taruvi-ai/taruvi
TaruviBase skills and MCP access for building TaruviBase apps: datatables, access policies, functions, storage, secrets, analytics, and Refine frontends.
Backend work on a Taruvi app: provisioning datatables, Cerbos policies, roles, users, buckets, secrets, analytics queries, or raw SQL via the Taruvi MCP server; and authoring Python function bodies that run in the Taruvi function runtime (def main(params, user_data, sdk_client)) for multi-resource cascades, event/cron handlers, public webhooks, and external API calls. Triggers: "create a datatable", "Frictionless schema", "Cerbos policy", "serverless function", "scheduled job", "analytics query", "sdk_client", "Taruvi MCP". Skip for Refine frontend work — use taruvi-refine-providers instead.
Refine.dev frontend work on a Taruvi app: wiring data/storage/app/user providers, authProvider, accessControlProvider; Refine hooks against Taruvi (CRUD, useCustom, useCan, useDataGrid, useForm); building list pages, dashboards, KPI cards, file managers, network-backed autocompletes; calling Taruvi functions and analytics from the frontend; debugging 401/403, token refresh, redirect loops, or permission failures. Triggers: any Refine/React work in a Taruvi project, "build a list page", "add a dashboard", "wire up auth", "dataProvider", "@taruvi/refine-providers", VITE_TARUVI_*. Skip for backend Python, MCP provisioning, schemas, policies, or raw SQL — use taruvi-app-developer instead.
Start or connect a project on TaruviBase: optionally suggest the TaruviBase Refine starter template for a new frontend, confirm the Taruvi MCP connection, and write the app's .env (TARUVI_SITE_URL, TARUVI_APP_SLUG, TARUVI_API_KEY). Triggers: "setup taruvi", "connect taruvi", "configure taruvi", building a new app or frontend on Taruvi/TaruviBase, using Taruvi as the backend for a new project, missing Taruvi tools, missing or wrong TARUVI_* values.