Agent Skills
Native SDK ships its agent guidance as skills: curated, versioned SKILL.md documents that the CLI delivers to coding agents.
An agent should not assume it knows the Native SDK from general model knowledge. A skill closes that gap: it travels with the CLI, so the guidance an agent reads always matches the toolkit version it is building against — not whatever the model remembers.
Install for your agent
One command sets an agent up:
npx skills add vercel-labs/nativeIt installs the Native SDK discovery skill into your agent's skills directory: a compact entry point that orients the agent and teaches it to load the full, version-matched skill content from the installed CLI with the native skills commands below. Install once — because the deep guidance is always read from the CLI, the agent stays current with whatever toolkit version each project uses.
Getting skills from the CLI
The CLI itself serves the full skill content. This is the layer the installed discovery skill reads from, and the direct path when you want to print a skill or deliver one by hand — it needs nothing beyond the installed CLI, so it also works offline:
native skills list # list built-in skills
native skills get core # print a skill
native skills get core --full # include its reference files
native skills get --all [--full] # print every skillskills get prints the skill to stdout, so delivering one to an agent is a single redirect into wherever your agent loads skills from:
mkdir -p .claude/skills/native-ui
native skills get native-ui > .claude/skills/native-ui/SKILL.mdnative init does not copy skills into the workspace — delivery is always explicit, so the skill in the workspace is exactly what the installed CLI serves. The repository's own eval harness gives fresh agents the native-ui skill this same way before grading what they build.
What ships
core- The shared foundation: the mental model, project structure,
app.zon, App and Runtime patterns, frontend integration, web engines, the JavaScript bridge, permissions, windows, WebViews, dialogs, packaging, debugging, and testing.--fullappends its five reference files (project anatomy, App/Runtime patterns, frontend assets, web engines/packaging/debugging, bridge/security/native capabilities). native-ui- Authoring native-rendered apps:
.nativemarkup views, bindings and message dispatch,Model/Msg/updateon theUiApploop, testing markup views, hot reload, and verifying the result through the automation harness. automation- Driving and verifying a running app through
native automate: snapshots, readiness waits, assertions, bridge round-trips, and smoke tests.
Skills in the agent workflow
AI is part of the workflow: the same declarative views and single typed update function that keep apps easy for people to reason about make them reliable for agents to generate. Skills supply the knowledge half of that loop, and the automation server supplies the verification half — an agent reads the skill, builds with the CLI verbs, and then sees and drives the running window to check its own work.