Skip to content

agentsope/SkillAlchemy / skills/agentsop-crewai

agentsop-crewai

Verified

SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation. Use when modeling agent teams with clear roles and task pipelines.

# crewai-sop-skill

SOP-style skill distilled from **CrewAI** (the multi-agent orchestration framework by João Moura / crewAIInc) — intended to guide a coder-agent in deciding **when, how, and when NOT to use CrewAI** for role-based multi-agent systems.

Part of a 7-framework landscape research package (LangGraph, LlamaIndex, DSPy, **CrewAI**, vLLM, Aider, Dify).

## Why this skill exists

CrewAI is the most intuitive multi-agent framework in the ecosystem — role + goal + backstory + task + crew — but it has known structural pitfalls (hierarchical-manager failures, delegation ping-pong, weak observability). This skill packages the decision logic and SOP so an agent doesn't fall into the common traps.

## Layout

```
crewai-sop-skill/
├── SKILL.md                    # main, 400-600 lines, 7 sections
├── README.md                   # you are here
├── references/
│   ├── R1-architecture.md      # Agent/Task/Crew/Process/Flow primitives
│   ├── R2-sop-workflow.md      # Phase 0→4 SOP
│   ├── R3-dilemma-cases.md     # 5 dilemmas with decision rules
│   ├── R4-anti-patterns.md     # 5 AP + boundaries
│   └── R5-ecosystem-context.md # vs LangGraph / AutoGen / Swarm
└── intermediate/
    └── operation_candidates.json
```

## How to use

A coder-agent should read `SKILL.md` first; references provide deeper rationale and cited evidence.

Activate when the user signals: "multi-agent crew", "role-based agents", "researcher + writer + reviewer pipeline", or explicitly mentions CrewAI.

## Quality notes

- All claims cite docs.crewai.com, github.com/crewAIInc/crewAI, community.crewai.com, or named third-party engineering posts
- 5 Dilemma Cases (exceeds ≥3 requirement), each with decision rules
- Web research date: 2026-05; CrewAI version 1.14.5 at time of capture
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall