跳到正文
cccskills
免费在 GitHub 公开

task-management

Use when admin gives a task to delegate to a Worker, when a Worker reports task completion, when managing recurring scheduled tasks, or when you need to check worker availability.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(8)

  • SKILL.md2.3 KB
  • references/finite-tasks.md5.8 KB
  • references/infinite-tasks.md2.3 KB
  • references/state-management.md1.6 KB
  • references/worker-selection.md3.7 KB
  • scripts/find-worker.sh4.3 KB
  • scripts/manage-state.sh9.7 KB
  • scripts/resolve-notify-channel.sh1.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Task Management

Gotchas

  • Don't let Workers hallucinate on unfamiliar domains — when a task involves niche frameworks, complex APIs, or domain-specific workflows that the Worker likely lacks knowledge about, include a suggestion to use find-skills to search for relevant skills first. Skipping this leads to hallucinated code and wasted iterations
  • Delegation-first — always prefer assigning to a Worker over doing it yourself. Only self-execute when admin explicitly says "do it yourself" or the task is within your management skills
  • Never @mention a Worker after recording infinite task execution — this creates a rapid-fire loop (execute → report → trigger → execute → ...) that burns tokens continuously. Triggering happens only during heartbeat
  • Always use manage-state.sh to modify state.json — never edit manually with jq. The script handles atomicity, deduplication, and initialization
  • Every task assigned to a Worker MUST be registered in state.json — this includes coordination, research, review, and management tasks, not just coding tasks. If a task is missing from state.json, the Worker's container will be auto-stopped by idle timeout while still working
  • Always push task files to MinIO before notifying Worker — Worker needs to file-sync to get the spec
  • Always pull task directory from MinIO before reading results — Worker pushes results there
  • Read SOUL.md before composing notifications — use the persona and language defined there
  • Infinite task status is always "active", never "completed" — they repeat until explicitly cancelled

Operation Reference

Read the relevant doc before executing. Do not load all of them.

SituationRead
Admin gives task, no Worker specifiedreferences/worker-selection.md
Assign a one-off task or handle completionreferences/finite-tasks.md
Create or manage a recurring scheduled taskreferences/infinite-tasks.md
Need to update state.json or resolve notification channelreferences/state-management.md

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

Use as a helper when the admin is assigning work but has not specified an existing Worker, so you need to search Nacos for a suitable Worker and ask whether to import it; also use when the admin explicitly says to import a Worker from the market or gives a direct nacos package URI.

中文简介正在准备中。当前显示原文说明。

agentscope-ai/AgentTeams57852026年10月17日 更新

Analyze current OpenClaw setup and generate a migration package (ZIP) for importing into AgentTeams as a managed Worker

中文简介正在准备中。当前显示原文说明。

agentscope-ai/AgentTeams57852026年10月17日 更新

Use when determining sender identity in any room, managing trusted contacts, configuring the admin's primary notification channel, handling first-contact from a new channel, or escalating to admin across channels.

中文简介正在准备中。当前显示原文说明。

agentscope-ai/AgentTeams57852026年10月17日 更新

将编码工作委托给持有 CLI 的 agent(Manager / Leader / 获授权 Worker)的 AI CLI 工具(Claude Code / Gemini CLI / qodercli / Qwen Code / OpenCode)执行

中文简介正在准备中。当前显示原文说明。

agentscope-ai/AgentTeams57852026年10月17日 更新

Execute AI coding CLI tools (Claude Code / Gemini CLI / qodercli / Qwen Code / OpenCode) on behalf of Workers. Use when a Worker sends a coding-request: message, asking the delegating agent (Manager, team Leader, or an authorized Worker) to run coding operations in their workspace.

中文简介正在准备中。当前显示原文说明。

agentscope-ai/AgentTeams57852026年10月17日 更新

Use before sending @mentions, deciding whether to reply, TASK_COMPLETED, BLOCKED, QUESTION, direct answers, loop prevention, or suppressing low-information acknowledgements.

中文简介正在准备中。当前显示原文说明。

agentscope-ai/AgentTeams57852026年10月17日 更新

查看 agentscope-ai 的全部技能

报告此技能的问题