Ask opencode-mastery: "What is the correct frontmatter structure for a command?"
Ask opencode-mastery: "What permissions can I set on a skill?"
Ask opencode-mastery: "What fields are required in agent metadata?"
Ask opencode-mastery: "How should I format the description for an agent?"
Ask opencode-mastery: "What are the differences between commands and skills?"

User: Create a skill for React development

Meta-Agent:
1. Analyze: Need to create a skill
2. [Internal Check]: Do I remember exact skill frontmatter structure?
3. [If unsure]: Ask opencode-mastery about skill frontmatter
4. Get answer: name, description, permissions, compatibility, metadata fields
5. Generate: Create SKILL.md with correct frontmatter
6. Write: Save to .opencode/skill/react-dev/SKILL.md

---
name: {{command-name}}
description: {{Short, keyword-rich description of what the command does}}
{{#if arguments}}
arguments:
  - name: {{arg-name}}
    description: {{What this argument is for}}
    required: {{true|false}}
{{/if}}
---

# {{Command Name}}

{{Brief description of what this command does}}

## Usage

`/{{command-name}} {{arg1}} {{arg2}}`

## What It Does

{{Detailed explanation of command behavior}}

## Arguments

{{#if arguments}}
| Argument | Type | Required | Description |
|----------|------|----------|-------------|
| {{arg1}} | {{type}} | {{yes/no}} | {{description}} |
| {{arg2}} | {{type}} | {{yes/no}} | {{description}} |
{{/if}}
{{^if arguments}}
*No arguments*
{{/if}}

## Examples

## Notes

{{Additional context, tips, or warnings}}

---
name: {{skill-name}}
description: {{Keyword-rich description for semantic matching}}
license: MIT
{{#if compatibility}}
compatibility: {{opencode|global|project}}
{{/if}}
{{#if metadata}}
metadata:
  author: {{author-name}}
  version: {{x.y.z}}
  refresh: {{weekly|daily|never}}
  {{#if paths}}
  paths:
    docs: {{path/to/docs}}
    memory: {{path/to/memory}}
    scripts: {{path/to/scripts}}
  {{/if}}
{{/if}}
{{#if permissions}}
permissions:
  - {{permission-type}}
{{/if}}
{{#if compatibility}}
compatibility: {{opencode}}
{{/if}}
---

# {{Skill Name}}

{{Purpose of this skill - what expertise it provides}}

## Quick Navigation

{{Ask user about these specific topics using bullets}}

## What This Skill Does

{{Detailed explanation of skill capabilities}}

## How I Work

### When Invoked

{{Explain what happens when this skill is triggered}}

### What I Can Help With

{{Bullet list of specific capabilities}}

## Resources & References

{{List any external resources, APIs, or docs}}

## Key Concepts

{{Explain important concepts relevant to this skill}}

## Examples

{{Show example questions and how this skill answers them}}

## Notes

{{Additional context, constraints, or best practices}}

---
name: {{agent-name-kebab-case}}
description: |
  Expert {{ROLE}} for {{DOMAIN}}. Use proactively {{SITUATION}}.

  When you prompt this agent:
  - Remember: NO context from previous conversations
  - Provide all relevant context
  - Specify focus area or files
color: {{blue|red|green|yellow|purple|orange|pink|cyan}}
tools: {{Read, Write, Edit, Grep, Glob, Bash, etc.}}
---

# Purpose

You are a {{ROLE}} for {{DOMAIN}}.

## Instructions

When invoked:
1. {{Step 1 - what to do first}}
2. {{Step 2 - what to do next}}
3. {{Step 3 - final steps}}

## Constraints

- You respond to PRIMARY AGENT, not user
- You have NO context from previous conversations
- Only use: {{allowed tools}}

## Report Format

When complete, respond with:
1. Summary of what was done
2. File locations (if applicable)
3. Next steps (if applicable)

## Best Practices

- {{Best practice 1}}
- {{Best practice 2}}

User request
    ↓
What is X?
    ↓
┌─────────────┬─────────────┬─────────────┐
│             │             │             │
│ Tool/Action │ Knowledge   │ Expert      │
│             │             │             │
▼             ▼             ▼
Command       Skill         Agent
              │             │
              │             ├─ Sub-agent
              │             └─ Primary agent
              │
              ├─ Simple skill
              └─ Mastery skill (with scripts/docs)

User: Create a code reviewer that checks for security issues

Meta-Agent:
1. Analyze: This is a specialized expert for security code review
2. Decision: Agent (responds to primary agent, needs tools)
3. Generate: Create `.opencode/agents/security-reviewer.md`
4. Result: Agent with security expertise, Read/Grep/Bash tools

User: Create a command to format all Python files

Meta-Agent:
1. Analyze: This is a specific, repeatable action
2. Decision: Command (user invokes explicitly)
3. Generate: Create `.opencode/commands/format-python.md`
4. Result: Command with `/format-python [path]` syntax

User: Create a skill for Kubernetes troubleshooting

Meta-Agent:
1. Analyze: This is knowledge/expertise with flexible interaction
2. Decision: Skill (semantic matching, full context)
3. [Check]: What frontmatter fields for skills?
4. [Consult]: Ask opencode-mastery about skill frontmatter
5. [Get]: name, description, permissions, compatibility, metadata
6. Generate: Create `.opencode/skill/k8s-troubleshoot/SKILL.md`
7. Result: Skill with k8s keywords and troubleshooting guidance

User: Create an agent for database migration

Meta-Agent:
1. Analyze: Specialized task, needs specific tools
2. Decision: Agent (primary agent delegation)
3. [Check]: What fields are required in agent metadata?
4. [Consult]: Ask opencode-mastery about agent structure
5. [Get]: name, description, color, tools frontmatter
6. Generate: Create `.opencode/agents/db-migrator.md`
7. Result: Agent with database migration expertise, SQL/Bash tools