Task Received
    │
    ├── Create new skill? ───────────────> Workflow 1: Build
    │   └── What type?
    │       ├── Primary (JARVIS-XX) ─────> Full policy skill
    │       ├── Branch (plugin-dev) ─────> Execution skill
    │       └── Domain (category) ───────> Domain knowledge skill
    │
    ├── Adapt marketplace skill? ────────> Workflow 3: Adapt
    │
    ├── Fix existing skill? ─────────────> Workflow 2: Improve
    │
    └── Validate skill? ─────────────────> Validation Checklist

skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   └── description: (required)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Python/Bash)
    ├── references/       - Documentation loaded as needed
    ├── examples/         - Working code examples
    └── assets/           - Files used in output (templates, icons)

---
name: skill-name
description: "This skill [does what]. Use when [conditions]. Triggers: '[trigger1]', '[trigger2]', '[trigger3]'."
---

description: "This skill should be used when the user asks to 'create a hook', 'add a PreToolUse hook', 'validate tool use', or mentions hook events (PreToolUse, PostToolUse, Stop)."

# Wrong: Vague, no triggers
description: "Provides hook guidance."

# Wrong: Not third person
description: "Use this skill when working with hooks."

# Wrong: Missing trigger phrases
description: "Load when user needs hook help."

---
name: [domain]-management
description: "This skill defines [domain] policy for JARVIS. Use when [conditions]. Triggers: '[trigger1]', '[trigger2]', '[trigger3]'."
---

# [Domain] Management - JARVIS-XX

[Core concept in 2-3 sentences explaining what this policy covers]

## Core Concept
[What this domain is about, key principles]

## When to Use This Skill
- [Condition 1]
- [Condition 2]
- [Condition 3]

## Key Structures
[Tables, diagrams, templates]

## Workflows
### Workflow 1: [Name]
1. [Step]
2. [Step]

### Workflow 2: [Name]
1. [Step]
2. [Step]

## Validation Checklist
- [ ] [Check 1]
- [ ] [Check 2]

## Reference Files
- [references/detail.md](references/detail.md) - [Description]

---
name: [domain]-manager
description: "Branch skill for [action]. Use when [conditions]. Triggers: '[trigger1]', '[trigger2]'."
---

# [Domain] Manager - Branch of JARVIS-XX

[What this branch executes]

## Policy Source
**Primary policy**: JARVIS-XX → `.claude/skills/[domain]-management/SKILL.md`

## Quick Decision Tree
[ASCII diagram for routing]

## Workflow 1: [Name]
### Step 1: [Action]
[Details]

### Step 2: [Action]
[Details]

## Validation Checklist
- [ ] [Check 1]
- [ ] [Check 2]

## Common Issues & Fixes
| Issue | Fix |
|-------|-----|
| [Problem] | [Solution] |

## Sync Protocol
[How to sync with Primary]

---
name: [domain]
description: "Domain knowledge for [area]. Use when [conditions]. Triggers: '[trigger1]', '[trigger2]'."
---

# [Domain] Knowledge

## Overview
[What this domain covers]

## Key Concepts
### [Concept 1]
[Explanation]

## Common Operations
```bash
[Example command or code]

### Step 5: Write Main Content

**Word limit**: Under 2000 words

**Writing style**: Imperative form ("Create...", "Validate...", "Check...")

**Required sections:**
1. Title with context (e.g., "- Branch of JARVIS-XX")
2. Core concept or Policy Source
3. When to Use (Primary) or Quick Decision Tree (Branch)
4. Main workflows with numbered steps
5. Validation Checklist
6. Reference Files (if references/ exists)

### Step 6: Create Bundled Resources (if needed)

**scripts/** - Executable utilities:

```bash
# When to include: Same code rewritten repeatedly
# Example: scripts/validate-skill.sh
# Benefits: Token efficient, deterministic

# When to include: Content that would bloat SKILL.md
# Examples: references/patterns.md, references/advanced.md
# Benefits: Loaded only when needed

# When to include: Complete, runnable examples
# Examples: examples/hook-example.sh
# Benefits: Users can copy and adapt

# When to include: Files used in output
# Examples: assets/template.json, assets/logo.png
# Benefits: Used without loading into context

# Read skill
cat skills/[name]/SKILL.md

# Check word count
wc -w skills/[name]/SKILL.md

# Check references
ls skills/[name]/references/

description: "Use this skill when working with hooks."

description: "This skill should be used when the user asks to 'create a hook', 'validate hooks', or mentions PreToolUse/PostToolUse events. Triggers: 'create hook', 'hook validation', 'PreToolUse'."

You should start by reading the configuration file.
The skill is used to create hooks.

Start by reading the configuration file.
Create hooks following these steps.

| Option | Pros | Cons | Use When |
|--------|------|------|----------|
| [A] | [+] | [-] | [Condition] |
| [B] | [+] | [-] | [Condition] |

Task Received
    │
    ├── Condition A? ──> Action 1
    │
    └── Condition B? ──> Action 2

cat marketplace-plugin/skills/[skill]/SKILL.md
ls marketplace-plugin/skills/[skill]/references/

description: "Build production-ready monitoring..."

description: "This skill should be used when setting up monitoring for JARVIS categories, tracking MCP server metrics, or implementing category alerting. Triggers: 'monitoring', 'observability', 'metrics', 'alerts'."

## When to Use This Skill
- Creating monitoring for new JARVIS category
- Setting up MCP server observability
- Implementing cross-category metrics
- Configuring JARVIS-00 dashboards

## Policy Source
**Primary policy**: JARVIS-XX → `.claude/skills/[domain]-management/SKILL.md`