Create Agent
Skill Verified ActiveComprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns
To provide developers with a comprehensive and structured guide for creating high-quality Claude Code agents, ensuring proper formatting, triggering conditions, and system prompt design based on best practices.
Features
- Guides agent creation with proper structure
- Defines triggering conditions and system prompts
- Includes validation rules and scripts
- Provides detailed frontmatter field reference
- Offers prompt engineering and agent design principles
Use Cases
- Creating new Claude Code agents with defined roles and responsibilities
- Structuring agent configurations according to Anthropic's best practices
- Ensuring agents are triggered correctly based on user intent and context
- Refining existing agent prompts for better performance and clarity
Non-Goals
- Developing the actual agent logic beyond its configuration structure
- Providing a runtime environment for agents
- Managing the lifecycle of deployed agents
Installation
First, add the marketplace
/plugin marketplace add NeoLabHQ/context-engineering-kit/plugin install customaize-agent@context-engineering-kitQuality Score
VerifiedTrust Signals
Similar Extensions
Create Command
100Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
Validate Plugin
100Validate a Claude Code plugin structure, frontmatter, and MCP tool references
Running Claude Code Via Litellm Copilot
100Use when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.
Guard
100Protect Claude Code sessions from context overflow by running a background daemon that monitors session size and auto-prunes before compaction hits. Use when the user says "guard", "protect session", "context getting long", "prevent compaction", "session management", or is running agent teams that need continuous context protection.
Rule Effectiveness Analysis
100Analyze which rules are actively used vs inert. Detect coverage gaps. Recommend pruning to reduce token consumption.
Bootstrap Project
100Initializes the Claude Code configuration in a new or existing project using the dotforge template.