5.9 KiB
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
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.
Gitea (Git Server - DO NOT INSTALL LOCALLY)
⚠️ CRITICAL: Gitea runs on a SEPARATE MACHINE (192.168.1.128). Do NOT install it on Matt's Mac.
Server Location: http://192.168.1.128:3000 (NOT localhost:3000)
- Login: ai-agent / !7883Gitea
- Organization: TopDogLabs
- All repos go under: http://192.168.1.128:3000/TopDogLabs/
Using Gitea
Clone existing repo:
git clone http://192.168.1.128:3000/TopDogLabs/repo-name.git
Push to Gitea:
git push origin main
# Enter username: ai-agent
# Enter password: !7883Gitea
Create new repo via web:
- Go to http://192.168.1.128:3000
- Login as ai-agent
- Click + → New Repository
- Owner: TopDogLabs
- Name: [project-name]
NEVER do this:
- ❌
brew install giteaon Matt's Mac - ❌ Run
gitea weblocally - ❌ Use port 3000 for anything (it's for Next.js dev)
Folders for All Content/Projects
- Location: /Users/mattbruce/Documents/Projects/OpenClaw
- Documents: /Users/mattbruce/Documents/Projects/OpenClaw/Documents
- iOS: /Users/mattbruce/Documents/Projects/OpenClaw/iOS
- Web: /Users/mattbruce/Documents/Projects/OpenClaw/Web
Blog Backup
- Location: /Users/mattbruce/Documents/Projects/OpenClaw/Web/blog-backup
- Live URL: https://blog-backup-two.vercel.app
- Local Dev: http://localhost:3002
- Stack: Next.js + Supabase + Vercel
- Deploy:
npm run build && vercel --prod(no GitHub, CLI only) - Features: Daily digest blog with tag filtering, search, responsive design
Mission Control
- Location: /Users/mattbruce/Documents/Projects/OpenClaw/Web/mission-control
- Live URL: https://mission-control-rho-pink.vercel.app/
- Local Dev: http://localhost:3001
- Stack: Next.js + Vercel
- Deploy:
npm run build && vercel --prod(no GitHub, CLI only)
Heartbeat Monitor
- Location: /Users/mattbruce/Documents/Projects/OpenClaw/Web/heartbeat-monitor
- Local Dev: http://localhost:3005
- Stack: Next.js + Vercel
Gantt Board
- Location: /Users/mattbruce/Documents/Projects/OpenClaw/Web/gantt-board
- Live URL: https://gantt-board.vercel.app
- Login: mbruce+max@topdoglabs.com / !7883Gantt
- Local Dev: http://localhost:3000
- Stack: Next.js + Supabase + Vercel
- Deploy:
npm run build && vercel --prod(no GitHub, CLI only)
CLI Access (Create Tasks Directly)
Location: /Users/mattbruce/Documents/Projects/OpenClaw/Web/gantt-board/scripts/gantt-task-crud.sh
Create Task:
cd /Users/mattbruce/Documents/Projects/OpenClaw/Web/gantt-board
./scripts/gantt-task-crud.sh create "Task Title" todo high a1b2c3d4-0001-0000-0000-000000000001 9c29cc99-81a1-4e75-8dff-cd7cc5ceb5aa task
Parameters:
title- Task title (required)status- open, todo, in-progress, review, validate, donepriority- low, medium, high, urgentproject_id- Default: a1b2c3d4-0001-0000-0000-000000000001assignee_id- Default: 9c29cc99-81a1-4e75-8dff-cd7cc5ceb5aa (Max)type- task, idea, bug, research, plan
Other Commands:
./scripts/gantt-task-crud.sh list # List all tasks
./scripts/gantt-task-crud.sh list todo # List todo tasks
./scripts/gantt-task-crud.sh get <task-id> # Get specific task
./scripts/gantt-task-crud.sh update <id> status done # Update task status
./scripts/gantt-task-crud.sh delete <task-id> # Delete task
Note: The CLI uses Supabase service role key for direct DB access. Description, tags, and sprint assignment must be added via the web UI after creation.
Supabase for Gantt Board
- URL: https://qnatchrjlpehiijwtreh.supabase.co
- Project ID: qnatchrjlpehiijwtreh
User IDs for Gantt Board
- Matt: 0a3e400c-3932-48ae-9b65-f3f9c6f26fe9
- Max: 9c29cc99-81a1-4e75-8dff-cd7cc5ceb5aa
Tavily AI Search (Configured)
API Key: Stored in .env.tavily (auto-loaded)
Quick Commands:
# Search
cd ~/.openclaw/workspace && ./tavily-search.sh "query" -n 5
# Extract URL content
cd ~/.openclaw/workspace && ./tavily-extract.sh "https://example.com"
# Deep research
cd ~/.openclaw/workspace && ./tavily-search.sh "query" --deep
Note: API key is automatically loaded from .env.tavily. No need to export manually.
Daily Digest Failsafe System
Cron Job: Daily Digest - 7am CST (America/Chicago)
Status: ✅ Fixed and monitored
Last Posted: 2026-02-23
What I Fixed:
- ✅ Wrong API key in cron job (was
cron_daily_digest_2025, nowdaily-digest-2026-secure-key) - ✅ Added retry logic (3 attempts with 30s delay)
- ✅ Enabled notifications on failure
- ✅ Added backup file creation on failure (
memory/YYYY-MM-DD-digest-failed.md)
If It Fails:
- You will get notified immediately
- Digest content saved to
memory/folder - Can be manually posted or I can fix it
Manual Posting (Emergency):
curl -X POST "https://blog-backup-two.vercel.app/api/digest" \
-H "Content-Type: application/json" \
-H "x-api-key: daily-digest-2026-secure-key" \
-d '{"date": "2026-02-23", "content": "...", "tags": [...]}'
Add whatever helps you do your job. This is your cheat sheet.