Build and deploy production-grade LLM applications with LangGraph for agent orchestration, advanced RAG pipelines leveraging vector and hybrid search, prompt engineering patterns, and automated evaluation. Covers embedding model selection, vector index optimization, and multi-agent architectures for document Q&A, chatbots, and semantic search over proprietary data.

Develop and deploy Odoo ERP solutions with custom module scaffolding, ORM operations, security rules, eCommerce and CRM configuration, Docker-based deployment, and performance troubleshooting.

Delegate complex data engineering, ML, and AI workflows to specialized sub-agents that design scalable pipelines, build and optimize models, architect LLM systems, tune databases for performance, and deploy production infrastructure across clouds.

Implement Domain-Driven Design with tactical patterns (aggregates, entities, value objects), CQRS, event sourcing, and saga orchestration. Design bounded contexts, map integration contracts, and build event stores with read models for scalable, event-driven systems.

Build and manage end-to-end data analytics workflows: implement A/B testing with statistical rigor, design reliable analytics tracking, create interactive D3.js visualizations, architect scalable database schemas, and optimize SQL for cloud-native databases.

Write and optimize SQL across data warehouses, profile datasets, and generate interactive dashboards or publication-quality charts from queries or files. Automates data analysis with natural language queries and connects to analytics platforms like Amplitude and Hex.

Manage Firebase projects through Claude: query and write Firestore data, manage authentication users, deploy and invoke Cloud Functions, and handle Storage and Hosting configurations directly from the chat interface.

Generate SQL queries from natural language descriptions using your database schema for PostgreSQL, MySQL, or BigQuery. Analyze CSV or Excel user data to produce cohort retention heatmaps, engagement trends, churn insights, and research recommendations. Evaluate A/B tests for statistical significance, confidence intervals, lift, and ship/extend/stop decisions with Python-powered reports.

Build, secure, scale, and troubleshoot production Supabase apps using 30 skills for Postgres schemas with RLS, auth/realtime/storage integrations, migrations, performance tuning, CI/CD deployments, cost optimization, monitoring, and incident response.

Query SQL databases and tabular files using SLQ or native SQL, manage database sources, inspect schemas, and diff tables from the command line

Analyze slow SQL queries and receive optimized rewrites, index recommendations, execution plan insights, anti-pattern fixes, and performance estimates for PostgreSQL, MySQL, and SQLite databases.

Design normalized relational database schemas for PostgreSQL and MySQL from natural language requirements. Generate DDL statements, constraints, indexes, relationships, migrations, checklists, and Mermaid ERDs following best practices and normalization guidance.

Track crypto portfolios using real-time CoinGecko prices to compute P&L, allocations, risk metrics like Sharpe ratio, volatility, max drawdown, VaR, and correlations. Receive rebalancing recommendations, export data to JSON/CSV, and store positions in PostgreSQL for persistent monitoring and analysis.

Interpret EXPLAIN plans and query metrics from PostgreSQL, MySQL, and MongoDB to detect bottlenecks like sequential scans, missing indexes, and inefficient joins. Receive targeted SQL optimization recommendations with expected performance impacts.

Introspect PostgreSQL, MySQL, SQLite, and MongoDB schemas to generate Markdown documentation and interactive HTML reports with ERD diagrams, relationships, indexes, constraints, views, procedures, and data dictionaries for onboarding, audits, and compliance.

Compare PostgreSQL and MySQL schemas across database environments to generate idempotent migration scripts with transaction safety, validation checks, rollback procedures, and detailed diff reports.

Automate archiving historical PostgreSQL/MySQL records to archive tables or cloud storage (S3, Azure Blob, GCS) using age/status-based rules, retention policies, compression, and compliance tracking to shrink primary database size and manage cold data.

Analyze PostgreSQL, MySQL, and MongoDB query workloads to detect missing indexes causing sequential scans, identify unused indexes, recommend optimal configurations, estimate performance impacts, and generate SQL scripts for index creation and drops.

Audit PostgreSQL, MySQL, and MongoDB databases for security risks including misconfigurations, privileges, encryption, network exposure, default credentials, and SQL injection in app code. Run scans for 50+ OWASP vulnerabilities, generate compliance reports, automated remediation scripts, and audit trails from your IDE.

Design and implement partitioning strategies for PostgreSQL and MySQL tables using range, list, hash, and composite methods to handle massive datasets. Automate schema design, maintenance routines, query optimization, and data retention policies for improved performance.

Automate complete operations for FairDB PostgreSQL SaaS on VPS: onboard customers with database/user provisioning, run health checks on resources/backups/connections, configure pgBackRest for Wasabi S3 backups, execute incident response scripts for restarts/corruption checks, and deploy agents for proactive monitoring/optimization.

Generate, validate with error handling and transactions, and deploy production-ready stored procedures, functions, triggers, and custom logic directly to PostgreSQL, MySQL, or SQL Server databases using natural language triggers or commands.

Scan codebases for SQL injection vulnerabilities by tracing user inputs through code to database queries, identifying unsafe patterns like string concatenation and unparameterized ORM usage in Django, Rails, Express, and Go apps. Get risk reports and mitigation recommendations via skills or direct commands.

Initialize Firestore Admin SDK in Node.js projects with authentication, manage safe CRUD operations batch writes queries schema design data migrations indexes, generate validate production-ready security rules using least privilege and emulator testing, and optimize performance costs.

Build secure Rust applications integrating Azure services: authenticate with Entra ID, manage Key Vault secrets/keys/certificates, perform CRUD on Cosmos DB documents and Blob Storage, and stream data via Event Hubs using official SDK patterns and code examples.

Query and verify Korean statutes, precedents, administrative rules, and treaties by integrating 42 National Law Information Center APIs into 9 unified tools. Includes LLM citation validation to prevent hallucination, article relationship graphs, automatic diff for temporal version comparison, precedent citator status, and a 5-step legal guidance assistant.

Audit PostgreSQL and MySQL databases for integrity issues including NULLs, orphans, invalid formats, ranges, and duplicates, then generate and enforce CHECK constraints, foreign keys, and triggers. Extend validation to application level with type checks, regex patterns, foreign key integrity, and custom business rules.

Introspect PostgreSQL or MySQL schemas to generate ORM models, migrations, and relations for Prisma, Drizzle, TypeORM, Sequelize, SQLAlchemy, and Django ORM. Reverse-generate database schemas from models supporting JavaScript/TypeScript, Python, C#, Java, Ruby, PHP, and more.

Implement disaster recovery and point-in-time recovery (PITR) workflows for PostgreSQL and MySQL databases using WAL archiving, automated backups to S3 or local storage, failover procedures, RPO/RTO planning, testing runbooks, and multi-cloud support for AWS, GCP, Azure.

Design and optimize NoSQL data models for MongoDB, DynamoDB, Redis, and Cassandra by analyzing access patterns, embedding vs referencing, denormalization trade-offs, sharding keys, and indexes.

Configure replication topologies, automate failover, monitor lag, resolve conflicts, and scale read replicas for high-availability setups in PostgreSQL, MySQL, and MongoDB databases.

Manage complete database migration workflows: generate timestamped up/down SQL or ORM files, validate schemas, execute migrations, perform rollbacks, and track evolution with version control for PostgreSQL, MySQL, MongoDB, and SQLite using Flyway, Alembic, Prisma, or Knex.

Generate automated backup scripts, cron schedules, restore procedures, monitoring setups, and recovery plans for PostgreSQL, MySQL, MongoDB, and SQLite databases, including compression, encryption, and retention policies with AWS support.

Generate realistic test data for users, products, orders, technical fields, and custom schemas to populate fixtures, factories, seeds, edge cases, and databases in JS/TS/Python/Ruby apps using Faker.js, Fishery, pytest fixtures, and factory patterns.

Implement trigger-based audit logging for PostgreSQL and MySQL databases to track INSERT, UPDATE, and DELETE operations with metadata for compliance, security monitoring, and debugging. Generate SQL trigger templates, CDC strategies, and application-level logging setups.

Audit database connections, calculate optimal pool sizes, configure app-level pooling parameters, and deploy PgBouncer or ProxySQL for PostgreSQL and MySQL to prevent exhaustion and boost throughput. Implement best practices with code examples for Node.js, Python, and Java.

Automate database testing workflows by generating test suites with data factories, transaction wrappers for automatic rollback, schema validation, assertions, cleanup, fixtures, migrations, integrity checks, and performance monitoring across PostgreSQL, MySQL, MongoDB, SQLite, Redis using Prisma, Drizzle, Jest, Pytest.

Implement multi-tier database caching using Redis for L2 distributed cache, in-memory L1 cache, and CDN layers with cache-aside and write-through patterns, TTLs, and invalidation strategies to reduce database load and boost read performance for PostgreSQL and MySQL setups.

Detect and resolve database deadlocks in PostgreSQL, MySQL, and MongoDB by running lock queries, parsing logs, tracing code, and applying preventive patterns. Generate Python and Node.js monitoring scripts, SQL analyzers, prevention docs, and dashboards for ongoing deadlock management.

Generate realistic, relationally consistent test data and idempotent seed scripts by analyzing database schemas, respecting foreign keys, constraints, and data types with Faker libraries for dev/test environments across JS, Python, C#, Prisma, Node, and TypeScript.

Set up real-time monitoring for database transactions in PostgreSQL, MySQL, and MongoDB to detect long-running queries, lock contention, idle sessions, throughput issues, and rollbacks. Generate Python scripts, SQL queries, and alert configs for automated performance alerting via CLI.

Implement horizontal database sharding for PostgreSQL, MySQL, and MongoDB at massive scale. Select shard keys, analyze data distribution, route queries, rebalance shards, and generate router code, migration plans, and monitoring setups using consistent hashing and virtual nodes.

Monitor PostgreSQL, MySQL, and MongoDB health via CLI queries for connections, throughput, disk usage, cache ratios, and locks. Configure alerting thresholds, receive predictive alerts with remediation guidance, and deploy Grafana dashboards using Prometheus exporters for real-time oversight.

Design optimal ClickHouse schemas with MergeTree engines, ingest data at scale via Node.js/Python clients, run analytical queries, optimize performance and costs, secure deployments with RBAC and quotas, integrate CI/CD testing and monitoring, troubleshoot errors/incidents, and manage migrations/upgrades for production analytics workloads.

Build and manage Snowflake data platforms: connect via Node.js/Python SDKs, ingest data from S3/GCS/Azure stages/Snowpipe, construct ELT pipelines with streams/tasks/dynamic tables, tune query performance/costs/clustering, enforce RBAC/security policies/governance, integrate CI/CD with GitHub Actions/Terraform, set up multi-env/observability, troubleshoot errors/incidents.

Operate FairDB PostgreSQL VPS instances end-to-end: run daily health checks and monitoring, execute P0 incident response playbooks for outages and disk issues, perform SOP-guided setups for secure servers with backups, and audit compliance using autonomous agents.

Profile database queries to detect performance issues like N+1 queries, missing indexes, full table scans, and inefficient joins, generating reports with query inventories, actionable recommendations, CREATE INDEX SQL statements, and before/after examples for quick optimizations.

Delegate specialized AI agents to design cost-optimized cloud architectures on AWS/Azure/GCP using Terraform, administer and optimize PostgreSQL/MySQL/MongoDB databases, troubleshoot DevOps outages with logs/metrics analysis, configure CI/CD pipelines with Docker/Kubernetes, and debug networks with nginx/HAProxy.

Design scalable backend architectures including REST/GraphQL/OpenAPI APIs, server-side logic, database schemas with indexing and Redis caching, OAuth authentication/security, and microservices.

Scaffold and deploy full-stack Cloudflare Workers apps with Hono APIs, Vite+React+Tailwind+shadcn frontends, Drizzle/D1 databases including schemas/migrations/seeds; manage infrastructure via REST API for DNS records, cache purges, WAF rules, R2/KV ops.

Agentically enhance Power BI semantic models in Tabular Editor by generating BPA rules via interactive Q&A or descriptions, executing C# scripts for bulk operations and DAX formatting, searching documentation and CLI syntax, and debugging Dynamic LINQ expressions for validation and CI/CD.

Build and query a local knowledge base for domain-specific projects: store documents, perform semantic searches via embeddings for RAG workflows, and generate automatic summaries using a Node.js MCP server.

Connect to Power BI Desktop's local Analysis Services instance via TOM and ADOMD.NET to enumerate models, run DAX queries, edit metadata, trace queries, and capture live DAX queries from visuals for real-time performance summaries, timings, and CPU usage—no MCP server needed.

Apply 28 prioritized best-practice rules for ClickHouse schema design, query optimization, and data ingestion, with companion skills for running ClickHouse SQL in Python, reviewing schemas and queries, writing Node.js client code, troubleshooting performance issues, and setting up local or cloud ClickHouse environments.

Optimize SQL queries and analyze execution plans in plain English for PostgreSQL, MySQL, SQLite, and SQL Server. Identify costs and bottlenecks, get index suggestions and rewrites, then compare before/after performance using EXPLAIN ANALYZE.

Build persistent data layers in SwiftUI iOS/macOS apps using Boutique: initialize Stores for CRUD on structured data, persist preferences and secrets via @StoredValue/@SecurelyStoredValue, bind reactively to views with onChange and previews, apply Swift 6 concurrency best practices, and test store setups.

Design MongoDB schemas with best patterns and anti-patterns, generate and optimize queries from natural language using schema and indexes, tune client connections across Node.js Python Java Go drivers, implement Atlas full-text vector hybrid search for RAG, provision stream processing pipelines with Kafka S3 Lambda, and configure MCP servers via Docker or Atlas API.

Provides LSP server for SQLite SQL files enabling diagnostics, completions, go-to-definition, hovers, symbol listing, and semantic tokens in your editor. Use companion CLI to format queries, parse AST as tree/JSON, and validate syntax/schema for files, stdin, globs, or embedded SQL in Python/TypeScript.

Design optimized PostgreSQL schemas from business requirements with entity modeling and SQL DDL, generate Node.js migration frameworks with zero-downtime strategies and rollbacks, and optimize performance for PostgreSQL/MySQL by analyzing slow queries, indexes, execution plans, and resource usage.

Perform Five Whys root cause analysis to identify issues and solutions, generate Mermaid ERDs from SQL migrations or database schemas, and follow structured 4-step guides for problem-solving and project building through to deployment.

Generate idempotent Prisma database seed scripts with realistic, reproducible data straight from your schema. Run one command to create scripts that respect foreign keys, include a reset function, and add a package.json npm script for easy population and management of test data in development workflows.

Architect scalable backend systems by designing REST/GraphQL APIs with OpenAPI specs, implementing server-side logic, creating database schemas with indexing and Redis caching, setting up secure OAuth authentication, and planning microservices.

Load, query, and analyze data from files (CSV, Parquet, JSON, Excel, Avro, spatial), S3-compatible storage, or attached DuckDB databases using SQL in Claude Code sessions. Preview schemas/samples without full downloads, convert formats, perform spatial analysis (distances, joins), search docs/session logs, install extensions.

Adds 14 productivity commands, 11 specialized AI agents, up-to-date documentation lookups, Supabase database operations (queries, schema inspection, data manipulation), and browser automation via Playwright for end-to-end testing, screenshots, and content scraping — all in local development workflows.

Provides Oracle Database guidance for writing, editing, debugging, and tuning SQL and PL/SQL; managing schemas, users, roles, and privileges; troubleshooting performance with optimizer plans, AWR, and ASH; and performing migrations, backup, recovery, and security configuration.

Run a local GraphJin MCP server to execute instant GraphQL queries against your PostgreSQL database and explore its full schema directly in Claude Code. Point it at your DB via a simple config file, then query data or introspect structure using natural language prompts—no extra setup needed.

Develop full-stack Supabase apps by configuring local environments and managing migrations, edge functions, secrets with CLI and TypeScript codegen; integrating supabase-js SDK for PostgREST queries, auth, storage uploads, realtime subscriptions; optimizing Postgres with best practices for schema design, query performance, connection pooling, RLS security.

Optimize PostgreSQL and MySQL query performance by running EXPLAIN ANALYZE to identify issues, locks, and patterns, generating structured reports with improvement estimates and suggestions, then applying index recommendations via safe concurrent migrations with redundancy checks.

Generate vector embeddings from text data using OpenAI, Cohere, or local models, store them in a vector database with indexing, and perform semantic similarity searches to retrieve top-K matches with scores, metadata, re-ranking, and deduplication.

Generate realistic test data from schemas or models, respecting constraints, relationships, and locales, then output as JSON, CSV, SQL INSERTs, or fixtures with validation reports. Seed development databases idempotently via transactional scripts that include cleanup and verify inserted counts for Prisma, Django, and SQL databases.

Interactively design database schemas from application requirements, defining entities, relationships, indexes, and constraints while generating SQL DDL and text-based ERDs. Create visual Mermaid ERDs (saved to docs/erd.md) from existing schemas, ORM models, migrations, or live databases, with optional DBML output and counts of tables/relationships.

Automate codebase migrations between framework versions, libraries, or patterns: research changes, apply incremental updates with tests, and get reports on affected files and verifications. Generate reversible database migration files for schema changes across ORMs like Prisma, Drizzle, and Django, including up/down functions, data migrations, validation, and dry-runs.

Generate up/down database migration files for schema changes in Prisma, Django, Rails, and similar tools, including constraints, indexes, data logic, and SQL previews. Safely rollback recent or specific migrations with data loss warnings, transactional execution, schema verification, and status reports.

Build Retrieval-Augmented Generation (RAG) pipelines by indexing documents from directories, URLs, databases, or APIs into vector stores like Pinecone, Weaviate, Chroma, or pgvector using semantic chunking and embeddings, then creating retrievers with hybrid search, re-ranking, caching, citations, fallback handling, and evaluation metrics.

Work with Power BI Project (PBIP) files, TMDL, and PBIR formats directly — rename cascades, validate project structure, fix semantic model metadata, and edit report JSON schemas in source-controlled repos.

Migrate dbt projects from Core to Fusion engine or across data platforms like Snowflake to Databricks by triaging errors as auto-fixable or guided, adapting SQL dialects, and validating fixes with dbt debug, compile, and unit tests.

Manage Notion workspaces from Claude Code: capture chat insights/decisions into structured pages/databases with templates/links; search/query content; create tasks/pages/rows; turn specs into implementation plans with estimates/tracking; prepare meetings with context/research; generate cited research reports.

Develop and manage Tencent CloudBase applications: deploy cloud functions and CloudRun services, query and manage NoSQL/MySQL databases, call AI models (DeepSeek, Hunyuan, etc.), handle authentication and storage, and integrate WeChat Mini Programs — all via MCP.

Architect scalable backend systems using a specialized AI agent: design REST/GraphQL/OpenAPI APIs with authentication and rate limiting, optimize database schemas via indexing and Redis caching, implement secure OAuth flows, build server-side logic, and structure microservices for robustness and performance.

Develop and troubleshoot CDS views, entities, and data models in SAP ABAP (7.4+ to Cloud) using inline references for annotations, associations, parameters, functions, CASE expressions, DCL access control, CURR/QUAN types, ABAP queries, and SALV IDA displays.

Assists developers in writing and refining ABAP code for SAP systems, enabling work with internal tables, structures, ABAP SQL, object-oriented programming, RAP services, CDS views, EML statements, ABAP Cloud patterns, string processing, dynamic programming, RTTI/RTTC, field symbols, data references, exception handling, and unit testing across classic and modern paradigms.

Build production-ready Convex apps using guided skills for realtime React subscriptions, TypeScript schema validation, secure functions and audits, cron jobs, file storage and serving, zero-downtime migrations, HTTP endpoints, and persistent AI agents with tool integration.

Build product metrics frameworks with North Star metrics, KPI trees, and counter-metrics; explain, optimize, and generate SQL queries for PostgreSQL, MySQL, SQLite; create structured dashboard specs including KPIs, charts, and layouts from business questions for BI tools like Looker or Grafana.

Manage Firebase projects from Claude: deploy apps to App Hosting and Hosting, configure Firestore databases and security rules, set up Authentication and Remote Config, build Data Connect backends with PostgreSQL and GraphQL, integrate Gemini AI features, and manage crash reporting with Crashlytics.

Manage AWS data lake and analytics workflows: create and manage S3 Tables (Iceberg), import data from databases and S3, query with Athena, manage Glue connections and catalogs, and store/query vector embeddings with S3 Vectors.

Build RAG pipelines for document Q&A and chatbots by chunking large docs, generating embeddings, storing in vector DBs, and retrieving context to reduce hallucinations. Engineer and optimize LLM prompts using chain-of-thought, few-shot examples, constitutional AI, meta-prompting, and validation workflows.

Delegate complex data analysis tasks to an expert agent that generates optimized SQL queries, executes BigQuery CLI (bq) operations via Bash, handles aggregations and joins, and delivers actionable insights on datasets.

Delegate complex data analysis tasks to an expert agent that crafts optimized SQL queries, executes BigQuery CLI operations via Bash, handles aggregations, joins, and delivers summaries with actionable insights.

Monitor ClickHouse cluster health and performance through a real-time dashboard built with React and Tailwind CSS. Manage and add UI components for the chmonitor observability interface using shadcn CLI tools.

Optimize PostgreSQL, MySQL, MongoDB, and Redis performance for enterprise B2B SaaS and multi-tenant platforms by tuning queries, designing indexing strategies, configuring connection pooling, implementing scaling solutions, and setting up monitoring workflows.

Manage Apache Cayenne ORM projects by reverse-engineering database schemas, designing and editing DataMaps, generating entity Java classes, writing Cayenne queries, and bootstrapping runtime configuration – all through MCP tool integrations.

Automate end-to-end Japanese income and consumption tax filings for salaried workers with side businesses using blue returns. Assess filing needs via interview, extract data from receipts/invoices/PDFs using OCR, record journal entries to SQLite ledger, compute taxes/depreciation/settlements, prepare e-Tax forms, verify compliance, and guide submission.

Build data processing pipelines, operator graphs, ABAP/S4HANA integrations, replication flows, and ML scenarios in SAP HANA Cloud Data Intelligence. Assemble workflows using Gen1/Gen2 operators and subengines in Python, Node.js, or C++, with JupyterLab for ML and Data Transformation Language functions.

Build in-database machine learning models directly on SAP HANA using Python hana-ml library to execute PAL and APL algorithms, perform DataFrame operations, run AutoML, persist models, and create visualizations.

Helps Qdrant users optimize and manage vector search deployments through tuning performance, diagnosing search quality, scaling clusters, deploying infrastructure, upgrading versions, and using client SDKs.

Manage Amazon Aurora DSQL databases—design schemas, execute queries, handle migrations, and diagnose query plans with IAM authentication and multi-tenant support. Also query AWS knowledge bases and access Aurora databases directly via MCP servers.