leionion/clawforge/openclaw-skill

OpenClaw Skill Forge — Demand Decomposition for OpenClaw

When a user describes what they want in natural language, use OpenClaw Skill Forge to decompose the demand into atomic meta skills, then execute or hand off.

When to Use

• User says: "backup my chat memory", "run a backtest on my data", "organize my files"
• Multi-step or ambiguous demands that need skill mapping
• Before executing—decompose first to route correctly

How It Works

1. Decompose: Call OpenClaw Skill Forge Cutter with the user's demand.
2. Skills returned: e.g. memory_backup, strategy_backtest, file_copy, etc.
3. Runnable standalone: memory_backup, strategy_backtest run via metaskill CLI.
4. Needs OpenClaw: Mac HCI, device, other skills—use OpenClaw's native skills.

Usage

CLI (recommended)

# Install: pip install -e /path/to/ClawForge
metaskill "backup my chat memory"
metaskill "run backtest on trading data" --decompose-only
metaskill --list

Python API

from core.cutter import CutterEngine
result = CutterEngine().process("backup my chat memory")
# result["decomposed"] → [{"skill": "memory_backup", "confidence": 0.8, ...}]

LLM Decomposition (optional)

Set CHUTES_API_KEY in .env and use --model chutes for smarter decomposition.

Cutter Keywords

Installation

cd ClawForge
pip install -e .
 
# Install into OpenClaw workspace (or run ./scripts/setup_openclaw.sh)
cp -r openclaw-skill ~/.openclaw/workspace/skills/metaskillbase

Permissions

• filesystem: For memory_backup, strategy_backtest (read/write CSVs, backups)
• network: Optional for strategy_backtest (data fetch), GPT decomposition
• shell: Run metaskill CLI from OpenClaw