跳到正文
cccskills
免费在 GitHub 公开

file-sharing

Coordinate shared files using local team and global input paths. The skill explains project refreshes, task file ownership, and missing-file troubleshooting, while identifying task directory transfers already handled by delegation and result checking.

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 filesync calls for project directories, global-shared inputs, non-task shared files, listing shared paths, or troubleshooting missing files. Do not use for task-level sync; taskflow delegate_task and check_task handle task directory sync internally.

查看安装方法

适用场景

  • Refresh project files after a restart
  • Give workers local paths to task specifications
  • Check who writes and reads each task file
  • Investigate shared files a worker cannot find

包含的文件(1)

  • SKILL.md2.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

File Sharing

Use this skill for shared files. Do not expose storage internals to Workers.

Local Abstraction

Use local shared paths only:

  • Team work: shared/...
  • Manager/global input: global-shared/...

Directory sync paths must end with /, especially shared/projects/{project-id}/ and shared/tasks/{task-id}/. If a directory pull fails, stop and report the sync failure; do not fall back to partial file pulls and then modify Project state.

Do not write these in chat or task specs:

  • agentteams/agentteams-storage/...
  • teams/{team}/shared/...
  • /root/agentteams-fs/...
  • /root/agentteams-fs/agents/...

Team Task Files

Team task directories use:

shared/tasks/{task-id}/

Ownership:

shared/tasks/{task-id}/
├── meta.json      # Leader creates
├── spec.md        # Leader writes, Worker reads
├── base/          # Leader writes, Worker reads
├── result.md      # Worker writes through its runtime protocol, Leader reads
└── workspace/     # Worker writes

Tell Workers only local paths:

Please read shared/tasks/{task-id}/spec.md and follow your Worker task participation skills.

Task Directory Sync

taskflow handles task directory sync internally:

  • delegate_task auto-pushes shared/tasks/{task-id}/ after creation.
  • check_task auto-pulls shared/tasks/{task-id}/ before reading the result.

Do not call filesync push/pull/stat for task directories during delegation or result checking.

Refresh Project Files

Before using projectflow to inspect an existing project after restart or heartbeat, refresh the project directory:

{
  "action": "pull",
  "payload": {
    "path": "shared/projects/{project-id}/"
  }
}

projectflow reads local files only, so stale project files can produce stale ready-task decisions.

If this project directory pull fails, stop. Do not pull only meta.json or plan.md and continue to update DAG or Loop state.

If Worker Cannot Find Files

Do not argue about absolute paths.

  1. Verify the task was published.
  2. Tell Worker: Please pull shared/tasks/{task-id}/ with filesync, then read shared/tasks/{task-id}/spec.md.
  3. If it still fails after one retry, report a filesync/shared-directory issue.

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/AgentTeams58402026年10月20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/AgentTeams58402026年10月20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/AgentTeams58402026年10月20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/AgentTeams58402026年10月20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/AgentTeams58402026年10月20日 更新

Guides communication in Matrix agent teams by choosing recipients, rooms, and when to mention someone. It covers task notifications and progress reports, helping agents avoid duplicate assignments and send concrete updates to the appropriate requester.

中文简介正在准备中。当前显示英语简介。

  • Choosing the right Matrix room for a report
  • Avoiding duplicate task assignment notifications
  • Deciding when to mention a team member
agentscope-ai/AgentTeams58402026年10月20日 更新

查看 agentscope-ai 的全部技能

报告此技能的问题