scaffold-ai-app
Scaffold a Veryfront app with AI tools, agent definitions, and knowledge base.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Scaffold a Veryfront app with AI tools, agent definitions, and knowledge base.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Build, test, push, deploy, and verify with rollback through Git on failure.
Build and run AI apps and agents with Veryfront CLI
Development flywheel - autonomous cycle of run, observe, fix, verify. Use for continuous development with browser automation.
Build Veryfront apps. Use for real-time errors, route preview, HMR control, and scaffolding pages/APIs/components/AI tools.
Onboard to veryfront-code architecture, testing, conventions, and PR process.
Diagnose and fix build failures using structured error output.
| name | scaffold-ai-app |
| description | Scaffold a Veryfront app with AI tools, agent definitions, and knowledge base. |
| metadata | {"version":"1.0.0"} |
Create a Veryfront app with AI capabilities: tools, agents, and project conventions.
Create base project
veryfront init <name> --template ai-agent --yes --json
Scaffold AI primitives (via MCP)
Use vf_scaffold to generate project-root primitives:
agents/<name>.ts for reusable agent behaviortools/<name>.ts for callable capabilitiesprompts/<name>.ts for prompt templatesworkflows/<name>.ts for multi-step coordinationAdd an app route
Use vf_scaffold with type: "api" to add a route such as
app/api/ag-ui/route.ts, then wire it to the agent runtime.
Configure inference
Set the model provider token required by the project in .env.
Verify
veryfront doctor --json
veryfront dev
.env file and ensure the expected token is setvf_get_conventions to check patterns, scaffold manuallysrc/provider/ for supported providers