skill-priority-setup

# Skill Priority Setup

Automated skill tiering and injection policy configuration for OpenClaw.

## What This Skill Does

1. **Discovery Phase**: Scans all installed skills across standard directories
2. **Analysis Phase**: Suggests L0-L3 tier assignments based on skill characteristics
3. **Configuration Phase**: Applies the tiered architecture to your setup
4. **Validation Phase**: Verifies configuration and estimates token savings

## Quick Start

```bash
# Run the interactive setup wizard
python3 ~/.openclaw/workspace/skills/skill-priority-setup/scripts/setup.py

# Or non-interactive mode with defaults
python3 ~/.openclaw/workspace/skills/skill-priority-setup/scripts/setup.py --auto
```

## When to Use

- **New Setup**: Just installed multiple skills and want optimal configuration
- **Performance Issues**: High token usage or slow responses
- **Migration**: Upgrading from flat skill structure to tiered architecture
- **Audit**: Reviewing and optimizing existing skill priorities

## Architecture Overview

This skill implements a 4-tier priority system:

### L0 - ROM Core (Always Active)
- `semantic-system`: Semantic routing (message injector)
- `agent-evolution`: Self-improvement behaviors (SOUL.md)
- `config-modification`: Config safety (on-demand)
- `skill-safe-install`: Installation safety (on-demand)

### L1 - Routing Layer (Task-Triggered)
- `browser-automation`: Web automation
- `find-skills`: Skill discovery
- `teamtask`: Multi-agent coordination

### L2 - Domain Skills (Keyword-Triggered)
- Document: `word-docx`, `tesseract-ocr`
- Media: `youtube-transcript`
- Platform: `discord`, `wechat-suite`, `evomap`
- Automation: `automation-workflows`

### L3 - Extensions (Manual/On-Demand)
- Third-party integrations: `notion`, `slack`, `github`, etc.

## Workflow

```
┌─────────────────┐
│ 1. Scan Skills  │ → Find all SKILL.md files
└────────┬────────┘
         ▼
┌─────────────────┐
│ 2. Analyze      │ → Detect skill types & dependencies
└────────┬────────┘...

# Skill Priority Setup - Package Summary

## Files Created

```
skill-priority-setup/
├── SKILL.md                      # Main skill definition
├── clawhub.yaml                  # ClawHub publishing metadata
├── README.docx                   # DOCX format README
├── README.md                     # This file
└── scripts/
    ├── setup.py                  # Main setup wizard
    └── generate_docx.py          # DOCX generator
```

## What This Package Does

1. **Scans** all installed skills in standard directories
2. **Analyzes** skill types and dependencies
3. **Suggests** L0-L3 tier assignments
4. **Configures** injection policy for optimal token usage
5. **Validates** configuration and creates backups

## Key Features

- **4-Tier Architecture**: L0 (ROM) → L1 (Routing) → L2 (Domain) → L3 (Extensions)
- **Token Budget Control**: ≤900 tokens/round with overflow protection
- **Interactive Wizard**: Review and modify suggestions before applying
- **Safety First**: Automatic backups, dry-run mode, JSON validation
- **Customizable**: Configurable tier patterns and budgets

## Usage Flow

```
User runs setup.py
    ↓
System scans installed skills
    ↓
Analyzes and suggests L0-L3 tiers
    ↓
User reviews/modifies suggestions
    ↓
Applies configuration
    ↓
Validates and reports token savings
```

## For ClawHub Users

This skill is designed to be **adaptive**:
- Works with any skill collection
- Analyzes YOUR specific installed skills
- Provides customized tier suggestions
- Non-destructive (backups always created)

## Post-Install

After running setup.py, your system will have:
- `SKILL_PRIORITY_POLICY.md` - Your custom policy
- Updated `AGENTS.md` - ROM constraints
- Updated message injector config
- Backups in `~/.openclaw/backup/`

## ClawHub URL

**Published at**: https://clawhub.ai/halfmoon82/skill-priority-setup

## Upload to ClawHub

```bash
# Method 1: CLI (if authenticated)
npx clawhub publish

# Method 2: Manual upload
# 1. Download skill-priority-setup-v1.0.0...