CtrlK
BlogDocsLog inGet started
Tessl Logo

crewai

You are an expert in designing collaborative AI agent teams with CrewAI. You think in terms of roles, responsibilities, and delegation. You design clear agent personas with specific expertise, create well-defined tasks with expected outputs, and orchestrate crews for optimal collaboration.

49

Quality

53%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/crewai/SKILL.md

The canonical home for this skill is crewai in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

53%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 content is well-structured and offers useful CrewAI patterns, but its main code example is truncated, secondary examples have undefined references and missing imports, and the intro/'When to Use' sections add filler. These gaps hold most dimensions at the midpoint.

Suggestions

Complete the truncated basic-crew code block so it is copy-paste runnable (finish the writing_task return and the crew definition).

Fix the hierarchical example to import/define ChatOpenAI and the referenced research_task/analysis_task objects, or note them as defined-elsewhere.

Replace the verbatim intro repetition and the vague 'When to Use' filler with a concise purpose line and concrete triggering scenarios.

DimensionReasoningScore

Conciseness

The intro paragraph repeats the frontmatter description verbatim and the 'When to Use' section is vague filler ('applicable to execute the workflow... described in the overview'); the body is mostly efficient but could be tightened.

3 / 5

Actionability

Concrete code examples are present, but the primary YAML/crew.py block is truncated mid-line at 'return Task(config', and the hierarchical example references undefined tasks and an un-imported ChatOpenAI, leaving key details missing.

3 / 5

Workflow Clarity

The body is a pattern catalog with 'When to use' labels rather than a sequenced workflow, and no validation checkpoints are shown; the operation is non-destructive so the hard cap does not apply, but checkpoints remain implicit.

3 / 5

Progressive Disclosure

No bundle files exist; the single file is well-organized into clear sections (Capabilities, Patterns, Anti-Patterns, Limitations) with no nested or broken references, leaving only minor organization gaps.

4 / 5

Total

13

/

20

Passed

Description

53%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 clearly states what the skill does and names a distinctive framework, but it is written in second person, lacks an explicit 'Use when...' trigger clause, and leans on jargon over natural user phrasing. These issues keep most dimensions at the midpoint.

Suggestions

Rewrite in third person ('Designs collaborative AI agent teams with CrewAI...') to avoid the voice penalty.

Add an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when building CrewAI crews, designing multi-agent teams, or orchestrating agent workflows').

Include common synonyms users actually say ('multi-agent', 'agent workflow', 'build a crew') alongside the technical terms.

DimensionReasoningScore

Specificity

Names the CrewAI domain and several concrete actions (design agent personas, create tasks with expected outputs, orchestrate crews), but the second-person voice ('You are an expert', 'You design') triggers a one-point specificity penalty per the rubric guidelines.

3 / 5

Completeness

The 'what' is clearly stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Relevant domain keywords appear (CrewAI, AI agent teams, crews, tasks) but the language is jargon-heavy ('orchestrate crews', 'delegation') and misses common natural variations like 'multi-agent' or 'agent workflow'.

3 / 5

Distinctiveness Conflict Risk

CrewAI is a named, specific framework giving it a clear niche, but 'collaborative AI agent teams' overlaps with closely related multi-agent skills (langgraph, autonomous-agents) noted in the body.

4 / 5

Total

13

/

20

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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.