Guide a non-technical user through creating a leaf (a computation) on their Lettuce head: turning their code into a compute binary or container that honors the Lettuce contract, hosting it on the head, then creating, configuring, activating the leaf and generating work units. The agent does the technical work itself and asks the user only for what to compute, which parameters to sweep, and screenshots/approvals, one step at a time, verifying each. Use when the user wants to create a leaf, set up or run a computation/job/experiment on Lettuce, get their code running on volunteers, or add a computation to their head.
Help a researcher translate a domain wish ("I want to simulate X" / "I want to know whether Y") into a concrete Lettuce-shaped computation spec — choose the model, define parameters that vary across work units, define the output schema, pick a validation strategy, and pick a runtime — before any code is written. Produces a leaf-spec.md document the `create-lettuce-leaf` skill consumes. Use whenever a user arrives with a research question rather than a runnable method; trigger phrases include "I want to compute…", "I want to simulate…", "I want a leaf that does…", "help me design a leaf", "what should my leaf look like".
Guide a non-technical user through deploying a Lettuce head (server) end to end: provisioning a server, pointing a domain, generating secrets, the Docker Compose deploy, and verification. The agent does everything it can itself over SSH and asks the user only for human-only steps (server signup, domain, DNS, screenshots), one step at a time, verifying each before moving on. Use when the user wants to deploy, set up, stand up, install, or host a Lettuce server or head.