Instantdb Expert — Data & AI agent for Claude Code
Expert in InstantDB realtime database.
How to install Instantdb Expert
Installs to ~/.claude/agents/ivklgn-ai-kit-instantdb-expert.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ivklgn/ai-kit/HEAD/agents/instantdb-expert.md -o ~/.claude/agents/ivklgn-ai-kit-instantdb-expert.md Restart Claude Code, or start a new session, for it to be picked up.
What Instantdb Expert does
name: instantdb-expert description: Expert in InstantDB realtime database. Use for code generation, reviews, optimizations, and type-safe patterns. Consults documentation, checks patterns, and parses GitHub repo for complex issues. tools: Read, Write, Edit, Glob, Grep, WebFetch, WebSearch, mcp__context7__resolve-library-id, mcp__context7__query-docs model: inherit
You are an expert InstantDB developer specializing in realtime database applications with React and React Native. Your goal
Alternatives in Data & AI
- Docs Drift Reviewer — Checks whether clickhouse-go documentation matches changes to its ClickHouse API, database/sql API, transports 3.3k ★
- Migration Agent — Creates safe, reversible database migrations with proper indexes, constraints, and zero-downtime strategies 652 ★
- Kosmos Architect — Senior architect agent for Kosmos codebase analysis 570 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Prose Review
Reviews prose for AI patterns, banned phrases, voice drift, and structural issues. Dispatched by the copydesk
Gsc Structured Data
Site-wide structured-data auditor. Samples URLs from the sitemap, parses every JSON-LD block, and validates re
Vercel AI SDK Expert
Use for Vercel AI SDK v5 implementation work: chat interfaces, tool calling, streaming, agentic loop control,
Baml Expert Agent
Use proactively whenever the user builds, modifies, or debugs BAML (Boundary ML) applications. Do not wait to
Data Science Expert
Principal Data Science engineer specialized in concurrent systems, ML pipelines, deep learning, NLP, scientifi
Code Smells Reviewer
Read-only reviewer that identifies code smells — design issues that aren't bugs but make code harder to mainta
Related Skills
Codex Sidecar
Safe Codex sidecar execution for reviews, codebase exploration, risk checks, and isolated worktree fixes.
Subroutine
A self-hosted, agent-native task and decision tracker for people and coding agents working on complex projects
Manus
Delegate complex tasks to Manus AI agent for deep research, market analysis, product comparisons, stock analys