orchestrate
Skill4 starsChanged 29 days agoMITView on GitHub
Orchestrate multi-task execution plans using Claude's native Agent tool (DAG-based, no external engine). Use when: executing a plan.json file with parallel/sequential task dependencies. Not for: producing the plan in the first place — use /plan; single tasks with no dependencies between them. Keywords: orchestrate, plan, execute, DAG, task plan.
- Deletes or force-pushes
- Commits and pushes
161 other projects use a version of this.
Adopted by
Most recently taken up by
- alexratmanpl/business-agent-skillstheir own version, first seen Nov 8, 2026
- gtonkov/claude-codetheir own version, first seen Nov 8, 2026
- edilsonvilarinho/usage-monitortheir own version, first seen Nov 8, 2026
- nathanonn/agent-skillstheir own version, first seen Nov 8, 2026
- peterpme/skillstheir own version, first seen Nov 8, 2026
- GDriem/agent-skillstheir own version, first seen Nov 8, 2026
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-erSkilldefine-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
EternallLightSkillorchestrate-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-erSkillrecord-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
PinkneyJiangSkillimprove-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
kjnezSkillticket
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
xfstudioSkillreverse-engineer
Expert reverse engineer specializing in binary analysis,
Also in 3 projects that use this
Other versions161 projects use a version of this.
Word for word · 1
- AsiaOstrich/universal-dev-standards★ 84100% same
Edited · 0
None found.
Wrote their own version · 160
- Significant-Gravitas/AutoGPT★ 188ksame name
- rohitg00/pro-workflow★ 2.9ksame name
- apmantza/pi-lens★ 521same name
- boshu2/agentops★ 453same name
- quantumaikr/quant.cpp★ 403same name
- Noizefield/audio-plugin-coder★ 334same name
- kagenti/kagenti★ 303same name
- varun29ankuS/shodh-memory★ 294same name
- provencher/codex-skills★ 271same name
- first-fluke/fullstack-starter★ 226same name
150 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository55 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ac-coverageSkill
- adrSkill
- ai-collaboration-standardsSkill
- ai-friendly-architectureSkill
- ai-instruction-standardsSkill
- api-designSkill
- atddSkill
- auditSkill
- bddSkill
- brainstormSkill
- changelogSkill
- checkinSkill
- ci-cdSkill
- code-reviewSkill
- commitSkill
- contract-testSkill
- databaseSkill
- deploySkill
- methodologySkill
- dev-workflowSkill
- docgenSkill
- documentation-guideSkill
- durableSkill
- e2eSkill
- error-code-guideSkill
- git-workflow-guideSkill
- incidentSkill
- journey-test-assistantSkill
- knowledge-graphSkill
- logging-guideSkill
- metricsSkill
- migrateSkill
- observabilitySkill
- planSkill
- prSkill
- discoverSkill
- project-structure-guideSkill
- pushSkill
- refactorSkill
- releaseSkill
- requirementSkill
- retrospectiveSkill
- reverseSkill
- runbookSkill
- securitySkill
- scanSkill
- skill-builderSkill
- sloSkill
- spec-deriveSkill
- sddSkill
- sweepSkill
- tddSkill
- coverageSkill
- testing-guideSkill
The file
Files
/orchestrate — 任務計畫編排 Skill
用法
/orchestrate <plan.json> # 執行計畫
/orchestrate <plan.json> --dry-run # 僅驗證,不執行執行流程
Step 1: 讀取與解析計畫(Claude-native)
使用 Read tool 讀取 plan.json,直接由 Claude 解析:
- 讀取 JSON 檔案,解析為任務清單
- 驗證結構:
tasks非空、每個 task 含id、title、spec - 安全掃描:檢查
task.spec是否含危險指令(rm -rf /、DROP DATABASE、git push --force)- 若發現安全問題,列出所有問題並詢問使用者是否繼續
- 拓撲排序:依
depends_on欄位將 tasks 分組為執行層(layers)- Layer 0:沒有依賴的 tasks(可並行)
- Layer N:依賴全部在 Layer 0..N-1 中的 tasks
若 validation.valid 為 false,輸出錯誤訊息並停止。
Step 2: 呈現執行計畫
向使用者顯示解析結果:
計畫:<project> 品質:<quality>
──────────────────────────────────
Layer 0 (並行):T-001, T-002
Layer 1 (序列):T-003 (依賴 T-001)
Layer 2 (序列):T-004 (依賴 T-002, T-003)
──────────────────────────────────
共 4 個任務,3 個執行層若使用 --dry-run:顯示以上摘要後立即停止,不啟動任何 Agent。
Step 3: 逐層執行
對 layers 陣列中的每一層:
- 同層並行:同一層的 tasks 在同一訊息中啟動多個 Agent tool
- Agent tool 參數:
prompt:task.spec + acceptance_criteria + user_intent 組合而成的執行提示isolation: "worktree":每個 task 在獨立 git worktree 執行description:"Task {task.id}: {task.title}"
- 等待完成:所有同層 agents 完成後,才進入下一層
Agent 提示範本:
Task: {task.title}
Spec:
{task.spec}
Acceptance Criteria:
{task.acceptance_criteria 逐條列出}
User Intent:
{task.user_intent}
After completing the task, run: {task.verify_command}Step 4: 依賴失敗處理
如果某個 task 的 agent 回報失敗:
- 標記該 task 為
failed - 後續層中
depends_on包含該 task ID 的所有 tasks 標記為skipped - 繼續執行不受影響的 tasks
- 最終報告中標示失敗原因
Step 5: Quality Gate
每個 task 完成後,若 task 定義了 verify_command:
- 使用 Bash tool 執行
verify_command - 成功:記錄
status: "success" - 失敗:
- 若
quality為"strict"或"standard":啟動 Fix Loop - Fix Loop:將錯誤輸出回傳給 agent,重新執行(最多 3 次)
- 超過重試上限:標記為
failed
- 若
Step 6: Judge 審查(選用)
如果 task 定義了 judge: true:
- 啟動一個額外的 Agent tool 進行審查
- 提示:
審查 task {id} 的 git diff,依照 code-review 標準檢查 - Judge 結果附加到最終報告
Step 7: 產出報告
彙整所有 task 結果,輸出執行報告:
{
"summary": {
"total_tasks": 4,
"succeeded": 3,
"failed": 1,
"skipped": 0,
"total_duration_ms": 120000
},
"tasks": [
{ "task_id": "T-001", "status": "success", "duration_ms": 30000 },
{ "task_id": "T-002", "status": "failed", "error": "..." },
{ "task_id": "T-003", "status": "skipped", "reason": "依賴任務失敗" }
]
}品質設定檔
| Profile | 行為 |
strict | 全部檢查 + Fix Loop 最多 5 次 |
standard | lint + test + Fix Loop 最多 3 次(預設) |
minimal | 僅跑 verify_command,不 Fix Loop |
none | 不執行任何驗證 |
重要注意事項
- 每個 Agent tool 的
isolation: "worktree"會自動建立 git worktree depends_on: []的 tasks 在同一層內全部並行- 使用繁體中文回覆使用者
版本歷程
| 版本 | 日期 | 變更 |
| 2.0.0 | 2026-04-28 | 升格為 UDS 正式 Skill;Step 1 改為 Claude-native 解析(移除 plan-resolver-cli.js 依賴);新增 Quality Gate / Fix Loop 章節(XSPEC-097 Phase 3) |
| 1.0.0 | 2026-04-09 | 初始發布(從上游遷移) |
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
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.

