一键导入
add-team
Scaffold a new Agno multi-agent team with boilerplate, register in main.py, and create docs page
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Scaffold a new Agno multi-agent team with boilerplate, register in main.py, and create docs page
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
Scaffold eval test cases for an agent in backend/evals/test_cases.py, following the TestCase dataclass pattern used by DATA_AGENT_CASES, KNOWLEDGE_AGENT_CASES, and WEB_SEARCH_CASES
Verify all project documentation reflects current codebase state after feature changes
Scaffold a new Agno agent with boilerplate, register in main.py, and add config.yaml entry
Scaffold a new Agno workflow with Steps, Loops, and Conditions, register in main.py, and create docs page
Scaffold a new mise task with correct headers, flags, and conventions
Pre-release validation checklist — verify versions, CI, docs, and Docker before running mise run release
基于 SOC 职业分类
| name | add-team |
| description | Scaffold a new Agno multi-agent team with boilerplate, register in main.py, and create docs page |
| disable-model-invocation | true |
Create a new Agno multi-agent team and integrate it into Apollos AI.
Ask the user for:
coordinate, collaborate, or route)ReasoningTools)Create backend/teams/{id_with_underscores}.py following this pattern:
"""
{Team Name}
{'-' * len(team_name)}
{Description}.
"""
from agno.agent import Agent
from agno.team import Team
from agno.team.team import TeamMode
from agno.tools.reasoning import ReasoningTools
from backend.db import get_postgres_db
from backend.models import get_model
team_db = get_postgres_db()
# Team Members
member_one = Agent(
name="{Member Name}",
role="{role description}",
model=get_model(),
tools=[...],
instructions=[...],
markdown=True,
)
# Team
{variable_name} = Team(
name="{Team Name}",
id="{team-id}",
mode=TeamMode.{mode},
model=get_model(),
db=team_db,
members=[member_one, ...],
tools=[ReasoningTools(add_instructions=True)],
instructions=[...],
markdown=True,
compress_tool_results=True,
max_iterations=5,
store_history_messages=True,
share_member_interactions=True,
num_history_runs=5,
enable_agentic_memory=True,
add_datetime_to_context=True,
)
Key conventions:
get_model() from backend/models.py (never inline model creation)id= (not team_id=), mode=TeamMode.coordinate (not string)TeamMode from agno.team.teammax_iterations to prevent runaway coordination loopscompress_tool_results=True for cost controlmember_timeout and max_interactions_to_share do NOT exist on TeamAdd the import and include in the teams list:
from backend.teams.{module_name} import {variable_name}
agent_os = AgentOS(
teams=[research_team, {variable_name}],
...
)
Add a quick-prompts entry in backend/config.yaml for the new team.
Create docs/teams/{id}.mdx with frontmatter, code example, member table, and feature table.
Add the page to docs/docs.json navigation under the Teams group.
Update these files to reflect the new team:
README.md — Teams tablePROJECT_INDEX.md — Teams section and core modules.serena/memories/project-overview.md — Teams listdocs/agents/overview.mdx — Teams tableTell the user:
backend/teams/{name}.pybackend/main.pybackend/config.yamldocs/teams/{id}.mdxmise run docker:up or docker compose restart