Task Received
    │
    ├── Create new category? ────────────> Workflow 1: Build
    │
    ├── Fix existing category? ──────────> Workflow 2: Improve
    │
    ├── Validate category? ──────────────> Validation Checklist
    │
    ├── Migrate to new standard? ────────> Workflow 3: Migrate
    │
    └── Self-improvement cycle? ─────────> Self-Improvement Process

# Check existing categories
ls -d JARVIS-* | sort -t'-' -k2 -n

# Create all directories at once
mkdir -p JARVIS-XX-Name/{.claude/skills/[name]-management/references,plugins/{orchestrator,dev,bigquery-[name],category-[name]},TASKS}

JARVIS-XX-Category-Name/
├── CLAUDE.md                        <- Category identity (REQUIRED)
├── .claude/
│   ├── settings.json                <- Tool permissions
│   ├── mcp.json                     <- MCP config (Execution layer)
│   └── skills/
│       └── [name]-management/       <- Primary Skill
│           ├── SKILL.md             <- REQUIRED
│           └── references/          <- Optional details
├── plugins/                         <- 4 Plugins (REQUIRED)
│   ├── orchestrator/                <- Shared - task routing
│   ├── dev/                         <- Shared - self-improvement
│   ├── bigquery-[name]/             <- Template - data access
│   └── category-[name]/             <- Unique - domain logic
└── TASKS/                           <- Task tracking
    └── TASK-XX-[name]/
        └── README.md

# JARVIS-XX-CategoryName

## Role
[One sentence describing primary function]

## Responsibilities
- [Key responsibility 1]
- [Key responsibility 2]
- [Key responsibility 3]

## MCP Servers
| Server | Location | Purpose |
|--------|----------|---------|
| vault | VPS | Secrets management |
| supabase-common | CloudRun | Database access |

## Quick Reference
[Most common commands or patterns]

# JARVIS-XX-CategoryName

## Role
[Category's primary function and domain expertise]

## Responsibilities
- [Responsibility 1]
- [Responsibility 2]
- [Responsibility 3]

## MCP Servers
| Server | Location | Purpose |
|--------|----------|---------|
| server1 | VPS/CloudRun/Local | Description |

## Schemas (if database access)
| Schema | Purpose |
|--------|---------|
| schema1 | Description |

## Common Tasks

### Task Type 1
[Step-by-step instructions]

### Task Type 2
[Step-by-step instructions]

## Best Practices
- [Practice 1]
- [Practice 2]

## Integration Points
- **Category XX**: [How they interact]
- **Category YY**: [How they interact]

## Learnings
- [Learning 1 from previous conversations]
- [Learning 2]

## Changelog
- YYYY-MM-DD: [Change description]

# JARVIS-XX-CategoryName

## Role
[Category function] for the JARVIS AI Ecosystem.

## Responsibilities
- Define [domain] policy for all categories
- Maintain [domain] standards
- Support categories in [domain] tasks

## Integration
- **Plugin-dev branch**: [branch-name]
- **Primary Skill**: [skill-name]-management

## Quick Reference
[Most common operations for this category]

# JARVIS-XX-CategoryName

## Role
Control [External System] via MCP with full coverage.

## Responsibilities
- Manage [System] resources
- Automate [System] operations
- Monitor [System] status

## MCP Servers
| Server | Location | Coverage | Purpose |
|--------|----------|----------|---------|
| [name] | CloudRun | 90%+ | [Description] |

## Schemas (BigQuery)
| Schema | Purpose |
|--------|---------|
| jarvis_XX_[name] | [Data stored] |

## Quick Reference
[Most common MCP operations]

{
  "permissions": {
    "allow": [],
    "deny": []
  }
}

{
  "permissions": {
    "allow": [
      "Bash(npm:*)",
      "Bash(git:*)",
      "mcp__vault__*"
    ],
    "deny": [
      "Bash(rm -rf:*)"
    ]
  },
  "mcpServers": {
    "vault": {
      "command": "npx",
      "args": ["-y", "@anthropic/mcp-vault"],
      "env": {
        "VAULT_ADDR": "${VAULT_ADDR}"
      }
    }
  }
}

---
name: [category]-management
description: "This skill [function]. Use when [conditions]. Triggers: '[trigger1]', '[trigger2]'."
---

# [Category] Management - JARVIS-XX

[Core concept in 2-3 sentences]

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

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

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

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

1. Analyze Current State
   ├── Read CLAUDE.md
   ├── Read settings.json
   └── Review recent patterns

2. Identify Improvements
   ├── Missing instructions
   ├── Outdated information
   ├── Permission gaps
   └── New learnings

3. Apply Changes
   ├── Update CLAUDE.md
   ├── Update settings.json
   └── Document changes

4. Validate
   ├── Test configurations
   └── Verify no breakage

# Run category audit
ls -la JARVIS-XX-Name/
cat JARVIS-XX-Name/CLAUDE.md
cat JARVIS-XX-Name/.claude/skills/*/SKILL.md
ls JARVIS-XX-Name/plugins/

# TASK-XX-Category-Improvement

## Date: YYYY-MM-DD

## Changes Made
- [ ] Updated CLAUDE.md with [changes]
- [ ] Added missing [component]
- [ ] Fixed [issue]

## Validation
- [ ] All checks pass
- [ ] Tested functionality

bigquery.jarvis_analytics.
├── jarvis_XX_conversations    # Conversation logs
├── jarvis_XX_improvements     # Improvement history
└── jarvis_XX_metrics          # Performance metrics