vizra-ai/vizra-adk/vizra-agent-creation
Claude Code and agent skill by vizra-ai/vizra-adk
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Create AI agents with Vizra ADK - includes patterns for customer service, data analysis, and content generation agents
Install
npx vskill@latest install vizra-ai/vizra-adk/vizra-agent-creationSKILL.md
Creating Vizra ADK Agents
Vizra ADK agents are AI-powered Laravel classes that can reason, use tools, and maintain memory. All agents must extend BaseLlmAgent.
Agent Class Structure
Every agent MUST follow this structure:
Key Rules
- Naming Convention:
- Class name MUST end with
Agent - The
$nameproperty must be unique and in snake_case - Place agents in
App\Agentsnamespace
- Auto-Discovery:
- Agents are automatically discovered - NO registration needed
- Simply create the class and it's ready to use
- Required Properties:
$name: Unique identifier$description: Brief description$instructions: System prompt for the LLM$model: Which LLM model to use
Common Agent Patterns
Customer Service Agent
Data Analysis Agent
Creative Content Agent
Using Your Agent
Basic Execution
Advanced Execution Options
Sub-Agent Delegation
Agents can delegate to other agents using the DelegateToSubAgentTool:
Model Selection Guide
Choose the appropriate model based on your needs:
- GPT-4o: Best for complex reasoning, tool use, and general tasks
- GPT-4o-mini: Cost-effective for simpler tasks
- Claude-3-Opus: Excellent for creative writing and analysis
- Claude-3-Sonnet: Balanced performance and cost
- Gemini-Pro: Good for multi-modal tasks
- Gemini-Flash: Fast responses for simple queries
Testing Your Agent
Common Mistakes to Avoid
- Don't forget to extend BaseLlmAgent - Your agent won't work without it
- Don't use duplicate agent names - Each $name must be unique
- Don't hardcode sensitive data - Use environment variables
- Don't make instructions too vague - Be specific about the agent's role
- Don't forget to include required tools - Agents need tools to interact with systems
Artisan Commands
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingresources/boost/skills/vizra-agent-creation/SKILL.md
Popularity
- Repository stars
- 290
- Repository forks
- 36
- 7-day trend score
- 28
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 1 Apr 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/vizra-ai/vizra-adk/vizra-agent-creation)