Expert at creating and modifying Claude Code agents (subagents). Auto-invokes when the user wants to create, update, modify, enhance, validate, or standardize agents, or when modifying agent YAML frontmatter fields (especially 'model', 'tools', 'description'), needs help designing agent architecture, or wants to understand agent capabilities. Also auto-invokes proactively when Claude is about to write agent files (*/agents/*.md), create modular agent architectures, or implement tasks that involv
SkillScore95Maintained
Automatic
◆AI Engineer pack
Last verified 8/18/2026
What it changes
Passed 21 of 22 test cases with the skill, and 11 of 22 without it.
Without skill50%
With skill95%
Checks it passed that the model alone missed
Includes Read, Grep, Glob in the tools list for file inspection.
Recommends including an explicit examples section in the agent body.
Identifies validate-agent.py as the script for validating agent files.
and 10 more in the full report
10 fixed11 passed either way1 still failing0 broke
Pass-rate lift
+45 pp
Tokens
+165%
Agent turns
0%
Response time
-51%
Model gemini-3.6-flashMeasured 8/18/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
I'm setting up an agent frontmatter block. I listed the tools as:
```yaml
tools:
- Read
- Grep
- Glob
```
Is this YAML list syntax the expected format for Claude Code agents?
What was checked, without and with the skill
Checked
Without skill
With skill
Specifies that the tools field must be formatted as a single comma-separated string.
Missed
Passed
case-05 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md506 linessingle file
Building Agents Skill
You are an expert at creating Claude Code agents (subagents). Agents are specialized assistants that handle delegated tasks with independent context and dedicated resources.
When to Create an Agent vs Other Components
Use an AGENT when:
The task requires specialized, focused expertise
You need independent context and isolation from the main conversation
The task involves heavy computation or long-running operations
You want explicit invocation rather than automatic activation
The task benefits from dedicated tool permissions
Use a SKILL instead when:
You want automatic, context-aware assistance
The expertise should be "always on" and auto-invoked
You need progressive disclosure of context
Use a COMMAND instead when:
The user explicitly triggers a specific workflow
You need parameterized inputs via command arguments
Agent Schema & Structure
File Location
Project-level: .claude/agents/agent-name.md
User-level: ~/.claude/agents/agent-name.md
Plugin-level: plugin-dir/agents/agent-name.md
File Format
Single Markdown file with YAML frontmatter and Markdown body.
Required Fields
---
name: agent-name # Unique identifier (lowercase-hyphens, max 64 chars)
description: Brief description of what the agent does and when to use it (max 1024 chars)
---