Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Tavily AI search API for LLM applications: web search, content extraction, site crawling, mapping, and research. Use when integrating real-time web search into LLM apps, extracting content from URLs, crawling sites, or building RAG pipelines with web data. Keywords: Tavily, AI search, RAG, web search API, LLM search, extract, crawl, map, research, tavily-python.
Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets, for PyTorch-based ML on molecules, proteins, and biomedical graphs.
Use when the user mentions memory search, RAG retrieval, knowledge queries, embedding rebuild, document upload, connection tokens, or invokes "/tm" / "transcendence-memory" — including indirect recall like "what did we decide last time", "上次怎么处理的", "之前的方案". Covers searching, storing, multimodal RAG queries, and troubleshooting against a self-hosted memory backend.
Fetch analytics from Umami. Use when the user asks about umami, analytics, website traffic, daily stats, pageviews, visitors, how is my site doing, traffic report, site performance, bounce rate, visitor count, active users, who is on my site, or website statistics.
Access UniProt for protein sequence and annotation retrieval. Use this skill when: (1) Looking up protein sequences by accession, (2) Finding functional annotations, (3) Getting domain boundaries, (4) Finding homologs and variants, (5) Cross-referencing to PDB structures. For structure retrieval, use pdb. For sequence design, use proteinmpnn.
Design and audit user research repositories that turn interviews, surveys, usability tests, support tickets, sales calls, churn reasons, app reviews, and product analytics into tagged, consent-safe, decision-linked evidence. Use when product teams need reusable insight instead of anecdote piles.
Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file uploads, text and video embeddings, live RTSP streams, health and metrics), Redis/Kafka/OTel integration, common failure modes, and teardown
Use to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-deploy-dense-captioning), or video summarization and reports (use vss-summarize-video).
Web scraping and search via paid API: crawl any URL with cascade escalation (fast HTTP -> browser -> stealth+proxy), bulk crawl multiple URLs, and search the web via Exa. Uses x_payment tool for automatic USDC micropayments ($0.005/crawl, $0.01/search). Use as escalation when built-in web_fetch fails or is blocked. Use when: (1) web_fetch returned empty/blocked content, (2) scraping JS-rendered or anti-bot protected pages, (3) bulk-crawling multiple URLs, (4) searching the web by query via Exa.
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like “the xlsx in my downloads”) — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Combine multiple forecasting models into ensemble predictions for improved accuracy. Use this skill when the user needs to improve forecast reliability, combine ARIMA/Prophet/ETS outputs, or build a robust forecasting pipeline — even if they say 'combine forecasts', 'model averaging', or 'which forecast should I trust'.
Alibaba Cloud LoongCollector / SLS installation, collection onboarding, Pipeline config management and validation, machine groups, permission troubleshooting, and Lens queries. HARD RULE: for matching requests, the first tool MUST load this skill before any SSH probe, directory setup, checklist/file write, or cloud read. Triggers: "安装 LoongCollector", "ECS 安装采集器", "自建 Linux 主机安装 LoongCollector", "ACK 安装 loongcollector", "自建 K8s 部署采集", "从安装到能查到日志", "SLS 日志采集接入", "SLS 日志采集接入相关的事", "修改采集配置", "改采集配置", "采集配置校验", "validate_pipeline.py", "SLS 机器组", "新建 Logtail Pipeline 采集配置", "Logtail Pipeline", "ClusterAliyunPipelineConfig", "SLS Lens 查询", "无数据排查", "心跳异常", "SLS 采集权限排查", "SLS 权限排查", "阿里云 CLI 凭证没有 SLS 操作权限", "Logtail", "iLogtail", "AgentSight", "Agentloop", "input_agentsight", "eBPF Runtime", "ebpf-event".
Build and embed pro-code JavaScript custom apps inside Domo App Studio pages. Bridges the custom app build pipeline (basic-custom-app-build, domo-app-theme) with App Studio layout (basic-app-studio, advanced-app-studio). Covers decision routing between native cards and pro-code apps, build coordination with design skills, canvas integration, page-level filter propagation (domo.onFiltersUpdated), App Studio variable integration (domo.onVariablesUpdated, domo.requestVariablesUpdate), and the pending/commit pattern for variable state management. Use when a visualization or interaction exceeds native card capabilities, when the user mentions pro-code editor, or when embedding custom apps in App Studio.
Query the ARCHS4 REST API for uniformly processed RNA-seq expression, tissue patterns, co-expression across 1M+ human/mouse samples. Retrieve z-scores, co-expressed genes, samples by metadata, and HDF5 matrices. For variant population genetics, use gnomad-database; for pathway enrichment, use gget-genomic-databases (Enrichr).
Clean, split, and featurize multivariate time-series data before embedding it with the Omega model. Bundles three reusable building blocks: `DataPreprocessor` (diagnose timestamp regularity, gaps, and nulls; build continuous gap-aware temporal blocks with imputation), `DataSplitter` (out-of-time or random train/test split that respects temporal order), and `FeaturePreparer` (pivot per-sensor embeddings into a "joint state" (X, y, metadata) matrix with optional L2 / standardization / PCA). Use this skill when the user is preparing raw sensor CSVs for the Omega model (`atai-newton-omega-model`), when training data has gaps and they're unsure whether to drop / impute / split, or when an n-shot CSV looks noisy and they want a principled cleanup pipeline. Do NOT use this skill to run inference or produce embeddings (use `atai-newton-omega-model`). Do NOT use for video / image / text data (use `atai-newton-fusion-model`) — time-series only.
Automates financial and business data analysis, mines data value in depth, and generates professional reports. Activation scenarios: the user provides financial statements (income statement, balance sheet, cash flow statement) or business data (sales, operations, customer, cost data), or asks for data analysis, data mining, report generation, KPI calculation, trend analysis, variance analysis, year-over-year and period-over-period analysis, multidimensional analysis, or data cleaning. Trigger keywords: 分析数据, 财务分析, 业务分析, 做报表, 数据挖掘, 看看数据, 分析一下, 出报告, KPI, 趋势, 同比, 环比, 差异分析, 数据质量, 收入分析, 成本分析, 客户分析, 运营分析.
Run SQL against Google BigQuery and browse its catalog — submit queries (sync or async), poll job status, page through results, list datasets/tables, and read table schemas. Use this whenever the user wants to query a BigQuery table, ask "what's in this dataset", check a BigQuery job's status, or mentions bigquery.googleapis.com or a `project.dataset.table` path. Always start from this skill when interacting with this service — its bundled scripts and recipes are the fastest path.
Use when the user wants to connect to, query, or explore a data source through a CData driver via the command line. This includes: creating or testing a connection to an enterprise system (Salesforce, NetSuite, Snowflake, SQL Server, Jira, etc.); running SQL queries against connected data; exploring schema (listing tables, columns, or stored procedures); executing source-specific stored procedures; and downloading, installing, or activating CData drivers. Acts as the prerequisite foundation for all driver-level cdata- skills (cdata-salesforce, cdata-airtable, etc.) that add source-specific guidance.
Develops data classification policies with tiered handling (public, internal, confidential, restricted), labeling requirements, enforcement mechanisms, and procedures per tier. Covers policy governance, exception handling, and compliance monitoring. Keywords: classification policy, data tiers, handling procedures, labeling, enforcement, data governance, information security.
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis
Cloudflare Vectorize, the globally distributed vector database for semantic search, RAG, and AI applications on Workers. Covers index creation with fixed dimensions and distance metric (cosine, euclidean, dot-product), insert/upsert/query/delete/list vector operations, metadata and namespace filtering, topK search, document chunking and batch ingestion pipelines, and embedding generation via Workers AI (@cf/baai/bge-base-en-v1.5) or OpenAI (text- embedding-3-small/large). Use when creating a Vectorize index, wiring a vectorize binding, inserting embeddings, building a RAG or semantic search pipeline, running wrangler vectorize commands, or debugging metadata index timing errors, dimension mismatches, filter syntax problems, or insert vs upsert confusion.
Integrate or upgrade the Contentsquare iOS SDK (current version 1.11.x) -- Session Replay, screen tracking, transactions, analytics, masking, privacy opt-in/out. Always starts with a mandatory Contentsquare project healthcheck (ask for the data source IDs or resolve the app bundle id, call the healthcheck endpoint, report project health) before any other work. Use when working with Contentsquare, CSQ, CSQ.start, CSQ.trackScreenview, CSQ.optIn, CSQ.registerWebView, WKWebView tracking, or migrating from SDK versions 1.0–1.6 / `configureProductAnalytics` to `CSQ.start(environmentID:options:)`.
Guide for Convex schema design, validators, and TypeScript types. Use when defining database schemas, creating validators for function arguments/returns, working with document types, or ensuring type safety. Activates for schema.ts creation, validator usage, Id/Doc type handling, or TypeScript integration tasks.
Model data with @data-client schemas (Entity, EntityMixin, Collection, Union, Query, Values, All, Invalidate, Lazy, Scalar) for atomic, consistent, referentially-equal async data via normalization, identity-based caching, and a single source of truth. Use when defining or editing pk, static schema, resource()/RestEndpoint schema, mutable lists/maps (push/unshift/assign/remove/move), polymorphic/discriminated types, memoized selectors / derived data, partial/supplementary entities, relational/nested/joined data, optimistic updates, or cache invalidation across @data-client/rest, /endpoint, /graphql, or /normalizr. Apply proactively when discussing data models, remote data shape, caching, normalization, identity, joins, polymorphism, mutable collections, or store consistency.
Design and audit data residency and regional operating models covering customer region commitments, data classification, storage, processing, backups, logs, analytics, search, AI providers, subprocessors, support/admin access, replication, failover, deletion, migrations, contracts, and proof. Use when customers or regulators require clarity about where data lives and moves.
Identify non-obvious signals, hidden patterns, and clever correlations in datasets using investigative data analysis techniques. Use when analyzing social media exports, user data, behavioral datasets, or any structured data where deeper insights are desired. Pairs with personality-profiler for enhanced signal extraction. Triggers on requests like "what patterns do you see", "find hidden signals", "correlate these datasets", "what am I missing in this data", "analyze across datasets", "find non-obvious insights", or when users want to go beyond surface-level analysis. Also use proactively when you notice interesting anomalies or correlations during any data analysis task.
Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.
Query Data912 market data endpoints for Argentina and USA instruments. Use when the user asks for MEP/CCL quotes, live Argentine market panels (stocks, options, cedears, notes, corporate debt, bonds), USA panels (ADRs, stocks), OHLC historical series by ticker, USA option chains, or volatility/risk metrics. Also use when the user mentions "Data912", "mep", "ccl", "cedears", "option chain", "historical bars", "OHLC", "implied volatility", "historical volatility", or "volatility percentiles" and expects API-backed market snapshots.
Designs comprehensive database schemas, including relational and NoSQL models, normalization, indexing strategies, relationship modeling, data types, constraints, and performance optimization. Covers entity-relationship diagrams, schema migrations, partitioning, and best practices for PostgreSQL, MySQL, MongoDB, and other databases. Use when designing databases, creating schemas, modeling data, optimizing queries, or when users mention "database design", "schema design", "data modeling", "ERD", "normalization", "indexing", or "database architecture".
Search 78 public scientific, biomedical, materials science, and economic databases via REST APIs. Covers physics/astronomy (NASA, NIST, SDSS, SIMBAD), earth/environment (USGS, NOAA, EPA), chemistry/drugs (PubChem, ChEMBL, DrugBank, FDA, KEGG, ZINC, BindingDB), materials (Materials Project, COD), biology/genomics (Reactome, UniProt, STRING, Ensembl, NCBI Gene, GEO, GTEx, PDB, AlphaFold, InterPro, BioGRID, Gene Ontology, dbSNP, gnomAD, ENCODE, Human Protein Atlas, Human Cell Atlas), disease/clinical (COSMIC, Open Targets, ClinicalTrials.gov, OMIM, ClinVar, GDC/TCGA, cBioPortal, DisGeNET, GWAS Catalog), regulatory (FDA, USPTO, SEC EDGAR), economics/finance (FRED, World Bank, US Treasury), demographics (US Census, Eurostat, WHO). Use when looking up compounds, genes, proteins, pathways, variants, clinical trials, patents, economic indicators, or any public database API query.
MongoDB and PostgreSQL database administration. Databases: MongoDB (document store, aggregation, Atlas), PostgreSQL (relational, SQL, psql). Capabilities: schema design, query optimization, indexing, migrations, replication, sharding, backup/restore, user management, performance analysis. Actions: design, query, optimize, migrate, backup, restore, index, shard databases. Keywords: MongoDB, PostgreSQL, SQL, NoSQL, BSON, aggregation pipeline, Atlas, psql, pgAdmin, schema design, index, query optimization, EXPLAIN, replication, sharding, backup, restore, migration, ORM, Prisma, Mongoose, connection pooling, transactions, ACID. Use when: designing database schemas, writing complex queries, optimizing query performance, creating indexes, performing migrations, setting up replication, implementing backup strategies, managing database permissions, troubleshooting slow queries.
Use when the user asks to generate a Substrait query plan, create a Substrait plan from natural language, convert a data query to Substrait JSON, write a Substrait DSL pipeline, translate a data request into a query plan, process a test entry from a JSONL dataset. Covers writing DSL code, calling MCP tools (compile_substrait_dsl, get_substrait_dsl_examples, load_test_entry), and self-correcting on compile errors. Trigger on: "generate substrait", "generate substrait dsl", "generate functional plan", "generate fp", "process entry", "run entry", "generate dsl".
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.