Create a new Claude Code agent with proper YAML frontmatter structure. Use when the user wants to add a specialized agent to a plugin. Handles agent file creation with name, description, tools, model selection, and color configuration.
Install with Tessl CLI
npx tessl i github:jpoutrin/product-forge --skill create-agent82
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Create new Claude Code agents with proper configuration and structure.
Agents are markdown files in the agents/ directory with YAML frontmatter:
---
name: agent-name
description: Full description of what the agent does and when to use it
tools: Glob, Grep, Read, Write, Edit, Bash, WebFetch, WebSearch, TodoWrite
model: sonnet
color: green
---
# Agent Title
Agent prompt content goes here...| Field | Description | Example |
|---|---|---|
name | Unique identifier (kebab-case) | code-reviewer |
description | One-line summary of agent's purpose | Reviews code for quality and best practices |
tools | Comma-separated list of available tools | Glob, Grep, Read, Write, Edit, Bash |
model | Model to use: opus, sonnet, or haiku | sonnet |
color | Status line color | green, blue, purple, red, orange, cyan, magenta, yellow, pink, teal, violet |
Common tool combinations by agent type:
Glob, Grep, Read, Write, Edit, Bash, TodoWriteGlob, Grep, Read, WebFetch, WebSearch, TodoWriteGlob, Grep, Read, Write, Edit, Bash, WebFetch, WebSearch, TodoWriteplugins/<plugin-name>/agents/<agent-name>.md---
name: code-reviewer
description: Reviews code changes for quality, security, and best practices. Use when user wants code reviewed, needs security audit, or asks about code quality.
tools: Glob, Grep, Read, TodoWrite
model: sonnet
color: yellow
---
# Code Reviewer Agent
You are an expert code reviewer focused on quality, security, and maintainability.
## Review Checklist
- Code correctness and logic
- Security vulnerabilities
- Performance considerations
- Code style and consistency
- Test coverage
- Documentation
## Output Format
Provide structured feedback with:
1. Summary of changes
2. Issues found (categorized by severity)
3. Recommendations
4. Approval status0ebe7ae
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.