메뉴
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).
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
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.
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.
Add or remove durable files in a ChatGPT project's Sources tab. Use after a verified result lands, after a route pivot, or when the durable proof-state file has been updated locally.
SOC 직업 분류 기준
| name | recover-chat |
| description | 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). |
Canonical content: .claude/commands/recover-chat.md in this repo. Codex
and Claude Code share the same procedure — edit the Claude command file,
not this stub.
Use when a chat completed but its response wasn't captured — the orchestrator has the chat URL but no response file on disk. Shells out to:
scripts/chatgpt_browser_agent.sh recover --chat-url URL --response-file PATH [--cdp-url URL]
This is also the right recovery path when a submit died mid-flight after the
model started responding. Always try /recover-chat before resubmitting —
re-running a 8-20 min Extended Pro role only to find the prior chat had
already completed is the worst-case outcome.
Read .claude/commands/recover-chat.md for the full step-by-step.