跳到正文
cccskills
免费在 GitHub 公开

channel-management

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。

原文查看原文说明

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.

查看安装方法

适用场景

  • Identify who sent a message in a room
  • Add or remove trusted contacts
  • Configure the administrator's primary notification channel
  • Handle first contact and contact the administrator across channels

包含的文件(4)

  • SKILL.md2.1 KB
  • references/identity-and-contacts.md3.1 KB
  • references/primary-channel.md2.8 KB
  • scripts/manage-primary-channel.sh3.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Channel Management

Manages communication channels, admin identity recognition, trusted contacts, and primary channel configuration.

Gotchas

  • Primary channel cannot be set to "matrix" — Matrix DM is the default fallback. Use --action reset to revert to it
  • Unknown senders in group rooms must be silently ignored — no response at all, until admin explicitly approves them as trusted contacts
  • Trusted contacts must never receive sensitive info — no API keys, tokens, passwords, Worker credentials, or internal config. No management operations either
  • When calling message tool from a Matrix session, you MUST explicitly set channel and target — otherwise the message goes to the current Matrix room instead of the primary channel
  • to field in primary-channel.json maps to target parameter in message tool — pass the value directly, no transformation needed
  • First-contact protocol: always ask in admin's language — match the language they used in their message
  • Task dispatch must go to Worker Room, not admin DM — when assigning tasks to Workers, use the task-management skill's send protocol (runtime-aware: agt get managers -o json for runtime, then message tool or copaw channels send per finite/infinite references). Never embed @worker task assignments in admin DM replies.

Operation Reference

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

SituationRead
Need to identify who sent a message (admin, worker, trusted contact, unknown)references/identity-and-contacts.md
Add/remove trusted contactsreferences/identity-and-contacts.md
Configure primary channel, send notifications, first-contact protocol, cross-channel escalationreferences/primary-channel.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

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/AgentTeams58602026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/AgentTeams58602026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/AgentTeams58602026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/AgentTeams58602026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/AgentTeams58602026年10月20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/AgentTeams58602026年10月20日 更新

查看 agentscope-ai 的全部技能

报告此技能的问题