agentleFS
Sign inStart free
quantumaikrquantumaikr/quant.cpp/.claude/skills/orchestrate/skill.md

orchestrate

Skill403 starsChanged 7 months agoApache-2.0View on GitHub

quant.cpp 개발 오케스트레이터. 에이전트 팀을 구성하고, score 기반 Phase 전환, 병렬 작업 위임, Merge Gate를 자동 수행한다. '개발 시작', '하네스 실행', '팀 구성', '오케스트레이션' 요청 시 사용. 프로젝트의 핵심 개발 루프를 조율하는 상위 스킬.

  • Deletes or force-pushes

161 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use define-requirements, orchestrate-plan and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • sson0-erSkill

    define-requirements

    Work with the user, one question at a time, to complete the requirements document (docs/claudex/<slug>/01-requirements.md). Run by the orchestrator (parent). Stays out of design and implementation.

    Also in 3 projects that use this

  • EternallLightSkill

    orchestrate-plan

    Use when executing a locked, reviewed PLAN.md by delegating the implementation to visible worker agents in Orca, herdr, or cmux ONE PHASE at a time — splitting the plan into context-window-sized phases, giving every phase a pristine worker context, and (when the plan touches INDEPENDENT repos) running one worker per repo IN PARALLEL. Triggers on "run the plan with a worker", "execute the plan in the other pane", "split the plan into phases and build it with workers", "build the backend and frontend in parallel panes". Not for edits you can finish inline; outside Orca, herdr, or cmux use tgc-skills:orchestrate.

    Also in 3 projects that use this

  • sson0-erSkill

    record-evidence

    How to record external facts (docs, command output, codebase findings) as evidence and design choices as decisions. Used by the researcher, designer and reviewer agents.

    Also in 3 projects that use this

  • PinkneyJiangSkill

    improve-architecture

    扫描代码库中的架构摩擦点，识别浅模块并挖掘深模块演进机会。生成可视化交互式 HTML 诊断报告，并在用户确认后闭环实施深度重构。

    Also in 4 projects that use this

  • kjnezSkill

    ticket

    Work on a JIRA/Linear ticket end-to-end: read ticket details, explore codebase, create a branch, implement with TDD, run quality checks, update ticket status, and create a PR. Use when the user provides a ticket ID to implement. Triggers on requests like "/ticket PROJ-123", "work on this ticket", "implement PROJ-123".

    Also in 4 projects that use this

  • xfstudioSkill

    reverse-engineer

    Expert reverse engineer specializing in binary analysis,

    Also in 3 projects that use this

The file

Create a free account to mount
Files
skill.md

quant.cpp Orchestrator

quant.cpp 에이전트 팀을 조율하여 프로젝트를 자율적으로 발전시키는 통합 스킬.

아키텍처: 계층적 위임 + 팬아웃/팬인

[Orchestrator/Leader]
    ├── score.sh 실행 → Phase 결정
    ├── Phase에 맞는 에이전트 팀 구성
    │   ├── core-dev (알고리즘)
    │   ├── perf-dev (SIMD/GPU)
    │   └── qa (검증)
    ├── 워커들이 병렬 작업 (Fan-out)
    ├── Merge Gate: 하나씩 머지 + score 확인 (Fan-in)
    └── 다음 라운드 결정

워크플로우

Step 1: 상태 평가

bash score.sh --quick

현재 점수, 가장 낮은 차원, 다음 WBS 항목을 파악한다.

Step 2: Phase 결정 및 팀 구성

ScorePhase전략
< 0.05Foundation직접 수행 (단일)
0.05~0.30Corecore-dev × 3 병렬 (polar, qjl, uniform)
0.30~0.60Advancedcore-dev + perf-dev + qa 병렬
0.60~1.00Fine-tune단일 에이전트 정밀 작업

Step 3: 작업 위임

에이전트 팀 모드:

TeamCreate("tq-round-N", members=[core-dev, perf-dev, qa])
TaskCreate("Implement tq_polar.c", owner="core-dev", blocked_by=[])
TaskCreate("NEON optimize polar", owner="perf-dev", blocked_by=["polar"])
TaskCreate("Verify polar boundaries", owner="qa", blocked_by=["polar"])

서브에이전트 모드 (ClawTeam):

clawteam spawn --team tq-N --agent-name core-polar --workspace \
  --task "Read .claude/agents/core-dev.md for your role. Implement tq_polar.c..."

Step 4: Merge Gate

워커 완료 후, 하나씩 순차적으로 머지:

  1. pre_merge=$(git rev-parse HEAD)
  2. git merge <worker-branch> --no-edit
  3. bash score.sh --quick
  4. score 하락 → git reset --hard $pre_merge (롤백)
  5. score 유지/상승 → 다음 워커

Step 5: QA 검증

Merge Gate 통과 후 QA 에이전트에게 경계면 검증 요청:

  • .claude/agents/qa.md의 체크리스트 실행
  • 발견 사항을 다음 라운드에 반영

Step 6: 루프 반복

목표 score 도달 또는 WBS 완료까지 Step 1로 돌아간다.

에러 핸들링

상황대응
워커 빌드 실패해당 워커 결과 버리고 다음 워커로
score 하락즉시 롤백, 원인 분석 후 재시도
테스트 실패QA에게 위임하여 원인 파악
머지 충돌모듈 소유권 위반 — 충돌 워커 결과 버림

테스트 시나리오

정상 흐름: score 0.90 → architect가 perf-dev에 NEON 최적화 위임 → simd_speedup 4x → merge gate 통과 → score 0.95

에러 흐름: core-dev의 polar 변경이 turbo 테스트를 깨뜨림 → merge gate에서 score 하락 감지 → 롤백 → qa가 경계면 불일치 보고 → core-dev에 수정 지시

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free