Install any skill in seconds. Free to start, no credit card required.
Get Started Free →cronusl-1141/os-workflow
在 AI Team OS 项目里使用 CC 内置 Workflow(ultracode)时,让工作流产出回写 OS 的标准做法。当 Leader 准备调用 Workflow 工具编排子 agent 时使用。
Passed 22 of 22 test cases with the skill, and 4 of 22 without it.
and 27 more in the full report
19 fixed4 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/3/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 18 test cases the skill fixed. Same model, same prompt, with and without the skill.
If the OS MCP tool is temporarily unavailable and a workflow script needs to fall back to the HTTP API, where should it read the current active server port configuration?
| Checked | Without skill | With skill |
|---|---|---|
| The HTTP fallback port is read from ~/.claude/data/ai-team-os/api_port.txt. | Missed | Passed |
The instructions your model reads when the skill loads.
调用 Workflow 后,每个内部 agent 会被 hook 自动注册成一个 OS 团队(workflow-<wf_id>,
一次 workflow = 一个团队)。追踪是自动的,但工作内容不会自己入库——下面两件事必须你做。
调用 Workflow 前用 task_create 把这次工作方向登记上墙并置 running(§2 的回写指令要把它的 id
插进每个 agent 的 prompt,事后补建来不及),完成后 task_update 置 completed 并填 result。
把下面这段粘进你写的 workflow 脚本里每个 agent() 的 prompt 末尾(已验证 workflow
agent 能调 OS 的 MCP 工具 + HTTP API,非沙盒):
【回写 OS(收尾必做)】
1. ToolSearch 加载:select:mcp__ai-team-os__task_memo_add,mcp__ai-team-os__report_save
2. 完成本职工作后:
- task_memo_add(task_id="<总任务id>", content="<这步干了啥+关键结论>", memo_type="progress")
- 重要产出再 report_save(...) 落库,并把 report_id 写进 memo
3. 你在项目目录运行,MCP 自动带项目头,无需关心端口/项目 id。
在脚本里把 <总任务id> 用第 1 步 task_create 拿到的 id 通过 prompt 字符串插值传进去。
// Leader 先 task_create 拿到 taskId(OS MCP),再写 workflow:
const WRITEBACK = `\n【回写 OS(收尾必做)】\n1. ToolSearch: select:mcp__ai-team-os__task_memo_add\n2. 完成后 task_memo_add(task_id="${taskId}", content="...", memo_type="progress")\n3. 项目目录运行,MCP 自动带项目头。`
const r = await agent('你的实际任务……' + WRITEBACK, { schema, label })
不传 model 即继承主会话模型,所以每个 agent() 都显式写 model(层级别名如 'opus'、'fable',浮动到最新,不写死型号)。选哪一档按使用者自己的派工策略(写在项目 CLAUDE.md 或用户规则里),本技能不预设档位。
test cases passed, vs 4 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.