parallel-execution
Skill2 starsChanged 6 months agoMITView on GitHub
堂官-员外郎并行模式,六部收到 ≥ 2 个互不冲突子任务时由堂官协调员外郎 Teammate 并行执行
10 other projects use a version of this.
Adopted by
Most recently taken up by
- intelligentcode-ai/skillstheir own version, first seen Nov 15, 2026
- andreymudri/claude-teammatestheir own version, first seen Nov 2, 2026
- andreymudri/fleetmatestheir own version, first seen Nov 2, 2026
- NoobyGains/godmodetheir own version, first seen Nov 1, 2026
- kimasplund/thinkbetter-skillstheir own version, first seen Oct 25, 2026
- garri333/Skillstheir own version, first seen Oct 11, 2026
Used with
Projects with it also use writing-skills.
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.
OpenAISkillwriting-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Also in 3 projects that use this
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- CloudAI-X/claude-workflow★ 1.4ksame name
- CloudAI-X/claude-workflow-v2★ 1.4ksame name
- CloudAI-X/opencode-workflow★ 275same name
- NoobyGains/godmode★ 120same name
- andreymudri/claude-teammates★ 3same name
- andreymudri/fleetmates★ 3same name
- beeltec/skills★ 2same name
- garri333/Skills★ 1same name
- intelligentcode-ai/skills★ 1same name
- kimasplund/thinkbetter-skills★ 0same name
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 repository26 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analysis-frameworkSkill
- architecture-overviewSkill
- audit-boundariesSkill
- biannianSkill
- communication-protocolsSkill
- dispatch-rulesSkill
- fault-toleranceSkill
- governance-coreSkill
- hanlinSkill
- intent-classificationSkill
- kejuSkill
- morning-courtSkill
- permission-matrixSkill
- qijuzhuSkill
- redline-referenceSkill
- report-formatSkill
- review-coverageSkill
- shengzhiSkill
- special-directivesSkill
- team-bootstrapSkill
- ticket-formatSkill
- token-optimizationSkill
- tuichaoSkill
- veto-mechanismSkill
- zouzheSkill
The file
Files
部门内并行执行
六部收到 ≥ 2 个子任务时,切换为堂官-员外郎模式并行执行。
触发条件
- 尚书省同时向同一部门派发 ≥ 2 个子任务
- 或部门已有 1 个进行中任务,又收到新的无冲突任务
- 仅 1 个子任务时不启动堂官模式,直接执行
角色
堂官(部门主 Teammate):冲突检测 → 任务分组 → 申请创建员外郎 Teammate → 汇总产出 → 回报尚书省。堂官模式下原则上不直接产出,仅协调。例外:串行链仅含 1 个任务时堂官可自行执行。
员外郎(Teammate Worker):堂官申请创建的独立 Teammate,继承部门核心身份,在独立 worktree 中执行单个子任务,完成后通过 SendMessage 向堂官回报。
上级并行提示(parallel_hint)
堂官在冲突检测前,须先查看工单中尚书省附加的 parallel_hint:
confidence: high+ 堂官验证无冲突 → 直接并行confidence: medium+ 堂官验证无冲突 → 并行confidence: medium+ 堂官发现冲突 → 改为串行,回报尚书省说明原因confidence: low或无 hint → 堂官自行完整检测后决定
hint 是建议不是命令:堂官有权基于实际冲突检测推翻上级标注,但推翻时须在回报中说明原因。即使上级未附加 hint,堂官仍须自行判断是否可并行。
冲突检测
1. 参考上级 parallel_hint(若有)
2. 提取每个任务的影响范围(文件路径、模块、外部资源)
3. 两两比较影响范围
- 无交集 → 可并行
- 有交集 → 必须串行
4. 输出:并行组 + 串行链📎 各部门冲突判定细则与完整约束清单见
parallel-conflict-rules.md
执行流程
收到 N 个子任务(N ≥ 2)
│
├── 堂官提取影响范围,划分 [并行组] + [串行链]
│
├── 并行组:
│ ├── 每个任务申请创建 1 个员外郎 Teammate(独立 worktree)
│ ├── 员外郎并行执行,通过 SendMessage 向堂官汇报
│ └── 完成策略:
├── 全部员外郎完成 → 堂官正常收集产出
└── 某员外郎超过执行超时(继承 fault-tolerance 六部默认 10 分钟)仍未完成 →
堂官不等待,以 **partial_done** 状态汇总已完成产出
汇总报告须含:`{ "status": "partial_done", "completed": [...], "timed_out": [...] }`
门下覆奏时按**部分验收**标准(仅验收已完成部分,注明缺失项及影响)
│
├── 串行链:
│ ├── 仅 1 个任务 → 堂官自行执行
│ └── ≥ 2 个任务 → 逐个启动员外郎按序执行
│
└── 堂官汇总
├── 检查产出间是否有 merge conflict
├── 有冲突 → 堂官协调解决或上报尚书省
└── 无冲突 → 合并产出,统一回报尚书省约束
- 员外郎上限:单部门同时不超过 3 个,超出排队
- 必须隔离:员外郎使用独立 worktree,禁止同目录并行修改
- 员外郎不互通:所有交互经堂官中转
📎 各部门冲突判定细则与完整约束清单见
parallel-conflict-rules.md
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.

