CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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 verified progressive disclosure to real reference files. Its main weaknesses are mild verbosity/marketing padding and the absence of explicit validation checkpoints in the core workflow.

Suggestions

Trim marketing-fluff bullets ('50+ tools', 'Production-ready: Tracing, enterprise features') and remove obvious inline comments ('# Web search') to tighten conciseness toward a lean 3.

Add an explicit verification checkpoint to the quick-start workflow, e.g. inspect result.tasks_output and validate expected_output before treating the crew run as complete.

Fix the repeated 'Synthetic Sciencestion' typo in the tags and H1 title, which reads as padding rather than deliberate content.

DimensionReasoningScore

Conciseness

Mostly efficient and executable, but padded with marketing-fluff bullets ('50+ tools', 'Production-ready: Tracing, enterprise features'), repeated Crew() examples, and basic inline comments ('# Web search', '# Task 1 → Task 2') that could be tightened.

2 / 3

Actionability

Provides copy-paste-ready executable Python (Agent, Task, Crew, Process), CLI commands (crewai create/run), pip installs, full YAML config, and a working Flow example.

3 / 3

Workflow Clarity

The quick-start sequence (install → create → install deps → run) is present and Common issues give fixes, but the core build-run workflow lacks explicit validation checkpoints or a verify-before-proceeding feedback loop.

2 / 3

Progressive Disclosure

Overview body points to well-signaled one-level-deep references (flows.md, tools.md, troubleshooting.md) that all exist as real files, with a dedicated References section for easy navigation.

3 / 3

Total

10

/

12

Passed

Description

100%

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 states concrete capabilities, provides explicit 'Use when' triggers, and distinguishes the skill from adjacent frameworks. Slight risk of jargon ('orchestration', 'hierarchical execution') but natural trigger phrases keep it effective.

DimensionReasoningScore

Specificity

Enumerates multiple concrete capabilities (role-based agent collaboration with memory, sequential/hierarchical execution, no-LangChain lean execution) rather than a single vague domain, matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what ('Multi-agent orchestration framework for autonomous AI collaboration') and when via an explicit 'Use when...' clause with multiple triggers.

3 / 3

Trigger Term Quality

Includes natural user phrases ('building teams of specialized agents working together on complex tasks', 'production workflows') with good coverage, despite some jargon ('orchestration framework', 'hierarchical execution').

3 / 3

Distinctiveness Conflict Risk

Carves a clear niche through role-based/sequential-hierarchical framing and the 'Built without LangChain dependencies' distinction, making it unlikely to trigger for the wrong skill.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
synthetic-sciences/openscience
Reviewed

Table of Contents

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.