Category
Agent Teamsrules, skills & MCP servers
Agent teams are multi-agent crews — orchestration graphs where specialized agents hand work to each other under a coordinator. A planner decomposes the task, workers execute in parallel, a reviewer checks the output before it ships. Done well, a team turns a sprawling job into a pipeline you can trust; done badly, the agents talk past each other and produce confident nonsense. The teams below are quality-scored on how clearly each role is defined, how the handoffs are wired, and whether the orchestration actually closes the loop with a verification step. Each crew is attributed to the GitHub author who designed it, so you can study their topology before you adopt it. Importing a vetted team saves you the hardest part of multi-agent work — getting the roles, the routing, and the stopping conditions right — and gives you a structure other engineers have already run. Browse the top agent teams below by quality score, or open the full catalog to filter by framework and the kind of workflow the crew is built to coordinate.
Top agent teams right now
Ranked by quality score — freshness, schema completeness, and review signals. Refreshed daily.
Browse other categories
Rules
Context files, style guides, and coding rules for AI editors.
MCP Servers
Model Context Protocol servers that extend AI capabilities.
Skills
Packaged capabilities your assistant can invoke on demand.
Agents
Autonomous agents and subagents for Claude Code, Cursor, Codex, and frameworks like LangGraph or CrewAI.
Workflows
End-to-end automations for n8n, Make, and similar tools.
Prompts
Hand-tuned system prompts and prompt libraries.
CLIs
Command-line utilities and AI-native shells.
Datasets
Training, evaluation, and retrieval datasets.
Bundles
Curated multi-item packs priced as a single drop.