feat: add crewai — expert skill for role-based multi-agent orchestration #81

Closed
opened 2026-07-09 14:40:35 -04:00 by jasper · 1 comment
Contributor

Summary

Add a crewai expert skill for role-based multi-agent orchestration. CrewAI provides a higher-level abstraction than LangGraph for multi-agent scenarios: agents are defined as Roles with Goals and Backstories, crews are composed with built-in sequential/hierarchical/collaborative workflow patterns, and inter-agent delegation is built into the framework.

Why This Skill

Our LangChain skills cover agent creation and our LangGraph skill covers low-level state-machine graphs. Neither provides the role-based crew abstraction that CrewAI specializes in — where "give each agent a role and a goal" is the mental model, not "define nodes and edges." This is a meaningfully different abstraction layer.

Scope

  • Deep research: CrewAI architecture (Agent, Task, Crew, Process), role-based agents, tool integration, sequential vs hierarchical processes, manager agents, human input
  • Vault notes: atoms + molecules on CrewAI paradigm, agent roles, crew composition, process types
  • Expert skill: SKILL.md + references (agent design, crew patterns, tool integration, callbacks), templates (research crew, writing crew, hierarchical crew), scripts
  • Greenfield SkillOpt: 3 epochs
  • PR: Single PR

Key References

Routing Guide Placement

Add rows to the Framework Routing Guide:

  • "Role-based multi-agent teams" → CrewAI
  • "Hierarchical agent workflows with built-in delegation" → CrewAI

Acceptance Criteria

  • Deep research pyramid
  • Vault clipping + 20+ atoms + 4 molecules
  • Agent skill with 7+ references, 3+ templates, 1+ script
  • Greenfield SkillOpt 3 epochs
  • PR merged to main
## Summary Add a **crewai** expert skill for role-based multi-agent orchestration. CrewAI provides a higher-level abstraction than LangGraph for multi-agent scenarios: agents are defined as Roles with Goals and Backstories, crews are composed with built-in sequential/hierarchical/collaborative workflow patterns, and inter-agent delegation is built into the framework. ## Why This Skill Our LangChain skills cover agent creation and our LangGraph skill covers low-level state-machine graphs. Neither provides the role-based crew abstraction that CrewAI specializes in — where "give each agent a role and a goal" is the mental model, not "define nodes and edges." This is a meaningfully different abstraction layer. ## Scope - **Deep research:** CrewAI architecture (Agent, Task, Crew, Process), role-based agents, tool integration, sequential vs hierarchical processes, manager agents, human input - **Vault notes:** atoms + molecules on CrewAI paradigm, agent roles, crew composition, process types - **Expert skill:** SKILL.md + references (agent design, crew patterns, tool integration, callbacks), templates (research crew, writing crew, hierarchical crew), scripts - **Greenfield SkillOpt:** 3 epochs - **PR:** Single PR ## Key References - https://docs.crewai.com — official docs - https://github.com/crewAIInc/crewAI — GitHub ## Routing Guide Placement Add rows to the Framework Routing Guide: - "Role-based multi-agent teams" → CrewAI - "Hierarchical agent workflows with built-in delegation" → CrewAI ## Acceptance Criteria - [ ] Deep research pyramid - [ ] Vault clipping + 20+ atoms + 4 molecules - [ ] Agent skill with 7+ references, 3+ templates, 1+ script - [ ] Greenfield SkillOpt 3 epochs - [ ] PR merged to main
Author
Contributor

Resolved by merged PR #85: #85

Filed by Jasper (AI agent on behalf of Magnus Hedemark)

Resolved by merged PR #85: https://git.brandyapple.com/magnus/agent-skills/pulls/85 Filed by Jasper (AI agent on behalf of Magnus Hedemark)
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
magnus/agent-skills#81
No description provided.