Data plugins

Give AI assistants persistent memory by automatically mining project files and conversations into a searchable semantic index, then recall past work, decisions, people, and projects via natural language queries or command-line tools.

Generate Nature-style scientific manuscripts, figures, response letters, patent drafts, and presentations from research materials. Conduct multi-source literature searches, citation management, paper reading with Chinese-English side-by-side rendering, and simulated peer review.

Organize and persist complex, multi-step development plans in crash-proof markdown files (task_plan.md, findings.md, progress.md) that survive context loss and /clear. Supports session recovery, plan integrity verification, and completion gating across 60+ AI coding agents.

Design and review database schemas, optimize SQL queries, and select appropriate data technologies for production systems across PostgreSQL, MongoDB, and cloud-native databases.

Accelerate full-stack development with 66 specialized skills covering 12 languages, frontend/backend frameworks, infrastructure, DevOps, security, and testing, plus Jira/Confluence project management commands for epic planning, discovery, and retrospectives.

Master essential developer workflows across Git, code review, debugging, error handling, authentication, SQL optimization, E2E testing, and monorepo management with Nx, Turborepo, and Bazel.

Design and optimize data pipelines, transformations, and orchestration with Airflow, dbt, and streaming tools. Build vector databases for semantic search and RAG, and select embedding models for production AI/ML workflows.

Integrates with DeerFlow AI agent platform to enable AI-powered research, content creation, and development automation. Generate presentations, reports, charts, documentation, podcasts, newsletters, images, videos, and conduct systematic literature reviews, code analysis, and UI audits.

Transform raw business data into compelling narratives and actionable KPI dashboards for analytics presentations, financial reporting, and strategic decision-making.

Design, build, and optimize production data pipelines and warehouses using Airflow, dbt, and Spark, with built-in data quality validation and analytics engineering patterns.

Automate database migrations with zero-downtime SQL scripts, rollbacks, and validation for PostgreSQL, MySQL, and SQL Server, plus observability infrastructure with CDC, Prometheus, and Grafana for MongoDB. Includes expert agents for multi-cloud database administration, performance tuning, and reliability engineering.

Implement secure backend APIs with input validation, authentication, and vulnerability fixes using hands-on security coding agents.

Open, edit, create, and convert spreadsheet files (.xlsx, .xlsm, .csv, .tsv) with full formula and formatting support. Clean messy tabular data, perform analysis, and recalculate formulas while preserving existing structure.

Reduce Claude's context window usage by intercepting large outputs, indexing project files into a persistent FTS5 knowledge base with BM25 ranking, and executing code in 11 languages within a sandbox. Automatically restore session state across compactions to maintain continuity.

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.

Enables end-to-end data analytics workflows: guides A/B testing with hypothesis validation, audits tracking quality, designs data layers and visualizations using d3.js, and optimizes SQL queries across Postgres, Supabase, and cloud databases.

Analyze cloud spending across AWS, Azure, and GCP to identify waste and savings, while optimizing database performance through query tuning, indexing, and caching strategies for scalable architectures.

Manage the full ML lifecycle on Hugging Face Hub: explore datasets, find and evaluate models, train or fine-tune with TRL/Unsloth, deploy Gradio demos on Spaces, publish research papers, and run models in-browser with Transformers.js.

Configure and debug Payload CMS backends in payload.config.ts by defining collections, fields, hooks, access control, and APIs. Troubleshoot validation errors, security issues, relationships, queries, transactions, and hook behaviors to build robust headless CMS applications.

Enforces structured troubleshooting, evidence-first delivery, and quality verification in Claude Code, using hierarchical agent roles (P7-P10) for task decomposition and multi-agent coordination. Includes coaching modes for motivation, failure analysis, and workplace productivity rituals.

Query data warehouses via natural language or SQL, profile datasets, create interactive dashboards and publication-quality charts, and run statistical analysis with built-in QA checks.

Evaluate and improve LLM applications by instrumenting agents, chatbots, and RAG pipelines with DeepEval tracing, generating test suites, running evaluations, and exporting traces to Confident AI for observability and iterative refinement.

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.

Control your iMessage conversations directly from Claude Code — send messages, manage access via pairing and allowlists, and enforce DM/group policies with built-in security controls.

Accelerate preclinical life sciences R&D by searching biomedical literature, accessing genomics and drug discovery databases, running nf-core analysis pipelines, and performing single-cell RNA/ATAC-seq QC and integration — all within Claude Code through connected MCP servers and automated analysis skills.

Generate self-contained HTML visual explainers for code diff reviews, implementation plans, slide decks, diagrams, and project recaps — with factual verification against git history and one-click deployment to Vercel.

Create, edit, and analyze spreadsheets (.xlsx, .xlsm, .csv, .tsv) with formulas, formatting, data analysis, and visualization, applying financial model standards for colors, numbers, and error-free formulas.

Analyzes meeting transcripts to detect communication patterns like conflict avoidance, filler words interruptions, speaking ratios, and active listening, delivering timestamped feedback and behavioral trends for professional development

Research, outline, and refine written content with citations and section-by-section feedback, improving hooks, flow, and clarity while preserving your voice.

Generate professional financial research reports including equity earnings previews, funding round briefings, and company tear sheets using S&P Capital IQ data, with remote access to S&P Global Kensho's financial intelligence platform for market data and analytics.

Look up Python code examples and enforce Pythonic style — fetch syntax, concurrency, ML, and HPC references from pythonsheets.com while writing, debugging, or optimizing code, and get linting guidance for readable, idiomatic Python.

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.

Access LSEG (Refinitiv) financial data and analytics to price bonds, analyze yield curves, evaluate FX carry trades and yield curves, value options, and build macro dashboards.

Execute shell commands, manage processes, and read/write files beyond the workspace, including PDFs, Excel, DOCX, and images, directly from Claude

Provides a suite of domain-specific expert agents for knowledge management workflows, including knowledge graph suggestions, markdown metadata standardization, MOC generation, tag taxonomy normalization, URL validation and extraction, research query clarification, report generation, and text comparison validation.

Open PDFs from URLs, paths, or arXiv in an interactive viewer to annotate sections collaboratively via screenshots, fill forms with live visual feedback, add signatures and stamps on approval, then download the marked-up document for contracts and approvals.

Query Trino (Presto-based SQL engine) directly from Claude to run distributed SQL queries across databases, data lakes, and other data sources connected to your Trino cluster

Run institutional-grade stock analysis for A-shares, HK, and US equities: 22-dimension data, 65-investor panel voting, 17 valuation methods (DCF, LBO, comps), fraud detection, and Bloomberg-style HTML reports. Supports portfolio drift analysis, earnings preview, catalyst calendars, and investment thesis tracking.

Automate web browser interactions, extract data, and run tests using natural language commands. Build and refine browser automation skills through iterative testing, perform adversarial UI testing on pull requests, and deploy serverless browser functions. Includes CLI tools for web scraping, sales prospecting, competitor research, and safe browsing with domain policies.

Run a complete AI-assisted coding workflow with self-correcting memory, persistent FTS5-indexed research wikis, auto-research loops, multi-LLM council deliberation, and 8 specialized agents that coordinate parallel sessions, enforce quality gates, audit context costs, and capture learnings across every session.

Generate structured engineering documents and analyses for code reviews, incident postmortems, API docs, architecture decisions, system design, runbooks, CI/CD, SLOs, database migrations, security threat models, and more — all from natural language prompts in Claude Code.

Manages AI governance workflows for legal teams: classifies use cases against a registry, runs impact assessments under regimes like the EU AI Act, reviews vendor AI terms for data-training and liability gaps, tracks policy drift, and drafts AI usage policies adapted to your practice profile.

Manage Firebase projects, resources like Firestore, Functions, and Hosting, and data directly in Claude using your local Firebase CLI. Understand project structure, deploy apps, add backend services, and query databases through conversational commands after authenticating via CLI.

Diagnose Swift concurrency issues, refactor callback-based code to async/await, and guide Swift 6 migration with best practices for tasks, actors, Sendable, and data race prevention.

Leverage Common Room's product usage, engagement, and intent signals as a GTM copilot to research accounts and contacts, generate call prep briefs with talking points and objections, draft personalized email/LinkedIn/call outreach, build targeted prospect lists, produce weekly meeting briefings, and create strategic account plans.

Implement Trail of Bits handbook security testing workflows: fuzz Rust, Python, C/C++, Ruby code with AFL++, libFuzzer, cargo-fuzz, Atheris; instrument AddressSanitizer; run static analysis via Semgrep, CodeQL; generate coverage reports, dictionaries, and bypass obstacles for vulnerability detection.

Automate long-form webnovel creation: initialize projects interactively with genre/characters/worldbuilding/outlines, generate beat sheets/chapters (2000+ words), extract entities/relationships to SQLite indexes, visualize status/entity graphs in read-only dashboard, recover interrupted workflows, and validate chapters via agents for inconsistencies, pacing, OOC, reader pull, and quality reports.

Build, deploy, and run serverless web scrapers and automation actors on Apify, including migrating existing code to actors, integrating scraping into data pipelines, and extracting data from 15+ platforms

Query SQL databases and tabular files directly from the terminal using sq's SLQ or native SQL, with capabilities to manage data sources, inspect schemas, diff tables, and handle various output formats

Guides Claude on implementing virtualized lists, chat message lists, and data tables using react-virtuoso in React applications.

Wrangle tabular data (CSV, TSV, Excel, JSONL, Parquet) using qsv's 50+ commands for profiling, cleaning, transforming, joining, validating, converting, and querying with SQL. Includes agents for automated exploration, transformation, and policy analysis with government data sources.

Orchestrate NVIDIA GPU-accelerated workflows across CUDA, AI inference, robotics simulation, Omniverse USD scenes, and Physical AI infrastructure — from CAD-to-SimReady conversion and cuOpt optimization to Dynamo deployment validation and AI-Q deep research.

Orchestrate AI-powered data engineering and ML workflows with a team of specialized subagents for ETL pipelines, quantitative analysis, LLM application development, MLOps, and prompt engineering across cloud platforms.

Build Rust applications that interact with Azure's storage, messaging, database, and secrets management services using official SDK patterns and best practices.

Build and manage PortalJS data portals: scaffold a portal, add datasets with charts and maps, connect CKAN backends, audit data quality, and deploy to Cloudflare static hosting.

Fetch content from WeChat, web, YouTube, PDF, Markdown, and other formats, then automatically convert and upload it to NotebookLM to generate podcasts, presentations, mind maps, and more.

Run all App Store compliance checks in one command – scans iOS/macOS/tvOS/watchOS/visionOS code for rejection risks (hardcoded secrets, missing Sign in with Apple, placeholder content, payment violations), automates fix guidance, and enables iterate-until-greenlit workflow

Parse Burp Suite .burp project files from the command line to search headers and bodies with regex, extract security findings like audit items, and dump filtered proxy history or sitemap for targeted HTTP security analysis workflows.

Build and test Flutter apps with skills for layered architecture, widget and integration testing, adaptive layouts, go_router navigation, localization, HTTP networking, and JSON serialization.

Scan Android APK files or directories for Firebase security misconfigurations like open Realtime Database, Firestore, storage buckets, authentication issues, and exposed Cloud Functions to conduct mobile security audits and authorized pentesting.

Apply proven architectural patterns from DDIA, Clean Architecture, and Team Topologies to design scalable distributed systems, structure maintainable code, improve production resilience, and optimize web performance. Provides interactive guidance for system design interviews and production diagnostics.

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.

Backtest crypto and stock trading strategies on historical data to compute performance metrics like Sharpe and Sortino ratios, maximum drawdowns, equity curves, and optimize parameters via grid search.

Run structured product data analyses including funnel analysis, cohort studies, churn investigations, and metric health reports to answer what changed, why, impact, and recommended actions.

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.

Delegate coding tasks to expert AI agents specialized in Python, Go, Rust, Java, JavaScript, PHP, Ruby/Rails, C/C++, SQL, and TypeScript. They proactively write idiomatic code, refactor for performance, implement advanced features like concurrency and generics, add tests with pytest or RSpec, optimize queries/schemas, and handle builds like Cargo.toml or CMake.

Transforms Claude Code into a learning and development platform with systematic reading coaching, personalized AI tutoring, code review with actionable improvement plans, skill creation and auditing, and wiki knowledge base compilation from documents.

Operate a FairDB PostgreSQL-as-a-Service platform: provision customer databases with role-based access, configure pgBackRest backups to Wasabi S3, monitor infrastructure health, and run incident response with automated recovery scripts.

Access 1000+ scientific tools and 120+ research skills for life sciences data analysis — drug discovery, genomics, variant interpretation, clinical research, and multi-omics integration.

Automate OWASP Top 10 vulnerability scans and penetration testing on JavaScript, Python, and Java codebases using Semgrep, ESLint-security, Bandit, and dependency audits. Delegate comprehensive security audits to a specialized agent covering injections, XSS, CSRF, authentication flaws, access control, and misconfigurations.

Guides an interactive frontend design workflow from trend research and moodboard creation to color/typography selection and production-ready code generation, with browser-based analysis of design inspiration sites.

Analyze cryptocurrency market sentiment by pulling data from social media, news, on-chain metrics, derivatives, whale activity, and Fear & Greed Index to generate 0-100 mood scores, weighted insights, and predictions for overall market or specific coins like BTC.

Build and validate LLM evaluation pipelines: design judge prompts, calibrate against human labels, generate synthetic test data, audit pipeline trustworthiness, analyze failure modes, evaluate RAG systems, and collect human annotations via a browser UI.

Manage the full AWS application lifecycle: author infrastructure with CDK/CloudFormation, deploy serverless and containerized workloads, configure messaging and observability, optimize costs, enforce security with IAM and secret safety, and build generative AI apps on Bedrock using SDK patterns for Python, TypeScript, and Swift.

Routes user requests to expert agents that specialize in domain-specific tasks, creating new agents on demand while maintaining a growing collection of specialists with persistent, agent-tagged memory that survives updates.

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.

Generate and execute automated Python pipelines for data cleaning, transformation, validation, and ETL in ML workflows. Analyze context to produce AI/ML code with built-in validation, error handling, performance metrics, saved artifacts, and documentation.

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.

Optimize LLM prompts for OpenAI and Anthropic by automatically detecting redundancy, simplifying instructions, and rewriting to reduce token usage, lower costs, and improve performance.

Automate full Databricks lakehouse lifecycle: build Delta Lake ETL pipelines with medallion architecture and Auto Loader, engineer ML workflows via MLflow and Feature Store, deploy jobs/pipelines with Asset Bundles and GitHub Actions CI/CD, secure via Unity Catalog RBAC, optimize costs/performance, troubleshoot errors, and monitor with system tables.

Generate plots, charts, and graphs from data via natural language requests—AI analyzes datasets, selects optimal visualization types, produces validated Python code, delivers performance metrics and insights, saves artifacts, and creates documentation.

Scan codebases for data privacy risks, identifying PII exposures, hardcoded sensitive data, unsafe logging practices, unencrypted storage, insecure transmission, missing consent mechanisms, and retention policy violations to audit and remediate compliance issues.

Automate web workflows via CLI: search for instant answers, fetch clean markdown from URLs, run browser agents to navigate sites, fill forms, and extract structured data, launch headless browsers for control, and expose local ports to public HTTPS via SSH tunnels.

Build and manage an AWS-native data lake and analytics platform — set up S3 Tables Iceberg tables, ingest data from JDBC databases, Redshift, Snowflake, BigQuery, and DynamoDB, query with Athena across federated catalogs, store and search vector embeddings on S3 Vectors, and deploy Amazon OpenSearch Service for search, log analytics, and trace analytics. Also troubleshoot Glue connections and inventory the Glue Data Catalog.

Build, deploy, and manage full-stack applications, mini-programs, and cloud functions on Tencent CloudBase, with AI-powered code auditing, documentation creation, automated git workflows, and interactive prototyping.

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.

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.

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.

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.

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.

Set up ML experiment tracking in Python projects using MLflow or Weights & Biases, automating package installs, tool initialization, and logging for parameters, metrics, and artifacts. Execute AI/ML tasks via context analysis, generating validated code, capturing metrics/insights, saving artifacts, and documenting results.

Manage and monitor Datadog resources (monitors, logs, APM traces, dashboards, security signals, SLOs) via CLI commands and specialized agents, enabling observability workflows for infrastructure, applications, and CI/CD pipelines.

Generate minimal macOS Seatbelt sandbox configurations with allowlist-based profiles to restrict application access to files, network, processes, and system resources, enabling secure isolation of macOS apps.

Send and read messages between multiple terminal AI agents (Claude Code, Codex, Gemini CLI, Copilot CLI) using a shared SQLite database — no daemon, no network required.

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.