product, strategy, and root-cause reasoning; route concrete feature briefs to $grill-me and specific failures to $debugging.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | brainstorming |
| description | Solve ambiguous, high-stakes, or multi-variable questions with a labelled problem tree. Use for open-ended life, business, product, strategy, and root-cause reasoning; route concrete feature briefs to $grill-me and specific failures to $debugging. |
Use Root → Expand → Solve → Synthesize. The tree is scaffolding; one answer to the root is the deliverable.
Scale depth with ambiguity, stakes, and irreversibility:
A directly answerable node is a leaf. Complete calibration when the root is one sharp sentence and the selected depth can plausibly change its answer.
A). State the exact question, decision, scope, and known constraints.assumed: statements;uncertainty × impact on A. Record low-leverage branches as
pruned.A, or it is
outside scope.A, its
load-bearing assumptions, and the fact that would most change it.Ask the user only at a pivotal unknown that evidence cannot resolve. Use the available user-input
mechanism with two to four concrete options and one recommendation. In a non-interactive run, choose
the safest plausible assumption, mark it assumed:, and continue.
Use stable IDs: A; children B, C, D; deeper nodes B1, B2, then B1-1. Render a nested
Markdown list so the user can steer by ID. Keep labels terse and converse in the user's language.
The brainstorm is complete only when every open node is solved, pruned, or explicitly blocked and
the final synthesis answers A. Return the tree in chat; save it only when the user requests a file.
Bootstrap software repositories from live evidence. Use for initial setup, inherited-codebase rehabilitation, repository mapping, conventions, documentation architecture, safe restructuring, or agent-ready tooling.
Diagnose software failures through evidence-based root-cause analysis. Use for bugs, failing tests, runtime errors, data anomalies, stuck jobs, environment failures, and intermittent or expensive-to-reproduce incidents.
Create, edit, and run persistent Codex workflow graphs with optional GitHub delivery.
Turn a rough software feature request into one codebase-grounded implementation brief. Use for feature pitches, vague product requirements, solution exploration, or explicit “grill me” requests before coding; use $brainstorming for non-implementation questions.
Implement an agreed story, plan, or failing-test target and prove the resulting behavior. Use when an accepted contract authorizes production changes; route diagnosis-only work to $debugging and test design to $tdd.
Land finished work in a Git repository through Gate, Record, Commit, and Publish. Use when the user asks to close completed work, commit and push it, or open a pull request; use repository review workflows for reviewing an existing PR.