crewai-multi-agent

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with comprehensive executable examples and good progressive disclosure to real bundle files. Its weakest spot is conciseness, where a few comparison/padded sections could be trimmed without losing value.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and dominated by copy-paste code examples that assume Claude's competence; minor trimming possible in the 'Use alternatives instead' and 'CrewAI vs alternatives' sections and the duplicated pip install, so it sits above the midpoint but below the leanest anchor.	4 / 5
Actionability	Fully executable, copy-paste-ready guidance across the common cases — install/CLI commands, full Agent/Task/Crew Python examples, YAML config, crew.py/main.py, tools, flows, memory, and LLM providers — with specific examples covering each typical use.	5 / 5
Workflow Clarity	Quick start and YAML project layout provide a clear numbered sequence (define agents, define tasks, create crew, execute) with a troubleshooting section; validation/verification checkpoints are only implicit (no 'verify result / check token_usage' step), so it stays at 4 rather than 5.	4 / 5
Progressive Disclosure	Clear overview in SKILL.md with well-signaled one-level-deep references to references/flows.md, references/tools.md, and references/troubleshooting.md (all confirmed present), with bulk detail appropriately split out and easy navigation.	5 / 5
	Total	18 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: it states what the skill does and gives multiple explicit 'Use when...' trigger conditions in third person. It is slightly below top marks on specificity and trigger-term breadth, where a few more concrete actions and synonyms would help.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities ('role-based agent collaboration with memory', 'sequential/hierarchical execution', 'Built without LangChain dependencies'), with only minor gaps in coverage; not quite a comprehensive list of discrete actions so it stays below 5.	4 / 5
Completeness	Explicitly answers both 'what' ('Multi-agent orchestration framework for autonomous AI collaboration... Built without LangChain dependencies for lean, fast execution') and 'when' ('Use when building teams... when you need... or for production workflows...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ('building teams of specialized agents working together', 'role-based agent collaboration with memory', 'production workflows'); a few obvious synonyms like 'crew', 'AI team', or 'autonomous agents' as triggers are missing, so it is above the midpoint but below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (multi-agent orchestration, role-based, LangChain-free) with distinct triggers; minor overlap risk remains with adjacent multi-agent frameworks such as AutoGen/LangGraph, so it does not reach the minimal-conflict anchor of 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/agents/crewai/SKILL.md
Commit: 01ef795

Reviewed: ~18 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

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.