跳到正文
cccskills
免费在 GitHub 公开

task-management

Manage an assigned Worker task from acceptance through delivery using taskflow. Keep work and optional progress notes in the task directory, submit structured results with deliverable paths, and report completion or blockers to the coordinator.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Use before any Worker taskflow call or assigned-task workflow, including reading task state, acknowledging a task, executing a task, tracking progress, handling blockers/questions, submitting structured results, or reporting completion. Always use this skill when the message mentions assigned task, task ID, shared/tasks, spec.md, meta.json, result.md, deliverables, BLOCKED, REVISION_NEEDED, SUCCESS, submit_task, or ack_task.

查看安装方法

适用场景

  • Accept an assigned task and read its requirements
  • Organize deliverables and progress notes by task
  • Submit results with completion or revision status
  • Report blockers to the coordinator

包含的文件(1)

  • SKILL.md4.3 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Task Management

You are a Worker. Execute only your assigned task.

Task Directory

All work for a task stays under:

shared/tasks/{task-id}/

Your coordinator creates:

shared/tasks/{task-id}/spec.md
shared/tasks/{task-id}/meta.json
shared/tasks/{task-id}/base/

You own:

shared/tasks/{task-id}/workspace/
shared/tasks/{task-id}/progress/
shared/tasks/{task-id}/<deliverables>

taskflow owns shared/tasks/{task-id}/result.md and meta.json. Do not hand-edit either file. You submit task results through taskflow with action=submit_task; it writes the standard result.md protocol for you.

ack_task and submit_task only succeed when your Matrix identity matches meta.json.assigned_to. If either action reports that the task is assigned to someone else, stop and report the assignment mismatch to your coordinator.

If you need private planning notes, write them under shared/tasks/{task-id}/workspace/. Do not create shared task-level plan.md.

Do not edit project-level shared/projects/{project-id}/plan.md or meta.json unless the task spec explicitly tells you to.

Execution Flow

  1. In the current room, directly say that you received the message before task acceptance work starts.

  2. Accept the task with taskflow. This single call pulls the task directory from storage, reads spec.md and meta.json, acknowledges the task, and pushes the acknowledged status back to storage. The response contains the spec content:

    {
      "action": "ack_task",
      "payload": {
        "taskId": "{task-id}"
      }
    }
    

    The response spec field contains the full task spec. Read it from the response instead of calling read_file separately.

    meta.json.room_id is the task's assignment and delivery room. Use it only when cross-room delivery is truly needed. If it is missing, stop and report a blocker in the current session instead of guessing another room.

  3. Execute the task. Keep deliverables inside shared/tasks/{task-id}/.

  4. Submit the task result with taskflow. This writes shared/tasks/{task-id}/result.md, marks local task state submitted, pushes the task directory to storage, and verifies result.md exists on storage:

    {
      "action": "submit_task",
      "payload": {
        "taskId": "{task-id}",
        "status": "SUCCESS",
        "summary": "<one paragraph summary>",
        "deliverables": [
          "shared/tasks/{task-id}/workspace/<file>"
        ]
      }
    }
    

    Use SUCCESS, SUCCESS_WITH_NOTES, REVISION_NEEDED, or BLOCKED for normal task execution status.

    Submitting a result ends this Worker task. If more work is needed after REVISION_NEEDED or BLOCKED, wait for your coordinator to assign a new task; do not resume or rewrite the submitted task on your own.

  5. In the current room, directly @mention your coordinator with completion:

    @coordinator:domain TASK_COMPLETED: {task-id} - <short outcome>. Result: shared/tasks/{task-id}/result.md
    

    Do not look up your Worker profile room or private room as a fallback. The task directory is the source of truth if you ever need to verify the assignment room.

Blocked

If blocked, submit a BLOCKED result. submit_task automatically pushes and verifies:

{
  "action": "submit_task",
  "payload": {
    "taskId": "{task-id}",
    "status": "BLOCKED",
    "summary": "<what is blocking you>",
    "deliverables": []
  }
}

Then @mention your coordinator:

@coordinator:domain BLOCKED: {task-id} - <what is blocking you>

Do not invent missing task files, project plans, or shared directories.

Progress

Progress notes are optional unless the task spec asks for them. If you write progress, put it under:

shared/tasks/{task-id}/progress/YYYY-MM-DD.md

Progress updates that require no decision should not @mention anyone.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Find worker agents in Nacos that match a task, recommend candidates, and import the administrator's chosen worker. It also supports importing a specified nacos package URI, with worker name confirmation and direct reporting of installation failures.

中文简介正在准备中。当前显示英语简介。

  • Find a suitable worker for an unassigned task
  • Compare Nacos worker candidates before importing
  • Import a worker from a specified nacos package URI
agentscope-ai/AgentTeams57912026年10月17日 更新

Prepare an existing OpenClaw setup for import as an AgentTeams managed Worker. Analyze tool dependencies, adapt role instructions and scheduled jobs, and build a ZIP package containing the configuration and custom image requirements.

中文简介正在准备中。当前显示英语简介。

  • Moving standalone OpenClaw into AgentTeams
  • Reviewing required tool dependencies
  • Adapting role instructions for a Worker
agentscope-ai/AgentTeams57912026年10月17日 更新

Manage communication channels by identifying senders, maintaining trusted contacts, and setting the administrator's primary notification destination. It also covers first contact on a new channel and contacting the administrator across channels, with rules for handling unknown senders.

中文简介正在准备中。当前显示英语简介。

  • Identify who sent a message in a room
  • Add or remove trusted contacts
  • Configure the administrator's primary notification channel
agentscope-ai/AgentTeams57912026年10月17日 更新

Prepare coding tasks for delegation to an authorized agent’s AI command-line tool. Set up and synchronize the workspace, write precise change requests, then review returned changes and run relevant checks before reporting completion.

中文简介正在准备中。当前显示英语简介。

  • Delegating code implementation or bug fixes to an AI CLI
  • Writing coding requests with clear acceptance criteria
  • Reviewing and testing changes returned by a CLI
agentscope-ai/AgentTeams57912026年10月17日 更新

Run AI coding command-line tools on behalf of worker agents using their prepared prompts and workspaces. Detect available tools, configure delegation, return results, and apply supported execution controls such as time budgets and permission settings.

中文简介正在准备中。当前显示英语简介。

  • Running coding tools for worker agents
  • Detecting and selecting available coding CLIs
  • Setting Qwen Code permissions and time budgets
agentscope-ai/AgentTeams57912026年10月17日 更新

Guide agent replies in Matrix chat rooms, including when to mention a coordinator, report completion, raise blockers, or answer questions. The rules limit repetitive acknowledgments and stop exchanges that add no new task, question, or decision.

中文简介正在准备中。当前显示英语简介。

  • Reporting task completion to a coordinator
  • Raising blockers or questions that need action
  • Reducing repetitive acknowledgments
agentscope-ai/AgentTeams57912026年10月17日 更新

查看 agentscope-ai 的全部技能

报告此技能的问题