Agent Development
Skill ActiveThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
To empower users to effectively create and develop autonomous agents for Claude Code plugins by providing clear instructions, examples, and best practices for agent structure and behavior.
Features
- Guidance on agent file structure and frontmatter
- Detailed instructions for system prompt design
- Explanation of AI-assisted and manual agent creation
- Validation rules for agent components
- Best practices for agent testing and organization
Use Cases
- Learning how to structure a new agent
- Understanding how to write effective system prompts
- Generating agent configurations using AI assistance
- Validating agent file syntax and content
- Troubleshooting agent triggering issues
Non-Goals
- Directly creating agents via code execution
- Providing pre-built agent templates
- Handling agent deployment or runtime management
- Developing agents for platforms other than Claude Code plugins
Workflow
- Consult SKILL.md for agent development guidance
- Review frontmatter field definitions
- Understand system prompt structure and best practices
- Utilize AI-assisted or manual agent creation methods
- Validate agent files using provided rules
- Test agent triggering and functionality
Practices
- Agent Design
- Prompt Engineering
- Code Quality
- Testing
Prerequisites
- Understanding of Claude Code plugin architecture
- Access to a development environment for creating agent files
License
- info:License usabilityThe license is only mentioned in the README footer and LICENSE.md, without a SPDX identifier in manifests, making its integration with downstream tools less direct.
Trust
- warning:Issues AttentionThere are 9462 open issues and 22831 closed issues in the last 90 days, indicating a very low closure rate and slow maintainer response.
Versioning
- info:Release ManagementA manifest version (0.1.0) is present, but there are no GitHub release tags or a CHANGELOG.md, and installation instructions reference 'main'.
Installation
First, add the marketplace
/plugin marketplace add anthropics/claude-code/plugin install plugin-dev@claude-code-pluginsQuality Score
Trust Signals
Similar Extensions
Create Command
100Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration
Write A Skill
100Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Plugin Authoring
100Use when creating, modifying, or debugging Claude Code plugins. Triggers on .claude-plugin/, plugin.json, marketplace.json, commands/, agents/, skills/, hooks/ directories. Provides schemas, templates, validation workflows, and troubleshooting.
Context Engineering
99Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.
Agent Evaluation
99Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.
Project Development
100This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture, agent-assisted development, cost estimation, or choosing between LLM and traditional approaches.