菜单
Decompose a task into subtasks with a planner, execute them with a tool-using worker, and synthesize the findings -- the orchestrator/workers pattern, sequential v1.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/KrakenNet/stargraph --skill orchestrator-workers命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Plan a coding task, generate and execute Python, and loop on reviewer feedback until the code passes -- a plan/code/judge fix-loop with governed execution.
Research a question with web search and page reads, judge the answer for completeness, and keep digging at the named gaps until nothing major is missing.
Draft an answer, judge it against a rubric, and refine on the judge's written feedback until it passes -- the generate/evaluate/optimize loop.
基于 SOC 职业分类
正在显示 SKILL.md
| name | orchestrator-workers |
| description | Decompose a task into subtasks with a planner, execute them with a tool-using worker, and synthesize the findings -- the orchestrator/workers pattern, sequential v1. |
| subgraph | graph.yaml |
Plan → work → synthesize (benchmark T5/T10). A plan node decomposes
the task, a react worker executes the subtask list through the
governed tool pipeline, and a summarize node synthesizes the
findings. Sequential v1: one worker walks the whole subtask list;
parallel fan-out lands when the IR's parallel action compiles to
live routing.
task.tasks (the plan), answer (worker findings),
tool_trace, summary (the synthesis).stargraph run graph.yaml (network tools need the
tools extra; set the LM via --lm-model/--lm-url or per-node
config.model).kind: subgraph, spec: <path to graph.yaml>.Edit graph.yaml: the worker's tool allowlist and max_iters, or the
plan/synthesize instructions.