菜单
This skill should be used when the user asks to "人机风暴", "Human-Machine Brainstorm", "human storm", "ccb brainstorm", "需求对齐调度", "spec convergence", or wants a CCB-based multi-model requirement alignment loop with Codex as the dispatcher.
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
Use when turning an academic paper PDF/arXiv/OpenReview page/local LaTeX source into a single-file Chinese HTML deep-reading page, especially when the user wants a Cheat-Sheet style explanation, KaTeX formulas, figure/table evidence, validation, or a publishable research page.
Use when you explicitly want a second local or SSH remote Codex CLI session to prototype, debug, or review code, while your current session remains the primary owner of the final result.
Use when the user wants multi-agent division of labor for research-led work and the lead should stay on the critical path while 1-2 bounded sidecars handle low-coupling tasks. Do not use this for tiny tasks, fully sequential debugging, or overlapping refactors.
Use when the user asks to review a skill, analyze skill quality, update a skill version, or run a repeatable keep/disable/archive decision loop from real failures instead of abstract best practices.
Use when the user explicitly wants to upload a final or near-final PDF to paperreview.ai for an external second opinion. Skip this for local paper critique, which should go through `paper-review-pipeline` first.
学术论文写作助手，专门用于 LaTeX 论文编写、BibTeX 管理、格式化、学术写作规范检查。适用于 AI/ML 研究论文、会议投稿（NeurIPS、ICML、ICLR 等）
| name | Human-Machine Brainstorm (人机风暴) |
| description | This skill should be used when the user asks to "人机风暴", "Human-Machine Brainstorm", "human storm", "ccb brainstorm", "需求对齐调度", "spec convergence", or wants a CCB-based multi-model requirement alignment loop with Codex as the dispatcher. |
| version | 0.1.0 |
| disable-model-invocation | true |
Run a repeatable multi-model requirement alignment loop in CCB where:
Keep every round auditable by exporting per-provider context into ./.ccb/history/ and keeping the canonical spec in ./.ccb/spec/.
./.ccb/spec/overview.md as the single source of truth. Only Claude Code edits it.C-Q01, C-Q02, ...O-Q01, O-Q02, ...This workflow is optimized for a 2×Codex setup:
Create (or choose) a topic directory (recommended location: $HOME/ccb-startups/...).
bash $HOME/.codex/skills/human-machine-brainstorm/scripts/hmb-init.sh "<topic-slug>"Start CCB.
ccbccb claude codex opencode cmd (fallback)Talk only to the Codex Chair (cmd pane).
claude, opencode, and participant codex via ask.references/round_prompt_template.md if needed.Send the same “Round prompt” to:
ask claude "<ROUND PROMPT>"ask opencode "<ROUND PROMPT>"ask codex "<ROUND PROMPT>" (participant Codex pane)Require them to respond with:
C-Q## / O-Q## / P-Q##Ask the human to answer in this format:
C-Q01: ...C-Q02: ...O-Q01: ...P-Q01: ...Optionally allow a shared block:
SHARED: ... (facts that apply to both)Send Claude only C-* + SHARED.
Send OpenCode only O-* + SHARED.
Send participant Codex only P-* + SHARED.
From the cmd pane (or any shell pane) run:
./.ccb/bin/round-save.sh 20This writes:
./.ccb/history/claude-<timestamp>.md./.ccb/history/codex-<timestamp>.md./.ccb/history/opencode-<timestamp>.mdAsk Claude to update:
./.ccb/spec/overview.md (bump version vN)./.ccb/spec/open_questions.md (close answered questions)./.ccb/spec/decisions.md (record non-reversible decisions)./.ccb/spec/changelog.md (vN → vN+1 diff)Then re-run another round until all reviewers say “no blocking issues”.
Provide a clean handoff pack:
./.ccb/spec/overview.md./.ccb/spec/decisions.md./.ccb/spec/open_questions.md (should be empty or non-blocking)./.ccb/spec/changelog.mdInstruct GPT-5.2 to: