Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Comprehensive ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) profiling for drug candidates. Integrates ADMET-AI predictions, SwissADME drug-likeness, PubChemTox experimental toxicity, ChEMBL clinical data, Lipinski rule-of-five, and CYP interaction data. Use for drug-likeness assessment, BBB penetration, bioavailability, hepatotoxicity prediction, ADME/PK profiling, or screening compound libraries before lab testing
Collecting and synthesizing user feedback across channels (support tickets, NPS, in-app feedback, sales calls, social mentions, customer councils) into a continuous signal that informs product decisions. The triage discipline that distinguishes loudest-voice (whoever complains most wins) from averaged-noise (every signal weighted equally) from triaged-synthesis (signal weighted by source quality, frequency, and decision relevance). Triggers on user feedback, customer feedback aggregation, NPS, support ticket analysis, customer councils, feedback synthesis, voice of customer, feedback triage, in-app feedback. Also triggers when feedback channels overflow with volume that does not produce decisions, when the loudest-voice problem is steering roadmap, or when continuous feedback streams need synthesis discipline.
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
DataWorks infrastructure management: create and query data sources (50 types), compute resources, and Serverless resource groups, as well as test connectivity and bind or unbind resource groups. Uses aliyun CLI to call the dataworks-public OpenAPI (2024-05-18). Trigger keywords: DataWorks data source, compute resource, resource group, datasource, data source, compute resource, resource group, mysql/hologres/maxcompute data source, holo/mc/flink resource, Serverless resource group, DataWorks infra, create/list datasource, DW environment config, infrastructure initialization, connect database to DataWorks, database connection failure, configure holo/mc resource. Do not trigger for: data development tasks, scheduling configuration, MaxCompute table management, data integration tasks, ECS/RDS/OSS operations, workspace member management, data quality monitoring, data lineage, or data preview.
Find the root cause of a slow ABAP SQL or Fiori-Elements OData request and propose the cheapest fix — GUI-free via ARC-1 (odata_perf sap-statistics timing split, cds_sql "Show SQL", SAPQuery execution metrics, ST05 SQL-trace control, ABAP profiler traces), escalating to SAP GUI / HANA only for trace records and execution plans. Use when a report, transaction, Fiori list, CDS view, or OData entity is slow, a query times out under load, or someone asks "why is this SQL/OData so slow" or "where is the time going".
Query and analyze real-time trending topics and searches on Google Trends for a specified time range and country or region. Trigger this skill when users mention Google Trends, hot topics, real-time trending searches, popular trends, current hot topics, recent trends, viral topics, trends over a time period, regional trend analysis, real-time hot topics, trending topics, popular trends, recent trending searches, or trend discovery. Trigger it even if users do not explicitly say “Google Trends” when they want to discover recent or emerging topics and search terms in a specific market.
TAM/SAM/SOM calculator with deep market research. Produces comprehensive market-sizing.md with top-down and bottom-up estimates, methodology, data sources, assumptions, sensitivity ranges, growth projections, competitive landscape, and Mermaid visualizations. Use when user needs market size estimates, addressable market analysis, go-to-market sizing, investor-ready market analysis, or business plan market validation.
Memory retrieval internals: knowledge graph orchestration with entity extraction, natural language query parsing, deduplication (>85% similarity), and cross-reference boosting over unified recency, relevance, and authority ranking. Use when designing or debugging how memory search itself works. Everyday lookups belong to memory; entry storage to remember; consolidation to dream.
Designs retrieval-augmented generation pipelines for document-based AI assistants. Includes chunking strategies, metadata schemas, retrieval algorithms, reranking, and evaluation plans. Use when building "RAG systems", "document search", "semantic search", or "knowledge bases".
End-to-end drug safety review integrating FDA labels, FAERS adverse event reports, PRR/ROR disproportionality, pharmacogenomic biomarkers, clinical trial data, and published literature. Use for regulatory drug safety reviews, comprehensive pharmacovigilance reports, label-vs-real-world AE comparison, and clinical decision support for drug safety.
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.
Wire a semantic layer into a nao agent so that metric queries are routed through a single source of truth. Supports dbt MetricFlow (dbt Cloud with Semantic Layer), Snowflake (views or semantic views via MCP), an in-house nao YAML semantic layer, or other tools (via MCP discovery). Installs the right MCP server, updates RULES.md to route metric queries through the semantic layer, and (for the nao YAML option) generates starter metric files. Use after a first round of tests has shown the agent struggling with metric reliability. Do not use for raw rule writing (write-context-rules) or first-time setup (setup-context).
DatoCMS CLI (datocms) — command-line migrations, schema codegen, schema inspection, one-off CMA calls, typed TypeScript CMA scripts, env operations, deployment workflows, multi-project profile syncing. Use for datocms CLI commands/scripts: migrations:new, migrations:run; schema:generate; schema:inspect (dump models, blocks, fields, validators, appearance, fieldsets, nested blocks, referenced/embedding models); cma:call, cma:docs, cma:script (ad-hoc typed TS with ambient client/Schema globals); migration scaffolding for models/fields/blocks; CLI setup via datocms.config.json + profiles; OAuth (login/logout/whoami); projects:list; project link/unlink; env list/fork/promote/rename/destroy; maintenance-mode toggle; CI/CD migration pipelines; blueprint/client project sync; imports from WordPress or Contentful (assets + content); CLI plugin management.
Generate a CDS analytical model (star schema — cube + dimension + text views) on top of a RAP business object or a DDIC table. Use when asked to "create a star schema", "generate an analytical cube and dimensions", "make a RAP BO analytical", "build a CDS cube from a table", or "create an analytical model".
Search and analyze TikTok product data, including sales, influencer sales, pricing, and commission rates, across 16 TikTok Shop sites. Trigger this skill when users mention TikTok product search, TikTok Shop product analysis, TikTok sales data, influencer sales, TikTok product selection, TikTok commission rates, TikTok product rankings, EchoTik data queries, TikTok product search, TikTok sales, influencer sales, TikTok commission, TikTok product selection, short-video e-commerce, or TikTok data. Even if users do not explicitly mention “EchoTik” or “TikTok,” trigger this skill whenever their needs involve searching for products on TikTok Shop or analyzing TikTok product performance metrics.
Expert-level Snowflake data warehouse platform, virtual warehouses, data sharing, streams, tasks, and SQL optimization. Use when the user mentions data warehouse, SQL, analytics, or cloud, or when the task involves Architecture and Virtual Warehouses, Database Objects and Organization, Data Loading and Stages, or Streams and Tasks.
Histone-modification ChIP-seq, ATAC-seq accessibility, chromatin state, and TF binding analysis from ENCODE, Roadmap Epigenomics, ChIP-Atlas. Use for chromatin-state-by-tissue queries, TF-binding-by-region, regulatory landscape mapping, and ENCODE-cCRE annotations. For DNA methylation use tooluniverse-epigenomics; for RNA-seq use tooluniverse-rnaseq-deseq2
GPCR receptor pharmacology — agonist/antagonist/inverse-agonist/biased-agonist classification, GPCRdb structural data, receptor-ligand binding analysis, antibody-target interface (SAbDab). Use for GPCR drug discovery, biased-agonism analysis, receptor subtype selectivity questions, and orthosteric vs allosteric pocket characterization
Find and retrieve proteomics datasets from MassIVE, ProteomeXchange, PRIDE Archive, and the NCI Proteomics Data Commons (PDC). Search by species, keyword, accession, or protein; retrieve detailed metadata (instruments, publications, species, PTMs studied), real file-download URLs (PRIDE), or quantitative abundance matrices with clinical linkage (PDC/CPTAC). Use for locating public proteomics datasets to reanalyze, comparing instrument/protocol coverage across studies, pre-download dataset evaluation, and finding every dataset that identified a specific protein.
Biological sequence analysis — gene/protein sequence retrieval (NCBI, Ensembl, UniProt), nucleotide/protein search, ortholog discovery, and FASTQ QC + alignment workflows (Trimmomatic, BWA, samtools, coverage depth). Use for sequence retrieval, sequence comparison, FASTQ QC analysis, and read alignment pre-processing
Subscribe to AI and tech RSS feeds and persist normalized metadata into SQLite using mature Python tooling (feedparser + sqlite3). Use when adding feed URLs/OPML sources, running incremental sync with deduplication, and storing entry metadata without full-text extraction or summarization
Build RAG pipelines with Exa.ai for real-time web retrieval. Use when building retrieval-augmented generation, integrating Exa with LangChain, LlamaIndex, Vercel AI SDK, or implementing AI agents with web search capabilities. Triggers on: RAG pipeline, retrieval augmented generation, Exa LangChain, Exa LlamaIndex, ExaSearchRetriever, ExaSearchResults, Exa MCP, Exa tool calling, Claude tool use, AI agent web search, grounded generation, citation generation, fact checking, hallucination detection, OpenAI compatibility, chat completions.
Investigate AI observability evaluations — `hog` (deterministic code-based), `llm_judge` (LLM-prompt-based), and `sentiment` (user-message sentiment). Find existing evaluations, inspect their configuration, run them against specific generations, query individual results, and set up scheduled reports on an evaluation. Use when the user asks to debug why an evaluation is failing, surface common failure modes, compare results across filters, dry-run a Hog evaluator, prototype a new LLM-judge prompt, inspect sentiment classifications, or manage the evaluation lifecycle.
Filter Etsy products by multiple criteria (keywords/URL, price, sales, favorites, reviews, listing date, category, types such as handmade/vintage, and tags such as Pick/Bestsell/Raving). Triggers when users mention Etsy products, Etsy listings, Etsy product selection, Etsy bestsellers, Etsy handmade, Etsy vintage, etsy items, or Etsy product searches. Also triggers when users search for products on Etsy, check sales/price/tags, or filter products, even without mentioning a tool name.
Seerfar Ozon keyword mining: Find keywords related to a seed keyword on Ozon (and Wildberries), filtering by multiple metrics such as search volume, growth, product count, seller count, competitor count, price, relevance, title density, and add-to-cart conversion. Return a market profile for each keyword, including monthly search volume, growth, market potential, competitor/seller counts, average price, add-to-cart conversion, and top products. Use for Ozon keyword expansion, long-tail keyword mining, and seed keyword opportunity analysis. Trigger this skill when the user mentions Ozon keyword mining, Ozon keyword expansion, Ozon long-tail keyword mining, finding related keywords around a term, Ozon low-competition keyword mining, Seerfar Ozon, Ozon keyword mining, Ozon keyword expansion, Ozon related keywords, or mine Ozon keywords. Even if the user does not explicitly mention “Seerfar,” trigger this skill if they intend to mine Ozon-related keywords around a seed term and view market profiles.
Predicts client renewal likelihood based on health score signals. Analyzes engagement, support, adoption, satisfaction, billing, stakeholder, and usage data to calculate a weighted Health Score (0-100), classify renewal risk, and generate a prioritized action plan with early warning signals and recommended save plays.
Gene-disease association analysis across DisGeNET, OpenTargets, Monarch, OMIM, GenCC, Orphanet, Gene2Phenotype (G2P). Cross-references multiple sources for evidence-graded association reports with concordance scoring (5/5 sources agree → strong, 1/5 → weak). Use for 'which diseases is gene X associated with' or 'which genes cause disease Y' queries with quantitative confidence, including clinical-panel-based curation (developmental disorders, cancer, cardiac, skeletal, eye, skin panels).
Small molecule identification, characterization, and procurement — PubChem, ChEMBL, BindingDB, ADMET-AI, SwissADME, eMolecules, Enamine. Covers compound name to structure to activity to ADMET properties to commercial sourcing. Use for chemical biology, lead identification, probe selection, and the full small-molecule discovery pipeline
Structural biology and proteomics integration for drug target validation. Combines PDB experimental structures, AlphaFold predictions, GPCRdb, SAbDab antibody structures, ProteinsPlus binding-site prediction, BindingDB ligand-affinity data, BMRB NMR data, CATH/InterPro fold classification, intrinsic-disorder prediction (MobiDB/DisProt/IUPred3), membrane-protein topology (OPM/TopDB/PDBTM/ChannelsDB), enzyme catalytic-site data (M-CSA), PDBe ligand/compound chemistry, and MD simulation trajectory metadata (MDDB). Use for druggability assessment, binding-site characterization, ligand-pocket analysis, structural-confidence scoring (resolution, pLDDT), antibody-target interface analysis, disordered-region assessment, membrane-protein topology, catalytic-mechanism lookup, and finding published MD simulations for a target.
Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.
Manage Alibaba Cloud Flink VVP instances and namespaces through create/query operations only. Use when user asks to create or query Flink instances, namespaces, regions, zones, or tags in Chinese or English. Reject Flink SQL/job requests, unrelated cloud services (ECS/Kafka/OSS/DataWorks), and all update/delete operations
Propose and execute rubric or bucket upgrades. Two modes: **full rubric bump** (highest-risk action, five mandatory steps + cross-model review) and **--bucket-only lightweight recalibration** (change bucket boundaries only, leave rubric formulas untouched). **Phase 2 must use a cheat-score-blind sub-agent to rescore the calibration pool**—self-scored fallback is not accepted. Trigger phrases: “升级 rubric”/“bump rubric”/“更新公式”/“我想加一个维度”/“调整权重”/“重校桶”/“recalibrate bucket”。
Convex backend development guidelines. Use when writing Convex functions, schemas, queries, mutations, actions, or any backend code in a Convex project. Triggers on tasks involving Convex database operations, real-time subscriptions, file storage, or serverless functions.
Generate an analytical CDS query (transient projection view with PROVIDER CONTRACT ANALYTICAL_QUERY) on top of an existing analytical cube. Use when asked to "create an analytical query", "build a KPI query on a cube", "generate an ANALYTICAL_QUERY view", or "expose a cube for analytics/embedded analytics".
Google Tag Manager implementation reference for web and server containers. Use when installing a GTM container snippet, configuring tags, triggers or variables, designing dataLayer pushes, setting up Consent Mode in GTM, debugging with Preview mode or Tag Assistant, building a custom template, setting up a server-side (sGTM) container, or automating containers through the GTM API or the bundled Stape MCP server. Do NOT use for gtag.js installs that bypass GTM, GA4 reporting or BigQuery export - use google-analytics; Adobe Launch, Tealium or other tag managers.
Generate HTML entity-relationship diagrams (ERDs) and database schema visualizations with clickable tables, relationship paths, and migration before/after views. Use whenever the user has a database schema, data model, or table structure to document, explain, migrate, or explore — even when they call it a “data model,” “schema diagram,” or just “the tables.” Reach for this any time the conversation touches database structure with more than ~3 tables.
Query and analyze Amazon ABA (Brand Analytics) search term data, covering weekly data from the past three years across 15 marketplaces. Trigger this skill when users mention ABA data, Amazon search term analysis, keyword research, search ranking trends, market opportunity analysis, seasonal keywords, high-click low-conversion analysis, blue ocean keyword discovery, competitor keyword analysis, ABA data, search term report, keyword mining, search ranking trends, blue ocean keywords, click share, conversion share, seasonal keywords, market opportunity analysis, or competitor keywords. Trigger it even if the user does not explicitly mention “ABA”, as long as their request involves Amazon search term data and ranking analysis.
Create and manage scheduled PostHog subscriptions for insight snapshots, dashboard snapshots, and AI prompt reports. Use when a user wants recurring email, Slack, or Microsoft Teams delivery; an AI summary; delivery history; schedule or recipient changes; a test delivery; pause, resume, or deletion; or help with subscription permissions, limits, billing, and failures. Use product alerts when delivery must depend on a threshold or anomaly.
Connect GWAS variants to biological pathways and druggable targets. Maps GWAS hits to causal genes (via fine-mapping/eQTL), then to pathways (Reactome, KEGG, WikiPathways), then to existing drugs hitting those pathways. Use for pathway-level disease mechanisms, druggable-pathway prioritization from GWAS, SNP-to-pathway-to-target tracing, and tissue-specific eQTL evidence for drug target hypotheses.
Post-translational modification (PTM) analysis — phosphorylation, ubiquitination, acetylation, glycosylation, and methylation. Uses iPTMnet (sites and enzymes), ProtVar (functional consequences), UniProt (baseline), STRING, ELM (linear motifs), MassIVE/ProteomeXchange (experimental data), and the EBI Proteins API (mutagenesis, MS-proteomics/HPP peptide evidence, antigenic regions, genomic coordinates, and protein-level variant lookup by accession/dbSNP/HGVS) for cross-validation. Use for PTM site annotation, kinase-substrate identification, and PTM-disease associations.
Use when the user wants to seed Dataverse tables with realistic sample records so a freshly-scaffolded code app shows real-looking data on first launch. Generates contextually appropriate rows from each table's schema and inserts them in dependency order. Mirrors microsoft/power-platform-skills/power-pages/add-sample-data, adapted for mobile apps.
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.