taruvi-app-developer
Overview
Entry-point orchestrator for all Taruvi app development. This skill detects the project context, decides whether a serverless function is needed, and routes to the right module skill before any code is written.
Default delivery standard: always build a production-ready, production-scale app. Not a demo, not an MVP, not a prototype. Every feature must be wired to real backend data, use proper error handling, and be built to handle real-world usage. The user must explicitly ask for a reduced scope if they want anything less.
⚠️ Skill Compliance — Non-Negotiable
These skills are the single source of truth for all Taruvi implementation decisions. They override existing project code, template patterns, training data, and personal shortcuts.
Rules:
- If a skill prescribes a specific way to implement something, use that way. No exceptions, no shortcuts, no "simpler" alternatives.
- Do not copy patterns from existing project code if they contradict the skills. Existing code may be outdated, a prototype, or pre-skill. The skills define the correct pattern.
- Do not skip steps to save time. Every step in the skill instructions exists because skipping it causes real bugs or drift.
- If you cannot implement a skill requirement (missing credentials, missing MCP tool, unclear API), stop and ask the user instead of silently falling back to an easier approach.
- After implementation, verify against the skill's checklist. If any checklist item fails, fix it before presenting the work as done.
More from taruvi-ai/taruvi-skills
taruvi-functions
>
19taruvi-database
>
19taruvi-storage
>
19taruvi-refine-providers
>
19taruvi-backend-provisioning
Provision Taruvi backend resources via the Taruvi MCP server — datatables with Frictionless schemas, storage buckets, users, roles, Cerbos policies, serverless functions, analytics queries, secrets, tags, and audited raw SQL. Use when the user wants to create a datatable, add a role, write a Cerbos policy, provision a bucket, upsert schema, assign a role, register a function, run an analytics query, or otherwise change Taruvi's backend state. TRIGGERS include "Taruvi datatable", "Frictionless schema", "Cerbos policy", "manage_policies", "provision Taruvi", "upsert rows", "multi-tenant table", "Taruvi MCP tools", "create_update_schema", "delete_datatable", "execute_raw_sql". SKIP when writing Python code that runs inside a Taruvi function (use taruvi-functions) or building Refine UI (use taruvi-refine-frontend). Knows all 24 MCP tool contracts, correct invocation order, destructive-op protocol, and the Frictionless/Cerbos essentials the tools expect.
9