메뉴
Use when acting as main_brain inside a rendered MathorCup instance and you need to inspect the ready pool, dispatch a bounded task, observe its status, or decide close, reopen, or cancel through repo scripts instead of hand-editing runtime truth.
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
Use when main_brain needs to inspect one task in depth, reconstruct its event and queue history, or compare multiple worker artifacts through adjudicate_task.sh before any human-gated close, reopen, or cancel decision.
Use when acting as a bounded worker inside a rendered MathorCup instance. Read the task packet, stay inside allowed paths, and return structured feedback or retrospective artifacts through the repo gate files without closing or mutating runtime state directly.
Use when a template-source change needs a safe, low-risk smoke test. Render scaffold into a temporary instance, then run validate_agent_docs.sh and doctor.sh on the rendered target without touching backend runtime execution.
Use when maintaining the mathorcup-template repository itself rather than a rendered instance. Read scaffold as the source of truth, edit scaffold-first artifacts, preserve stable script entrypoints, and validate changes with template-source checks plus render-only smoke.
Use when you need current runtime facts inside a rendered MathorCup instance. Read .env and project/paper/runtime/paper.env as machine truth, then use runtime contracts as rendered mirrors and never confuse the native bridge with runtime state truth.
| name | main-brain-dispatch |
| description | Use when acting as main_brain inside a rendered MathorCup instance and you need to inspect the ready pool, dispatch a bounded task, observe its status, or decide close, reopen, or cancel through repo scripts instead of hand-editing runtime truth. |
Use this skill for task orchestration in a rendered instance.
.codex/requirements.tomlAGENTS.mdMEMORY.mdproject/spec/runtime_contract.mdproject/spec/multi_agent_workflow_contract.mdbash scripts/doctor.sh --target <dir>
bash scripts/main_brain_summary.sh --target <dir>
bash scripts/show_task.sh --task <task_id> --target <dir>
bash scripts/list_open_tasks.sh --open-only --target <dir>
bash scripts/dispatch_task.sh --task <task_id> --owner <owner> --target <dir>
dispatch_task.sh is the canonical path for feedback skeleton creation.dispatch_task.sh writes a packet artifact under project/workflow/packets/ by default.submit_feedback.sh is only for repair or retrospective initialization.TASK_CODE_MODEL_P1TASK_CODE_MODEL_P23TASK_CODE_MODEL_P4project/output/model_manifest.json from project/output/MODEL_MANIFEST_TEMPLATE.json.bash scripts/paper_acceptance_check.sh --target <dir> --write-report
bash scripts/artifact_index.sh --target <dir>
paper_acceptance_check.sh after paper build and before final paper acceptance.artifact_index.sh when packets, feedback, callbacks, exec runs, handoffs, and adjudications are scattered.close_task.sh, reopen_task.sh, and cancel_task.sh.project/runtime/task_registry.jsonproject/runtime/work_queue.jsonproject/runtime/event_log.jsonlThe main brain still decides acceptance. Native bridge files do not replace repo state or repo scripts.