본문으로 건너뛰기
cccskills
무료GitHub에 공개

human-management

Manage human accounts in AgentTeams by adding users, assigning one of three permission levels, and choosing which agents they can contact. It also covers listing accounts, updating permissions, and removing access.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Use when admin requests adding a human user to the system, changing human permissions, removing human access, or managing human accounts.

설치 방법 보기

이럴 때 유용합니다

  • Add a team member to AgentTeams
  • Limit an external collaborator to selected Workers
  • Update a user's permissions
  • List human accounts or remove access

포함된 파일(3)

  • SKILL.md1.9 KB
  • references/create-human.md1.0 KB
  • scripts/create-human.sh1.2 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Human Management

Import real human accounts into AgentTeams with configurable permission levels. Humans use their own Matrix client (Element) to communicate with agents.

Permission Levels (inclusive — higher includes all lower)

LevelCan talk toUse case
1Manager + all Team Leaders + all Workers (= Admin equivalent)CTO, tech lead
2Specified Team Leaders + their Workers + specified standalone WorkersTeam member, PM
3Specified Workers onlyExternal collaborator

Quick Create

bash /opt/agentteams/agent/skills/human-management/scripts/create-human.sh \
  --matrix-id "@john:domain" --name "John Doe" \
  --level 2 --teams alpha-team --workers standalone-dev \
  --email john@example.com

Full workflow: read references/create-human.md

Gotchas

  • Humans don't need containers, MinIO, or Higress — they only need Matrix room access and groupAllowFrom entries
  • Email is optional but recommended — if provided, a welcome email with credentials is sent automatically
  • Matrix account is registered automatically — username from --matrix-id, random password generated
  • Level 1 humans get access to everything — --teams and --workers are ignored
  • Level 3 humans ignore --teams — only --workers matters
  • Changing permission level requires recalculating all groupAllowFrom — use create-human.sh with --update flag

Operation Reference

Admin wants to...ReadKey script
Add a human userreferences/create-human.mdscripts/create-human.sh
List/query humans—agt get humans
Remove human access—agt delete human <name>

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • 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/AgentTeams5.8천2026년 10월 17일 업데이트

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Moving standalone OpenClaw into AgentTeams
  • Reviewing required tool dependencies
  • Adapting role instructions for a Worker
agentscope-ai/AgentTeams5.8천2026년 10월 17일 업데이트

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Identify who sent a message in a room
  • Add or remove trusted contacts
  • Configure the administrator's primary notification channel
agentscope-ai/AgentTeams5.8천2026년 10월 17일 업데이트

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • 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/AgentTeams5.8천2026년 10월 17일 업데이트

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Running coding tools for worker agents
  • Detecting and selecting available coding CLIs
  • Setting Qwen Code permissions and time budgets
agentscope-ai/AgentTeams5.8천2026년 10월 17일 업데이트

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.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Reporting task completion to a coordinator
  • Raising blockers or questions that need action
  • Reducing repetitive acknowledgments
agentscope-ai/AgentTeams5.8천2026년 10월 17일 업데이트

agentscope-ai의 스킬 모두 보기

이 스킬의 문제 신고