How to organize folders, run automations, and deploy your code — a visual breakdown of the complete workflow.
How you organize your code, configs, and documentation in the workspace.
How your automations actually run — scheduled, event-driven, or always-on.
How your changes go live — in-place, via CI/CD, or packaged as a skill.
Everything lives under one root directory. Four top-level folders, each with a clear purpose.
Each project gets its own subfolder with src, config, tests, and scripts.
Only if packaging as a reusable Skill — contains SKILL.md + scripts.
Runbooks, docker-compose files, systemd configs. How to run & recover.
MEMORY.md and context files. Not app code — assistant memory only.
Every project follows the same clean layout. Predictable structure = fewer mistakes.
The single source of truth. What it does, how to install, how to run. Always write this first.
Templates, schemas, non-secret configuration. Everything that shapes behavior without being code.
The actual application code. Keep it clean, modular, and well-commented.
Use environment variables, .env files (gitignored), or a secret store. Never commit API keys.
Pick the right execution model based on what triggers your automation.
Runs on a schedule. Best for daily summaries, periodic syncs, monitoring.
"When X happens, do Y." Triggered by messages, webhooks, or platform events.
Always-on server. Best for webhooks, queues, background workers, APIs.
Match the execution model to what kicks off your automation.
Daily reports, weekly summaries, data syncs, monitoring checks, reminder systems
Chat commands, Telegram bots, Discord handlers, notification routing
API endpoints, webhook receivers, background job workers, real-time pipelines
Three paths from code to production. Pick based on your team size and project maturity.
Code lives directly on the server. Update by pulling and restarting.
Push to GitHub → CI builds image → deploys automatically to VPS.
Package as a skill folder. Version it. Deploy by updating the skill.
Regardless of which option you pick, the flow follows the same pattern.
The bot's answer describes a VPS environment. Here's how Cowork compares.
Create proposals, clean pages, sync data, scheduled tasks
Build in Cowork → deploy to Netlify
Always-on listener, webhook receiver, message handler
PPTX, DOCX, PDF, HTML decks, data analysis
REST APIs, payment webhooks, data pipelines
Answer these and you'll have a complete setup plan in minutes.
Once you pick, the bot (or Cowork) can scaffold the exact folder structure + first runnable automation for you.