Use when you act as Leader to turn ready Quick Task or Project Work state into Worker task instructions, send assignment messages, check submitted results, and define completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow involves checking submitted Worker task results via `check_task`, which ingests outsider-authored task results and deliverables from shared task directories.
agentscope-ai/AgentTeams
8a661dd
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.