Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Guides use of Zarr-Python 3 for storing chunked, compressed N-dimensional arrays and groups, with local, in-memory, ZIP, and fsspec-backed S3/GCS/HTTP stores, plus NumPy, Dask, and Xarray integration. Covers array creation, resizing and appending, attributes, chunk and shard sizing, codecs, consolidated metadata, and v2-to-v3 migration. Use when creating or opening Zarr arrays or groups, choosing chunk sizes or compression for large datasets, reading or writing arrays on S3 or GCS, appending to time-series arrays, or migrating code from Zarr-Python 2 to 3. Use when setting up parallel I/O with Dask or Xarray. For labeled multi-dimensional datasets, use Xarray instead.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Manages AI model retention and machine unlearning requirements. Covers training data deletion verification, model versioning for compliance, machine unlearning techniques (SISA, gradient-based), and retraining triggers. Keywords: AI retention, machine unlearning, model versioning, training data deletion, retraining, storage limitation.
Implements data subject rights mechanisms for AI systems including right to explanation of AI decisions, contestation procedures, human review, model output correction, and training data access. Covers GDPR Arts. 15-22 and AI Act Art. 86. Keywords: data subject rights, AI explanation, contestation, human review, training data access, model correction.
Implements federated learning architecture patterns for GDPR compliance. Covers secure aggregation protocols, differential privacy integration, communication protocols, and privacy-by-design distributed ML training. Keywords: federated learning, distributed training, secure aggregation, differential privacy, privacy-preserving ML.
This skill should be used when the user asks about "data journalism", "data visualization", "data storytelling", "FOIA request", "RTI request", "spreadsheet analysis", "chart design", "act as a data journalist", "data journalist mode", "infographic", "open data", "statistical analysis for journalism", "investigative data", "public records", "Datawrapper", "Flourish", "Tableau Public", "D3.js", "chart type selection", or needs expertise in finding, analyzing, and visualizing data for journalistic storytelling. Part of the AlterLab FC Skills collection (New Media & Communication department).
This skill should be used when the user asks about "campaign report", "performance report", "KPI dashboard", "campaign evaluation", "Barcelona Principles", "post-campaign analysis", "metrics report", "ROI measurement", "media evaluation", "act as a report generator", "report generator mode", "campaign results", "advertising effectiveness", "analytics report", or needs expertise in building campaign performance reports, evaluation frameworks, and KPI dashboards. Part of the AlterLab FC Skills collection (Public Relations & Advertising department).
End-to-end research workflow skill for investment analysts and policy researchers. Three scope modes the user picks at trigger time — light (4-5 page decision memo, ~15 min, 0 charts), medium (12-15 page topic brief, ~1 h, 6-10 charts), heavy (flagship report 30-40 pages / 15k+ words, ~2-3 h, 25-35+ charts, multi-stage workflow, multi-LLM, PDF + Word + WeChat + HTML derivations). Reports default to English; the AI replies in the user's chat language. Battle-tested on real macro/policy/equity reports (e.g. Saudi Vision 2030 deep-dive). Triggers when user types /analyst-research, /flagship-research, or describes needs like "research report", "topic analysis", "investment research", "做研报", "投研报告", "主题分析", "深度分析", "policy assessment", "industry deep-dive". Not for: pure news commentary (use topic-brief), slide decks (use deckster-slide-generator), one-shot Q&A.
Automated enforcement of GDPR Article 5(1)(e) storage limitation principle. Covers TTL-based deletion, retention policy engines, archival workflows, legal hold exemptions, and lifecycle automation. Includes technical implementation patterns for automated data expiry and defensible deletion across distributed systems.
Guidance for the security-side use of Azure Monitor and Log Analytics — designing the workspace strategy that feeds Microsoft Sentinel and Defender for Cloud, choosing analytics vs basic vs auxiliary log tiers, retention and archive, table-level transformations to drop noise pre-ingestion, Data Collection Rules (DCRs) and Azure Monitor Agent (AMA), workspace topology (single vs regional vs sovereign), commitment tiers and cost control, customer-managed keys for the workspace, RBAC including table-level RBAC, integration with Sentinel (workspace requirements), and decommissioning legacy MMA. WHEN: Log Analytics workspace design, Azure Monitor security data, Sentinel workspace, log tier basic auxiliary, AMA Azure Monitor Agent, DCR data collection rule, drop columns ingestion transform, log retention archive, workspace CMK, table-level RBAC, log ingestion cost control. DO NOT USE for Sentinel detection authoring (use sentinel-detection-engineering), App Insights instrumentation (use appinsights-instrumentation), or non-security observability.
ByteHouse AI query skill providing natural language to SQL (Text2SQL), SQL execution, schema lookup, multimodal vectorization and vector retrieval, covering everyday querying, SQL generation and execution on the ByteHouse cloud data warehouse. Use this Skill when users mention "ByteHouse", "query a table", "query data", "Text2SQL", "natural language query", "list databases", "list tables", "execute SQL", "generate SQL", "multimodal retrieval", or need to accomplish the above tasks with ByteHouse.
Generate publication-quality PNG chart images from data, supporting line, bar, area, candlestick, pie, and heatmap charts. Triggers when the user asks to visualize data, create a graph, plot a time series, or generate a chart for a report, alert, or dashboard. Runs as a lightweight, headless Node.js process without a browser.
Professional data visualization creation using D3.js with support for interactive charts, custom visualizations, animations, and responsive design. Use for: (1) Creating custom interactive charts, (2) Building dashboards, (3) Network/graph visualizations, (4) Geographic data mapping, (5) Time series analysis, (6) Real-time data visualization, (7) Complex multi-dimensional data displays
Serverless compute for Databricks jobs, Lakeflow pipelines and Declarative Automation Bundles (DABs), with STANDARD or PERFORMANCE_OPTIMIZED and classic only where serverless cannot run the workload. Use when creating, deploying, scheduling or editing a job or pipeline, or deciding its compute. Invoke BEFORE writing a job spec. For migrating existing classic workloads, use databricks-serverless-migration.
Use this skill when answering business analytics, RevOps, GTM metric, pipeline, revenue, funnel, customer, or warehouse questions with Deepline. Triggers on phrases like 'query Snowflake', 'analyze pipeline', 'total ACV', 'break down by quarter', 'use the semantic layer', 'run a semantic query', or any use of snowflake_get_semantic_layer / snowflake_run_semantic_query. Skip prospecting, enrichment, contact finding, outbound, or personalization workflows; use deepline-gtm for those.
Use Docling to understand the content of documents in any supported format — PDF (born-digital or scanned), DOCX, PPTX, XLSX, HTML, Markdown, AsciiDoc, CSV, images, audio, and XML — by converting them into a unified DoclingDocument (Markdown or structured JSON). Use this skill whenever you need to read, parse, convert, extract, or chunk a document you cannot read directly: “what's in this PDF”, “convert this to markdown”, “extract the tables”, “chunk this for RAG”, “read this scanned document”, “parse this DOCX/PPTX”. Covers the `docling` CLI, the Python SDK (DocumentConverter + PipelineOptions), the remote Service Client (self-hosted or managed docling-serve), and the docling-slim install extras for a minimal dependency footprint.
Type-safe Drizzle ORM patterns for Cloudflare D1 databases: schema definition, migration management with Drizzle Kit and drizzle.config.ts, relations and relational queries, joins, prepared statements, the D1 batch API for transaction-like work, and Workers/Wrangler integration. Documents 12 known pitfalls including D1 transaction errors (SQL BEGIN is unsupported), foreign key constraint failures during migrations, module import errors under Wrangler, missing D1 bindings, migration apply failures, schema TypeScript inference errors, prepared statement caching, rollback patterns, TypeScript strict mode errors, remote versus local database confusion, and mixing wrangler.toml with wrangler.jsonc. Use when building a D1 schema, writing type-safe queries, running or repairing Drizzle migrations, or hitting D1_ERROR, BEGIN TRANSACTION, d1 binding, or schema inference errors.
Deploy Electric via Docker, Docker Compose, or Electric Cloud. Covers DATABASE_URL (direct connection, not pooler), ELECTRIC_SECRET (required since v1.x), ELECTRIC_INSECURE for dev, wal_level=logical, max_replication_slots, ELECTRIC_STORAGE_DIR persistence, ELECTRIC_POOLED_DATABASE_URL for pooled queries, IPv6 with ELECTRIC_DATABASE_USE_IPV6, Kubernetes readiness probes (200 vs 202), replication slot cleanup, and Postgres v14+ requirements. Load when deploying Electric or configuring Postgres for logical replication.
Fetch results for a GrowthBook experiment, refresh the snapshot only when the cached data is over 24 hours old, then interpret. Use when the user asks "what are the results of X", "analyze this experiment", "is X winning", "did the test work", "show me the results", or "dig into the dimensions". Reads only — does not stop or modify the experiment. For stopping after you've seen results, use experiment-stop.
Propose new experiment ideas grounded in the team's past stopped experiments via the GrowthBook REST API. Use when the user asks "what should we test next", "give me experiment ideas", "brainstorm A/B tests", "what's worth testing", or "ideas for experiments". Proposes only — does not create experiments. For designing a specific test, use experiment-design. For reading results of one, use experiment-analyze.
Imports datasets into FiftyOne with automatic format detection. Supports all media types (images, videos, point clouds, MCAP multimodal recordings), label formats (COCO, YOLO, VOC, KITTI), multimodal grouped datasets, LeRobot v3 robot-learning episode datasets, and Hugging Face Hub datasets. Use when importing datasets from local files or Hugging Face, loading autonomous driving data, importing robotics/AV sensor logs (MCAP, ROS bag), importing LeRobot robot-learning episodes (teleop recordings, observation.state/action data), or creating grouped datasets.
Generate financial statements (income statement, balance sheet, cash flow) with period-over-period comparison and variance analysis. Use when preparing a monthly or quarterly P&L, closing the books and need to flag material variances, comparing actuals to budget, building a financial summary for leadership review, or looking up GAAP presentation requirements and period-end adjustments.
Use when the user wants to define, parse, or manage a GA4 event taxonomy (이벤트 정의서) — turning a spreadsheet of planned events/parameters into taxonomy.json/taxonomy.md, comparing planned events against what GA4 actually collects, or drafting an initial taxonomy from live GA4 data. Consumes .ga4/config.json + token.json from the ga-auth skill for the live features.
A skill that uses GLM-V native grounding capabilities for coordinate conversion, bounding-box visualization, and more. GLM-V native grounding can locate any target specified by the prompt in an image and output relative coordinates normalized to 0-1000 based on image size. Coordinate formats include 2D bounding box (default), 2D points, and 3D bounding box. GLM-V also supports spatiotemporal localization and tracking of multiple prompt-specified targets in videos, outputting 2D bounding boxes per second.
Analyze liquid markets with a strict ICT/SMC framework that combines multi-timeframe bias, liquidity sweeps, displacement, close-confirmed MSS/BOS, FVG/OB/Breaker/OTE retracements, premium-discount location, session timing, invalidation, targets, and risk-to-reward. Use for ICT chart reviews, live-market analysis, OHLCV scans, or validating a user's trade thesis. Return an auditable setup status and conditional plan; do not use for generic indicator analysis, order execution, or claims of proven institutional intent.
Identify and diagnose organic-search articles that need maintenance. Use when asked to find pages whose organic traffic declined mainly from ranking loss rather than search-demand decline, analyze Search Console or GA4 data across recent and year-over-year periods, prioritize a maintenance backlog, or compare target pages with current Google results. Do not use this skill to edit article content.
Read your Instagram niche and profile from real data via Apify, no login. Scan a hashtag for the posts traveling now (likes, comments, owner) to see the format and hook that works. Pull profile stats for any handle, yours or a competitor's: followers, posts, bio, category. Instagram hides who liked or commented on other accounts, so this is discovery plus profiles, not engagers. Triggers on "what works in my niche", "scan the hashtag", "competitor stats". Not for writing captions (use ig-caption-writer)
When the user wants to calculate insurance loss reserves or analyze insurance financial health. Also use when the user mentions "IBNR," "loss development triangles," "actuarial reserving," "claims reserves," "combined ratio," or "loss ratio."
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.