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

79%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/llm-tools/crewai/SKILL.md

Quality

Content

75%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.

A highly actionable, well-structured skill body with comprehensive executable examples and real, clearly signaled references. It is held back by redundancy between the Quick Start and Core Concepts sections and inline scaffolding that could be externalized.

Suggestions

De-duplicate the Agent/Task/Crew definitions: keep a single concise example in Quick Start and reference Core Concepts for the full parameter surface instead of re-listing overlapping constructors.

Move the complete YAML project scaffold (agents.yaml, tasks.yaml, crew.py, main.py) into a reference file, leaving a minimal skeleton inline with a link.

Isolate time-sensitive values like the model id 'claude-sonnet-4-5-20250929' and 'Version: 1.2.0+' into a dedicated section or note so they can be updated without touching instructional content.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but the Quick Start and Core Concepts sections redundantly redefine Agent, Task, and Crew with overlapping parameters, and a dated model id ('claude-sonnet-4-5-20250929') is inlined rather than isolated.	3 / 5
Actionability	Copious copy-paste-ready, executable code covering the common cases—installation, CLI, agents, tasks, crews, flows, tools, memory, LLMs, and full YAML project scaffolding.	5 / 5
Workflow Clarity	A clear install→create→run sequence is present with a troubleshooting section, though validation checkpoints are only implicit; the core crew-kickoff operation is not destructive, so the missing-feedback cap does not apply.	4 / 5
Progressive Disclosure	Well-signaled one-level-deep references (flows.md, tools.md, troubleshooting.md—all verified to exist) with clean section headers, but the full crew.py/main.py scaffold and YAML configs are inlined where they could be split into references.	4 / 5
	Total	16 / 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.

A strong description that answers both what and when with concrete trigger phrases and natural keywords. The main limitation is modest overlap risk with competing multi-agent frameworks.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ('role-based agent collaboration with memory', 'sequential/hierarchical execution', 'Built without LangChain dependencies') rather than vague abstractions, though framed as features more than discrete actions.	4 / 5
Completeness	Clearly states what it is ('Multi-agent orchestration framework for autonomous AI collaboration') and explicitly answers when to use it via a 'Use when...' clause with multiple concrete trigger conditions.	5 / 5
Trigger Term Quality	Natural phrases a user would say ('teams of specialized agents', 'agent collaboration', 'production workflows') appear with an explicit 'Use when' clause, though some synonyms like 'autonomous agents' are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a fairly distinct role-based crew niche and self-differentiates from LangChain, but 'multi-agent'/'agent collaboration' triggers still overlap with AutoGen and LangGraph skills.	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: synthetic-sciences/openscience
Path: backend/cli/skills/llm-tools/crewai/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.