For coding agents
The wizard ends by handing the project to a coding agent, so the project ships with notes — and this site ships as text for the agent that has not run it yet.
The wizard's last step is a handoff. It writes the app, installs a skill for every module you picked and one more that comes with every app, writes the instructions file your agent reads on every session, and then offers to start that agent inside the new project and point it at a setup checklist. The project ships with notes for the same reason it ships with source: whoever continues the work needs what we know about the API's edges, in the place their own CLI looks for it.
That gives you three ways in, depending on what exists yet.
Run the wizard
One command writes the app and installs the skills into the directory your agent reads — one per module, plus chatfuel-update. Node 22.19.0 is the only prerequisite; the wizard installs the agent too if you have neither.
Hand an agent one URL
/SKILL.md is this site written as a skill file — the command, the modules and where to read more. Paste it into an agent before there is a project at all.
Read the docs as text
An index at /docs/llms.txt, everything in one file at /docs/llms-full.txt, and a Markdown twin at every documentation address.
Skills is what lands where, and The handoff is what the wizard writes for the agent to read. Agent skills is why the project is shaped this way rather than generated and left.
Environment variables
Every variable the app reads, which side reads it, what it defaults to, and what it does.
Skills
Fifteen skills — one per module and one for the wizard itself — copied into the directory your coding agent reads, and recorded in the app's lock so a later run can tell its own installs from yours.