Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, targets, pathways, chemical structures, and pharmacology data. This skill should be used when working with pharmaceutical data, drug discovery research, pharmacology studies, drug-drug interaction analysis, target identification, chemical similarity searches, ADMET predictions, or any task requiring detailed drug and drug target information from DrugBank.
Analyze e-commerce performance using GA4 metrics, conversion funnel analysis, and key e-commerce KPIs. Use this skill when the user needs to evaluate online store performance, diagnose conversion drop-offs, set up e-commerce tracking, or create performance dashboards — even if they say 'why are sales down', 'optimize our online store', 'set up GA4 for e-commerce', or 'what metrics should we track'.
Use Electric with Drizzle ORM or Prisma for the write path. Covers getting pg_current_xact_id() from ORM transactions using Drizzle tx.execute(sql) and Prisma $queryRaw, running migrations that preserve REPLICA IDENTITY FULL, and schema management patterns compatible with Electric shapes. Load when using Drizzle or Prisma alongside Electric for writes.
Turn financial model outputs into a clear written narrative. Use when asked to write a financial narrative, explain a financial model, summarise a P&L, or translate spreadsheet numbers into a board-ready story. Produces an executive narrative with key insights, drivers, and forward-looking commentary.
Search, scrape, and interact with the web via the Firecrawl CLI. Use this skill whenever the user wants to search the web, find articles, research a topic, look something up online, scrape a webpage, grab content from a URL, get data from a website, crawl documentation, download a site, or interact with pages that need clicks or logins. Also use when they say "fetch this page", "pull the content from", "get the page at https://", or reference external websites. This provides real-time web search with full page content and interact capabilities — beyond what Claude can do natively with built-in tools. Do NOT trigger for local file operations, git commands, deployments, or code editing tasks.
Use this skill when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
CLI/Python toolkit for rapid bioinformatics queries. Preferred for quick BLAST searches. Access to 20+ databases: gene info (Ensembl/UniProt), AlphaFold, ARCHS4, Enrichr, OpenTargets, COSMIC, genome downloads. For advanced BLAST/batch processing, use biopython. For multi-database integration, use bioservices.
Official skill for recognizing and extracting tables from images and PDFs into Markdown format using ZhiPu GLM-OCR API. Supports complex tables, merged cells, and multi-page documents. Use this skill when the user wants to extract tables, recognize spreadsheets, or convert table images to editable format.
Generates a one-page IPO prospectus overview. Use this skill when the user provides a prospectus or filing link (A-shares, Hong Kong 18A/18C, US S-1/F-1), a local document, or only a company name and asks for analysis of its IPO prospectus, filing, or hearing materials, or mentions scenarios such as “prospectus overview,” “one-page prospectus,” “prospectus analysis,” “IPO analysis,” or “filing”—even if the user does not explicitly say “one-page.” Output: a mobile-readable, single-file HTML overview and a structured Excel data workbook. This skill faithfully translates disclosed prospectus content; it does not provide investment advice or full due diligence. Earnings and annual report extraction are outside its scope—direct the user to run /hike-earnings-core (explicit invocation only).
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment.
Generates in-depth research reports for a specified industry based on the East Money database. This Skill should be triggered when a user's question contains an identifiable industry/sector/domain subject and the intent is industry understanding, industry analysis or writing a research report. Common phrasings include "XX industry research", "XX industry report", "help me analyze industry XX", "in-depth research on industry XX", "market analysis of domain XX", etc. Even if the user does not explicitly say "report", it also applies whenever an industry is the core subject and systematic or in-depth research/analysis is requested.
Guide for accessing financial and economic data in MATLAB using the Datafeed Toolbox. Covers Bloomberg (market data via bloomberg/blp/bloombergHypermedia), FRED (Federal Reserve economic data via fredrs), Haver Analytics (economic data via haver/haverdirect/haverview), and LSEG Datastream (historical data via datastreamws). Use when connecting to any of these data providers from MATLAB.
MLflow 3 (open-source, pinned to 3.15) for classic-ML MLOps — logging and registering models, promoting versions across dev/staging/prod, standing up a tracking server, evaluating with gates, and serving. Corrects the MLflow 2-era defaults a model reaches for (artifact_path, registry stages and get_latest_versions, top-level mlflow.evaluate with baseline_model, runs-URI registration, pickle serialization, mlruns file stores, MLServer serving) with the MLflow 3 idioms that replaced them (named LoggedModels, aliases and copy_model_version, models.evaluate plus validate_evaluation_results, skops/torch.export defaults, database backends, the FastAPI scoring server). Use when writing, reviewing, or migrating Python code that touches MLflow tracking, the model registry, evaluation, or serving.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
When the user wants to optimize multiple conflicting objectives, find Pareto-optimal solutions, or balance trade-offs between cost, service, quality, and sustainability. Also use when the user mentions "multi-objective," "Pareto optimization," "NSGA-II," "trade-off analysis," "scalarization," "weighted objectives," "goal programming," or "multiple criteria optimization." For single objective, see optimization-modeling.
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use for network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.
A skill for writing server-side APIs with the Nitro v3 framework and H3. Use for initialising backend-only Nitro projects, adding full-stack capabilities to Vite projects, writing spec-compliant CRUD endpoints, and database interaction with Drizzle ORM. Use this skill when developing new Nitro endpoints, initialising Nitro configuration, or consulting Nitro development conventions.
Offline transaction support for TanStack DB. OfflineExecutor orchestrates persistent outbox (IndexedDB/localStorage), leader election (WebLocks/ BroadcastChannel), retry with backoff, and connectivity detection. createOfflineTransaction/createOfflineAction wrap TanStack DB primitives with offline persistence. Idempotency keys for at-least-once delivery. Graceful degradation to online-only mode when storage unavailable. React Native support via separate entry point.
Use when an AI coding assistant needs GIS/CAD/C#/AI/IoT/3D domain expertise. Index of 114 skills across 8 categories: gis (40), cad (21), csharp (12), ai (17), iot (4), 3d (6), demos (4), others (10). Tag-based search and on-demand loading for GDAL, GeoServer, MapServer, Leaflet, PROJ, PostGIS, DuckDB Spatial, GeoLibre, JTS, CesiumJS, FreeCAD, Blender, OpenSCAD, OCCT, NPOI, SqlSugar, Furion, Serilog, Dify, Ollama, LangChain, vLLM, MinerU, SuperSplat, Home Assistant, CHAGS and more.
Runs the parallel-cli tool for web workflows: web search, URL and PDF extraction, deep research reports, structured data enrichment of supplied rows, FindAll entity discovery, and recurring web monitors. Prefers primary literature and institutional sources for scientific queries. Use when looking up current web evidence or a bounded research question. Use when fetching content from a known URL, PDF, or JavaScript-rendered page. Use when adding web-sourced fields to a list of companies, people, or products. Use when discovering entities that match natural-language criteria. Use when an explicitly exhaustive multi-source report is requested. Use when tracking web changes on a recurring schedule. Not for one-time checks of a known page that need no CLI, or for offline literature databases.
An Astropy coordinated package for detecting and performing photometry of astronomical sources. Provides tools for background estimation, source detection (DAOFIND, IRAF), aperture photometry, and PSF (Point Spread Function) fitting. Use when working with astronomical image analysis, star/galaxy detection, measuring brightness (photometry), background subtraction, PSF fitting, aperture photometry, centroiding, or isophotal analysis.
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure
Populates investment banking pitch deck templates with data from source files. Use when: user provides a PowerPoint template to fill in, user has source data (Excel/CSV) to populate into slides, user mentions populating or filling a pitch deck template, or user needs to transfer data into existing slide layouts. Not for creating presentations from scratch.
Write a business case for adding product telemetry and analytics to a product. Produces a concise, stakeholder-ready document explaining what telemetry enables, what you're currently blind to, what's involved in implementation, and the business value. Sits outside the main telemetry lifecycle — use before committing to the technical work. Use when the user asks to 'write a business case,' 'justify analytics,' 'make the case for tracking,' 'telemetry brief,' 'why add analytics,' 'convince leadership about tracking,' or 'analytics ROI.'
Python visual creation and matplotlib/seaborn patterns for PBIR reports. Automatically invoke when the user mentions "Python visual", "matplotlib in Power BI", "seaborn in Power BI", "pythonVisual", or asks to "create a Python visual", "add a matplotlib chart", "write a Python visual script".
Use when the user needs to build, choose the pattern for, or optimize a SQL query against Protheus ERP tables -- covering Workarea (DbSelectArea/DbSeek) vs Embedded SQL vs TCSqlExec pattern choice, mandatory D_E_L_E_T_/xFilial filters, SIX index-aligned WHERE ordering, FWPreparedStatement parameterization to prevent SQL injection, and cross-database (PostgreSQL/MSSQL/Oracle) portability. Also triggers on Portuguese phrasing like "consulta SQL", "montar query", "otimizar consulta", "qual indice usar", "escolher entre DbSeek ou SQL", or "prevenir SQL injection no Protheus".
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.