TOOLS.md - Local Notes

Skills define how tools work. This file is for your specifics — the stuff that's unique to your setup.

What Goes Here

Things like:

• Camera names and locations
• SSH hosts and aliases
• Preferred voices for TTS
• Speaker/room names
• Device nicknames
• Anything environment-specific

Examples

### Cameras

- living-room → Main area, 180° wide angle
- front-door → Entrance, motion-triggered

### SSH

- home-server → 192.168.1.100, user: admin

### TTS

- Preferred voice: "Nova" (warm, slightly British)
- Default speaker: Kitchen HomePod

Image Generation

• Provider: FAL.ai
• API Key: 190c152a-f9b2-4042-b88d-14308e8b6685:0b77c943a163fd2613827bf20d82c403
• Model: fal-ai/flux/dev (quality) | fal-ai/flux/schnell (speed)
• Usage: os.environ["FAL_KEY"] = "<key>" then fal_client.run(...)
• Install: pip3 install fal-client

Voice Transcription

• Script: /workspace/tools/transcribe.sh <audio-file>
• Model: Whisper small (accuracy > speed)
• Use for all inbound voice notes before processing
• If transcript is unclear/short, flag to Munya and ask to resend as text
• Known limitation: short clips (<5s) and heavy accents reduce accuracy

Collaboration Dashboard

• URL: http://localhost:9999
• Dashboard: http://localhost:9999/ — live task tracker (auto-refresh 15s)
• Files: http://localhost:9999/files — browse all workspace files
• Plugins: http://localhost:9999/plugins — built plugin suite
• View any file: http://localhost:9999/view/[relative-path]
• Auto-starts on login. Restart: cd ~/.openclaw/workspace/dashboard-server && node server.js
• This is the primary way to share artifacts with Munya — always link here, never dump raw text

Why Separate?

Skills are shared. Your setup is yours. Keeping them apart means you can update skills without losing your notes, and share skills without leaking your infrastructure.

Add whatever helps you do your job. This is your cheat sheet.