Data Engineering plugins

Create, read, edit, and generate Office documents — Excel spreadsheets, Word reports, PowerPoint presentations — plus PDF manipulation, form filling, and conversion between formats. Also includes art/image generation, frontend UI building, and document co-authoring workflows.

Perform end-to-end research workflows: market analysis, competitor benchmarking, trend detection, data validation, and idea vetting. A team of specialized agents retrieves and synthesizes information from web, files, and scientific literature to deliver actionable insights and strategic recommendations.

Build production-ready data pipelines with Apache Airflow and dbt, manage scalable data warehouses, and implement vector search and RAG systems using embedding models and vector databases.

Perform business analysis workflows — KPI frameworks, predictive models, real-time dashboards, TAM/SAM/SOM calculations, and multi-year financial modeling for startups — using Python, SQL, and cloud data warehouses like Snowflake and BigQuery.

Autonomous investment banking pitch agent: pulls market data, builds DCF and football-field valuation Excel models, and produces branded pitch deck files on disk — all from a single natural-language request.

Accelerate LLM application development with production-ready patterns for context window management, RAG pipelines, prompt caching, observability via Langfuse, and agent architectures.

Ingest GP valuation packages, run portfolio-company marks through valuation templates, compute NAV and waterfall, and stage LP reporting for IR review in private equity workflows

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.

Automate professional equity research workflows: generate earnings reports, initiating coverage, pre-earnings analysis, morning meeting notes, and sector landscapes. Screen stocks, track catalysts, update financial models, and maintain investment theses with cited sources.

Generate sector and thematic market research reports including industry overviews, competitive landscapes, comparable company analyses, and investment idea shortlists. Automates creation of structured .pptx and Excel outputs for financial analysis workflows.

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.

Manipulate spreadsheet files (Excel, CSV, TSV) with full support for formulas, formatting, and charts. Enables reading, editing, creating, and converting workbooks for data cleaning and analysis.

Automates finance and accounting workflows including month-end close, SOX compliance testing, financial reporting, journal entries, reconciliations, and variance analysis, with integrations to Slack and BigQuery for notifications and data querying.

Manage the full Hugging Face ML lifecycle from a single agent: search and select models, estimate GPU memory, train or fine-tune with TRL/Unsloth, evaluate locally, build and deploy Gradio demos on Spaces, publish datasets and research papers, and run models in-browser with Transformers.js.

Automate sell-side M&A workflows: build buyer universes, draft CIMs and teasers, manage deal pipelines with milestones and deadlines, model accretion/dilution, populate pitch decks and strip profiles, and create financial data packs — all from company data, SEC filings, or web sources.

Automates equity research workflows: reads earnings transcripts and filings, updates financial models with new data, generates professional post-earnings reports with variance analysis, and drafts morning meeting notes — all without live Excel, using Python/openpyxl for .xlsx output.

Automate private equity workflows: screen deals, run due diligence, analyze financials, build IRR models, assess unit economics, monitor portfolio performance, and generate investment memos and value creation plans.

Automate general ledger to subledger reconciliation: detect breaks, trace root cause to originating journal entries, classify break causes, and route exception reports for sign-off. Also audits spreadsheets for financial model errors and integrity.

Write SQL across data warehouses, profile datasets, and generate interactive dashboards and publication-quality charts. Connect to BigQuery, Amplitude, Hex, and Atlassian for integrated data analysis and reporting.

Build and audit financial models (DCF, LBO, comps, 3-statement) in Excel, generate competitive landscape and pitch decks in PowerPoint, and access financial data from FactSet, PitchBook, Morningstar, and other sources.

Build institutional-quality financial models (DCF, LBO, three-statement, and trading comparables) directly in Excel from a ticker and assumption set, with automated formula linkages, integrity audits, sensitivity tables exports as .xlsx files.

Query biomedical literature and preprints (PubMed, biorxiv), search clinical trials, explore drug-target associations (Open Targets, ChEMBL), and run preclinical analyses (RNA-seq, single-cell QC, scvi-tools) directly from the coding environment

Streamlines fund administration and month-end close by automating reconciliation break analysis, accrual schedules, roll-forward tie-outs, and variance commentary — supporting controller — supporting review and audit documentation.

Audit LP capital-account statements against the fund NAV pack before distribution — ties out balances, allocations, and fees, flags discrepancies, and checks spreadsheet formulas for errors, hardcodes, and circular references.

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.

Perform product market research workflows: generate user personas, behavioral segments, and customer journey maps from surveys, CSVs, or feedback; conduct competitive landscape analysis with competitor profiles and differentiation maps; run sentiment analysis on reviews for insights and recommendations; estimate TAM/SAM/SOM with growth projections; output markdown reports.

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.

Automate 90+ Korean daily-life and business tasks — search/reserve KTX/SRT/intercity buses, monitor canceled restaurant slots, check real estate/used goods/car listings on Daangn, compare Coupang/Naver Shopping prices, look up business registration/tax delinquency/patent status, generate Korean legal documents for Next.js, proofread Korean text, and more — all from a CLI or agent.

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.

Create and repair Redpanda Connect pipeline configurations and Bloblang transformation scripts using natural language. Automates component search, config generation, and script debugging with optional sample data validation.

Build, deploy, and run serverless web scrapers and automation scripts on Apify's platform, extract structured data from 15+ websites (Instagram, LinkedIn, Google Maps, etc.), integrate scraping into JavaScript/TypeScript/Python applications, and convert existing projects into scalable Apify Actors.

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.

Work with Mooncake Python APIs to perform distributed storage operations, RDMA/TCP data transfers, and PyTorch tensor processing.

Generate professional Excel financial models including DCF valuations with FCF projections, WACC, sensitivities; LBO analyses with debt schedules, IRR/MOIC; budget vs actual variance reports with waterfalls; and dynamic pivot tables via natural language prompts and auto-invoked skills.

Automate training and optimization of ML models for classification and regression on datasets: analyze data, select/configure algorithms, cross-validate, evaluate metrics, generate Python code using scikit-learn/PyTorch/TensorFlow/XGBoost, and save artifacts.

Build and deploy data portals with PortalJS — scaffold a portal from a brief, add datasets and resources, create charts and interactive maps, connect a CKAN backend, harvest datasets from open-data platforms, define schemas, deploy to Cloudflare static hosting, and audit data quality.

Generate BUY/SELL trading signals for cryptocurrencies and stocks using technical indicators like RSI, MACD, and Bollinger Bands. Scan and rank watchlist opportunities with confidence scores, stop-loss/take-profit levels, multi-timeframe analysis, and markdown reports including risk guidance.

Build, debug, optimize, secure, and deploy FireCrawl web scraping pipelines for LLM/RAG data ingestion: scrape/crawl sites to markdown/JSON, extract structured data, handle rate limits/errors, add monitoring/observability, scale with backoff/caching, and integrate into Node/Python apps from dev to production.

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.

Automate machine learning feature engineering by generating and executing validated Python code to create interactions, scale data, encode categoricals, select features via importance analysis, compute metrics, save artifacts, and generate documentation.

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.

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.

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.

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.

Forecast future values from historical time series data using ARIMA and Prophet models, including trend, seasonality, and autocorrelation analysis with confidence intervals. Generate validated AI/ML code for forecasting tasks complete with error handling, performance metrics, insights, artifacts, and documentation.

Analyze DeFi liquidity pools on Uniswap V2/V3, Curve, Balancer, and other DEXes across multiple chains to calculate impermanent loss, APY, TVL, volume, fees, risks, LP profitability, and optimization opportunities using Python scripts.

Optimize DeFi yield farming strategies across Ethereum, BSC, and Polygon by aggregating DeFiLlama APY data, assessing risks via TVL and audits, and generating portfolio allocations tailored to your capital, risk tolerance, duration, and preferences.

Run an AI product manager workflow: design ethical AI reviews, structure product canvases for ML features, transform PRDs into design briefs for Figma, set up statistically rigorous A/B experiments, and synthesize multi-source user signals into actionable insight briefs.

Build production Clay SaaS integrations for lead enrichment: configure tables and webhooks, deploy receivers to Vercel or Docker, scale pipelines with Redis queues, secure with RBAC and PII guards, optimize costs and performance, troubleshoot failures, and monitor metrics using 30 dedicated Claude Code skills.

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.

Track institutional options flow and detect smart money movements or unusual activity in BTC/ETH markets on Deribit, OKX, and Bybit via API queries, analyzing positioning and sentiment for any symbol or market-wide with customizable params like timeframe and min-premium.

Analyze and monitor on-chain blockchain metrics across chains and DeFi protocols, tracking whale movements, holder distributions, network health, TVL, fees, DEX volumes, yields, and trends. Generate analytics reports via DeFiLlama API using Python CLI tools.

Calculate cryptocurrency capital gains taxes from exchange CSV transaction data using FIFO, LIFO, or HIFO methods. Identify taxable events across trading, DeFi, NFTs, and mining. Generate compliant tax reports and forms like Form 8949 for US, UK, and EU jurisdictions.

Scan cryptocurrencies, stocks, and forex markets for top gainers, losers, volume spikes, and unusual activity. Customize by market, timeframe, category, limits, filters, and sorting. For crypto, rank 1000+ assets by composite score of price change, volume ratio, and market cap to track pumps and trends.

Query EVM blockchain data on Ethereum, Polygon, and Arbitrum from the command line using Etherscan APIs to fetch transactions, address balances, token histories, blocks, and smart contract details, then generate structured markdown reports with holdings, histories, and insights.

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.

Run 89 bioinformatics skills for genomics, pharmacogenomics, single-cell RNA-seq, metagenomics, and variant annotation with deterministic Python execution, reproducibility bundles, and local-first privacy.

Wrangle, profile, clean, transform, and analyze tabular data (CSV, TSV, Excel, JSONL, Parquet) using 51 qsv skill-based commands — including SQL queries, joins, validation, ontology inference, charting, performance acceleration, and reproducible logging.

Run structured product data analysis, retention analysis, and health reporting. Deep-dive into metrics, build funnel and cohort studies, investigate churn, and produce prioritized recommendations with RAG status and root cause hypotheses.

Build and validate linear and polynomial regression models on datasets to predict outcomes, uncover relationships, and report metrics like R-squared and RMSE. Generates validated code with error handling, delivers insights, saves artifacts, and creates documentation.

Split CSV datasets into stratified training, validation, and test sets using custom ratios for ML workflows, generating production-ready Python code with validation, error handling, performance metrics, artifact saving, and automatic documentation.

Detect anomalies and outliers in datasets using ML algorithms like Isolation Forest, One-Class SVM, LOF, and autoencoders to identify unusual patterns. Generate Python code for custom anomaly detection tasks, including validation, error handling, performance metrics, insights, saved artifacts, and documentation.

Build end-to-end AutoML pipelines in Python, automating data checks, feature engineering, model selection, hyperparameter tuning, evaluation, and deployment artifacts for repeatable ML workflows. Generate validated ML code with error handling, performance metrics, and documentation from context analysis.

Guides Chinese academic paper writing from brainstorming through publication: structures research plans, generates literature reviews with BibTeX citations, produces publication-quality Python charts (matplotlib/seaborn), and outputs LaTeX-formatted manuscripts with journal templates.

Scrape, search, crawl, and map the web from the command line, extracting clean markdown or structured JSON from any site—including JavaScript-rendered SPAs. Supports bulk site downloads, interactive browser control, change detection with AI-powered alerts, and local file parsing into LLM-ready markdown.

Use natural language to automate browser interactions—navigate, fill forms, click elements, handle multi-tab sessions—and extract structured data from websites into JSON/CSV, all via Claude through the ActionBook MCP server running locally.

Delegate AI agents to analyze business metrics and KPIs, build revenue models and dashboards, draft GDPR-compliant legal documents, integrate Stripe payments with webhooks, and develop quantitative financial models for trading strategies and portfolio optimization.

Delegate complex AI and data tasks to specialized agents that proactively build LLM applications with RAG and orchestration, design scalable ETL pipelines and warehouses, deploy MLOps workflows, optimize prompts, analyze datasets, manage context, and decompose goals into actionable hierarchies.

Build, deploy, optimize, secure, and troubleshoot Python pipelines exporting Clari revenue forecasts, quotas, CRM data, and adjustments to Snowflake, BigQuery, or PostgreSQL. Includes CI/CD integration, API debugging, cost/performance tuning, local mocks, schema migrations, rate limit handling, and production checklists.

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 production Navan API integrations for travel bookings, expense management, and data syncing to ERPs/warehouses: automate OAuth auth setup, REST workflows, error debugging, CI/CD deployment, monitoring, security hardening, and webhook handling.

Develop, deploy, and manage Databricks-based data pipelines, ML models, AI agents, and dashboards using code, SQL, and declarative tools for multi-environment workflows.

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.

Automate processing of PDF, DOCX, PPTX, and XLSX files in Anthropic Claude workflows: extract text, tables, images, and metadata; edit content, structure, and tracked changes; generate documents and presentations from templates; clean, format spreadsheets with formulas, charts, and financial standards.

Build production web scraping pipelines with Bright Data: authenticate proxies/APIs, scrape JS/SPA sites via Scraping Browser/Playwright/Puppeteer/SERP, debug errors/rate limits, tune costs/performance/caching, deploy to Vercel/GCP/Fly.io, set up CI/CD/tests/webhooks, and monitor usage in Node.js/Python projects.

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.

Orchestrate Hex data projects via API in external pipelines: trigger parameterized runs, poll status, integrate GitHub Actions CI/CD for deploys/refreshes, optimize costs/performance/rate limits, debug errors, secure auth, deploy to Vercel/Fly.io/Cloud Run, and migrate SDKs.

Accelerate Palantir Foundry integrations by generating Python SDK code for building ETL data pipelines, managing Ontology objects, handling API errors and rate limits, configuring RBAC and security, setting up CI/CD with GitHub Actions, deploying to GCP/AWS/Docker, and implementing monitoring, observability, and cost optimization.

Build, deploy, debug, and scale Apify Actors for web scraping: scaffold Crawlee crawlers with input schemas and routers, manage datasets/queues/APIs programmatically, set up local dev/CI-CD pipelines with GitHub Actions, diagnose errors/timeouts/proxies, tune performance/costs, secure tokens, and integrate runs into Node.js apps.

Agentically audit, optimize, and manage Power BI semantic models in Microsoft Fabric: trace dependencies across workspaces for impact analysis, review quality and performance against best practices, standardize TMDL naming conventions, author and validate Power Query M expressions, and orchestrate full/incremental refreshes via REST APIs and CLI.

Manage AWS data lakes and analytics workflows: create and query Iceberg tables on S3 Tables, run Athena SQL across Glue and Redshift catalogs, ingest data from JDBC databases, Redshift, Snowflake, BigQuery, and DynamoDB, audit Glue Data Catalog assets, and store/query vector embeddings on S3 Vectors for semantic search and RAG.

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.

Discovers and runs weather/climate AI models from the Earth2Studio ecosystem: browse models and data sources filtered by GPU/VRAM, install with uv or pip and model extras, fetch variables and times from data sources, and build deterministic forecast inference scripts.

Manage Microsoft Fabric workspaces, notebooks, lakehouses, and OneLake files using the fab CLI, with support for migrating workspaces from trial to production capacity and retrieving Microsoft Learn documentation.

Build, manage, and deploy the full Salesforce platform stack — Apex, OmniStudio, Data Cloud, Agentforce agents, Lightning Web Components, UI bundles, flows, metadata, and mobile apps — with code generation, validation scoring, debugging, documentation retrieval, and CLI-driven deployment.

Detect PII in codebases and data stores, generate severity-ranked risk inventories with remediation recommendations, and anonymize datasets via pseudonymization techniques, outputting formatted reports of processed fields and applied methods.

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.

Follow expert Dagster conventions and dg CLI guidance to create projects, define assets jobs schedules sensors, debug issues, and query pipeline components in Python data engineering workflows.

Scrape any webpage, search Google, and extract structured data from 40+ platforms (Amazon, LinkedIn, Instagram, TikTok, YouTube) via Bright Data's CLI, MCP server, or SDKs, with built-in bot detection bypass, proxy integration, and real-time competitive intelligence.

Write, debug, and maintain fenic code with skill-based guidance for fenic's semantic DataFrames and LLM operators, plus automated API reference regeneration after version upgrades.

Automate creation, editing, analysis, and visual review of Office documents: build Excel spreadsheets with formulas/charts, edit Word docs and PowerPoint slides preserving layout, generate/extract from PDFs, using rendered previews for validation.

Generate AntV G6 v5 graph visualizations—network graphs, tree diagrams, flowcharts, and mind maps—with correct layout, interaction, and plugin configuration, while avoiding v4 API pitfalls.

Manage the full Airflow data engineering lifecycle: author, test, debug, and deploy DAGs; profile and trace lineage across warehouses; migrate between Airflow versions; and troubleshoot production deployments via CLI.

GPU-accelerated Mean-CVaR portfolio optimization using NVIDIA cuOpt for efficient frontier computation, scenario generation, backtesting, and rebalancing of stock portfolios.