AgentTeams
Review Skills in agentscope-ai/AgentTeams, with license, maintenance context, and source paths.
- Skills
- 3
- Repository stars
- 5,500
- Identity status
- Source-linked
Provenance
Source and identity
- Profile type
- Repository
- Canonical name
- AgentTeams
- Public sources
- 1
- License context
- Apache-2.0
Source entries
Agent Skills from AgentTeams
Repository stars and maintenance signals provide context, but do not automatically become an individual Skill's quality score.
agentscope-ai/AgentTeams
task-management
Use before any Leader taskflow call or task-level workflow involving delegating a ready DAG or Loop node, writing task meta/spec, checking a Worker task result, handling result statuses, task directory ownership, or Worker result contracts. Always use this skill when the request mentions delegate_task, check_task, task result.md, task spec.md, BLOCKED, REVISION_NEEDED, INTERRUPTED, SUCCESS, or assigning/delegating a Worker task.
agentscope-ai/AgentTeams
teamharness-communication
Use for TeamHarness message delivery details after a flow has decided a message must be sent: current-session reply, NO_REPLY, cross-room/cross-channel message tool payloads, PROJECT_REQUESTED task-room handoff, and requester replyRoute reports. Do not use to choose work mode, create rooms, delegate, check, or accept tasks.
agentscope-ai/AgentTeams
teamharness-project-management
Use when a Leader maintains durable TeamHarness project state for Quick Task or Project Work: create_quick_project, create_project, plan_dag, plan_loop, ready_nodes, resolve_project, accept_task_result, project completion, and requester report state. Do not use to create Matrix task rooms or send messages.
Pinned paths
Every entry links to a specific source path and commit when available.
Repository context
Activity, license, and repository-level popularity are shown as context.
Open the source
Inspect the public repository