agent-identifier

Create and validate Claude Code agent files with frontmatter and system prompts.

Updated Oct 7, 2022
One-click install
npx skills add https://github.com/tamagusko/linux-cfg --skill agent-identifier-tamagusko
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-identifier
Source: https://github.com/tamagusko/linux-cfg/tree/main/dotfiles/claude/skills/agent-identifier
Command: npx skills add https://github.com/tamagusko/linux-cfg --skill agent-identifier-tamagusko

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Writing Claude Code agents requires precise frontmatter fields, triggering examples, and well-structured system prompts, and mistakes in any of these cause agents to trigger unreliably or behave unpredictably. ## Core Features & Use Cases - Agent File Authoring: Provides the complete agent markdown format covering name, description, model, color, and tools frontmatter fields with validation rules. - Triggering Example Design: Documents the example block format with context, user message, assistant response, and commentary so agents activate at the right moments. - System Prompt Patterns: Supplies reusable templates for analysis, generation, validation, and orchestration agents plus an AI-assisted generation prompt that outputs JSON. - Use Case: When building a plugin that needs a code review agent, use this Skill to generate the frontmatter with triggering examples, write the system prompt, and validate the result with the included script. ## Quick Start Create a Claude Code agent that reviews pull requests for security issues and validate the resulting agent file.

Frequently Asked Questions about agent-identifier

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a Claude Code agent file?

Create a markdown file in the plugin's agents directory with YAML frontmatter containing name, description, model, and color fields, followed by a system prompt written in second person. The description must include triggering conditions and example blocks.

How do I write triggering examples for a Claude Code agent?

Write example blocks containing Context, a user message, an assistant response, and commentary explaining why the agent triggers. Include two to four examples covering explicit requests, proactive triggering, and varied phrasings of the same intent.

What frontmatter fields does a Claude Code agent require?

Agents require name (lowercase with hyphens, 3-50 characters), description with triggering examples, model (inherit, sonnet, opus, or haiku), and color (blue, cyan, green, yellow, magenta, or red). The tools field is optional and restricts tool access.

How do I validate a Claude Code agent file?

Run the included validate-agent.sh script with the agent file path. It checks frontmatter structure, required fields, name format and length, model and color values, system prompt length, and the presence of example blocks.

When should I use an agent instead of a slash command?

Use agents for autonomous multi-step work that Claude triggers based on context, and slash commands for actions the user explicitly invokes. This Skill covers agents only, not command design, hooks, or MCP server setup.