菜单
Submit a proof role prompt to a ChatGPT project via CDP and monitor for completion. Verifies Extended Pro (or toggles Deep Research for the literature role), sends, reports the chat URL, and provides recovery guidance for long-running roles.
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
Fan out a 4-member council (1 Codex thinking-high + 1 Gemini Pro + 1 Claude Opus + 1 ChatGPT Extended Pro) on a stalled re-attack. Preserves all four independent memos; hands off to the regular Strategy Searcher for pure selection. Opt-in (attempt ≥2), ~3× the cost of a single search.
Harvest a completed ChatGPT chat's last assistant message into a response file. Use when a role finished but the response file wasn't captured (e.g., orchestrator lost the chat URL, or the submit script died after the model responded).
Create or update {PROOF_REPO}/referee_targets.yaml — the target-journal registry the paper_referee role consults to judge whether the result clears the bar at the journals you might submit to. Optional; without it the referee falls back to a generic publishability check.
Use when working in MathPipeProver on ChatGPT project preparation, durable source refresh, project-source inspection, or browser-backed external_agent submission. Prefer scripts/chatgpt_browser_agent.sh prepare/submit over ad hoc UI work, enforce the Extended Pro target, and keep durable sources separate from temporary attachments.
Read-only one-shot inspection of a live ChatGPT chat — returns generating flag, assistant turn count, last assistant message length and tail. Use during long-running roles to check whether the chat is still working or done.
Verify or set the ChatGPT composer to the Extended Pro target (reasoning Pro + model 5.5; pill reads "Extended Pro" or "Pro"). Required before any analytical submission.
| name | submit-role |
| description | Submit a proof role prompt to a ChatGPT project via CDP and monitor for completion. Verifies Extended Pro (or toggles Deep Research for the literature role), sends, reports the chat URL, and provides recovery guidance for long-running roles. |
Canonical content: .claude/commands/submit-role.md in this repo. Codex and
Claude Code share the same operational steps — edit the Claude command file,
not this stub, when changing the procedure.
Use this when MathPipeProver pauses with waiting_external_agent and the
orchestrator needs to fulfill the pending request manually. The skill:
prompts/soft/02_literature_soft.md).scripts/chatgpt_browser_agent.sh submit ... (preferred) or
scripts/chatgpt_browser_agent/cdp_submit.mjs (lower-level)./inspect-chat (one-shot), /recover-chat
(harvest), /heartbeat <interval> (unattended orchestrator-pace loop).Read .claude/commands/submit-role.md for the full step-by-step, CLI
argument shapes, and error-recovery guidance.