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.

51

Quality

56%

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-claude/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 body is a well-organized, code-forward CrewAI pattern reference, but it is held back by a truncated code block, undefined variables in the hierarchical example, and some redundant prose. Workflow clarity is mid-range because it is a pattern catalog without sequenced validation steps.

Suggestions

Complete the truncated Basic Crew crew.py example (the @task writing_task method is cut off mid-line) so all code blocks are copy-paste ready.

Define or instantiate the task objects (research_task, analysis_task, writing_task) referenced in the hierarchical example, or note that they are defined elsewhere.

Trim the redundant intro paragraph (it duplicates the frontmatter description) and replace the generic 'When to Use' sentence with concrete trigger conditions.

DimensionReasoningScore

Conciseness

Mostly efficient with code-forward patterns, but the intro paragraph repeats the frontmatter description and several code comments restate concepts Claude already knows ('# Manager decides: Which agent handles which task'); the generic 'When to Use' filler ('applicable to execute the workflow or actions described in the overview') adds nothing. Not a 4 because multiple padding spots could be trimmed.

3 / 5

Actionability

Provides concrete, mostly-executable YAML and Python examples, but the first crew.py example is truncated mid-line ('return Task(config') and the hierarchical example references undefined tasks (research_task, analysis_task, writing_task). Not a 4 because the broken/incomplete code blocks prevent copy-paste readiness.

3 / 5

Workflow Clarity

Each pattern carries a 'When to use' label, which is helpful, but this is a pattern catalog rather than a sequenced workflow, and there are no validation/checkpoint steps for the crew-building process. Not a 4 because no explicit sequence or checkpoints are present.

3 / 5

Progressive Disclosure

Single self-contained file (no bundle directories exist) organized with clear section headers (Capabilities, Requirements, Patterns, Anti-Patterns, Limitations, Related Skills) and per-pattern 'When to use' labels. Not a 5 because ~240 lines of inlined code examples could arguably be split into reference files, though the structure is solid.

4 / 5

Total

13

/

20

Passed

Description

58%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 conveys concrete CrewAI-specific actions and is clearly distinct, but it omits any explicit 'Use when...' trigger guidance and relies on framework jargon over natural user phrasings. This caps completeness at 3 and leaves trigger term coverage at the mid-range.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when building CrewAI multi-agent crews, defining agent personas, or orchestrating sequential/hierarchical workflows.'

Broaden trigger terms with user-natural synonyms like 'multi-agent framework', 'agent orchestration', and 'agent crew'.

Reflect the full capability set (memory configuration, tool integration, Flows) to lift specificity from good to comprehensive.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'design clear agent personas with specific expertise', 'create well-defined tasks with expected outputs', 'orchestrate crews for optimal collaboration' — giving good coverage of the CrewAI design domain with only minor gaps (e.g., memory/flows mentioned in body but not description). Not a 5 because coverage is not comprehensive across the full capability set.

4 / 5

Completeness

Has a clear 'what' (designing agent teams, personas, tasks, crews) but no explicit 'when' / 'Use when...' clause, so per the rubric guideline completeness is capped at 3. Not a 4 because the trigger guidance is entirely missing rather than merely weak.

3 / 5

Trigger Term Quality

Includes the key natural term 'CrewAI' plus 'agent teams', 'crews', and 'agent personas', but misses common variations a user might say ('multi-agent framework', 'agent orchestration') and leans on jargon ('roles, responsibilities, delegation'). Not a 4 because several natural phrasings users would actually invoke are absent.

3 / 5

Distinctiveness Conflict Risk

The named framework 'CrewAI' gives it a clear, distinct niche with minimal conflict risk, though it overlaps slightly with related agent skills (langgraph, autonomous-agents). Not a 5 because those adjacent multi-agent skills share conceptual triggers.

4 / 5

Total

14

/

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.