Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
ZoomInfo platform help — SalesOS, MarketingOS, OperationsOS, Copilot, API, integrations. Use when ZoomInfo searches aren't returning the right prospects, enrichment data is incomplete or stale, intent signals aren't surfacing target accounts, Engage sequences have low reply rates, advertising audiences aren't matching your ICP, FormComplete isn't auto-filling leads, data orchestration rules aren't firing, or Copilot recommendations seem off. Do NOT use for general enrichment strategy (use /sales-enrich), general intent strategy (use /sales-intent), general cadence design (use /sales-cadence), general data hygiene strategy (use /sales-data-hygiene), or general B2B advertising strategy (use /sales-b2b-advertising).
CLI toolkit for SAM/BAM/CRAM: sort, index, convert, filter, QC alignments. Core commands: view, sort, index, flagstat, stats, depth, markdup, merge. Required between alignment and variant/peak calling. Use pysam for Python-native BAM access; deeptools for normalized coverage tracks.
Use when the user has scientific data (or a prompt alluding to scientific data) and wants a publication-quality figure made from it. A generator drafts and renders a figure that lands a frozen communication goal; an adversarial critic critiques it hard and grades it 1-5 per axis against a fixed rubric (message, aesthetic, clarity, integrity, and a conditional domain-completeness axis), aggregates to 0-100, and decides pass; the generator revises against the critic's findings until the grade clears a threshold or the budget is hit. Both roles may consult the literature (Semantic Scholar + arXiv) to verify domain content (e.g. a pathway figure's gene set, or a benchmark's reported numbers), and conform to / grade against a named journal's figure spec fetched via web search. Not for writing a paper or analyzing a dataset, and not for editing an existing finished image — this renders a figure from data/brief and iterates on it.
Translate natural language to SQL, optimize query performance, and interpret EXPLAIN plans for SQLite and PostgreSQL. Triggered when users ask to convert questions into SQL, improve slow queries, tune indexes, analyze execution plans, or mention keywords like NL2SQL, query tuning, or full table scan.
Design and analyze A/B tests with proper statistical methodology including sample size calculation, randomization, frequentist and Bayesian approaches, and sequential testing. Use this skill when the user needs to set up an experiment, calculate required sample size, interpret test results, or decide between testing methodologies — even if they say 'should we A/B test this', 'how many users do we need', 'is the test result conclusive', or 'can we stop the test early'.
Conduct statistical hypothesis testing including null/alternative hypothesis formulation, p-values, Type I/II errors, and test statistic selection. Use this skill when the user needs to determine whether a result is statistically significant, choose the right statistical test, interpret p-values correctly, or evaluate research findings — even if they say 'is this result significant', 'which statistical test should I use', or 'what does this p-value mean'.
Generate professional company tear sheets using S&P Capital IQ data via the Kensho LLM-ready API MCP server. Use this skill whenever the user asks for a tear sheet, company one-pager, company profile, fact sheet, company snapshot, or company overview document—especially when they mention a specific company name or ticker. Also trigger when users ask for equity research summaries, M&A company profiles, corporate development target profiles, sales/BD meeting prep documents, or any concise single-company financial summary. This skill supports four audience types: equity research, investment banking/M&A, corporate development, and sales/business development. If the user doesn't specify an audience, ask. Works for both public and private companies.
Detects and removes duplicate transactions across overlapping bank, credit-card, and brokerage statement imports using a stable composite key (account_id, date ±1d, amount_cents, description_normalized). Emits a list of new transactions to commit, a list of suppressed duplicates with their reasons, and a list of suspicious near-duplicates that need human review. Use when ingesting financial statements that may overlap prior drops, merging multiple export sources for the same account, or when user mentions duplicate transactions, deduping a transaction file, or reconciling overlapping statements.
Design and audit usage-metering accuracy for usage-based pricing, credits, quotas, overages, AI/token billing, API calls, seats, storage, event ingestion, idempotency, late events, aggregation, reconciliation, invoices, customer visibility, disputes, corrections, and revenue leakage. Use when billable usage must be trusted by customers and finance.
Fetch web page content via Chrome DevTools Protocol (CDP). Full JS rendering, handles redirects (including Google News). Use when you need to read the text content of a web page, scrape articles, or extract information from URLs. Zero dependencies — Python 3 stdlib only. Cross-platform (Mac, Windows, Linux).
Use xlsx binary for Excel file manipulation including viewing, SQL-like filtering, cell editing, conversion to/from CSV, and data analysis operations. Use this instead of Python (openpyxl, pandas, xlrd) or Node.js libraries for ALL .xlsx file operations — reading, writing, filtering, conversion, and analysis. Trigger on any request involving .xlsx or Excel files.
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.
AI Agent-driven Kaggle competition workflow. Learn from real competition experience: score stabilization patterns, submission troubleshooting, kernel workflows, GPU task delegation, and the spec-driven development approach that achieved top leaderboard positions. Use when: working on any Kaggle competition, analyzing submission failures, setting up automated pipelines, or replicating top notebook solutions.
Design and analyze factorial experiments to identify significant process factors and optimize settings. Use this skill when the user needs to systematically test factor effects, optimize a manufacturing process, or determine which variables matter most — even if they say 'which factors affect quality', 'optimize process settings', or 'design an experiment'.
Implement text summarization using extractive and abstractive approaches. Use this skill when the user needs to condense long documents, build an automatic summarization pipeline, or compare summarization strategies — even if they say 'summarize this document', 'TLDR', or 'key points extraction'.
Implement Elo rating system to rank items or players from pairwise comparison outcomes. Use this skill when the user needs to rank items from head-to-head matchups, build a competitive rating system, or evaluate relative quality from comparison data — even if they say 'player rating', 'ranking from comparisons', or 'competitive scoring system'.
Implement a web crawler pipeline covering URL discovery, fetching, parsing, and storage. Use this skill when the user needs to build a site crawler, audit website structure, or collect web data systematically — even if they say 'scrape a website', 'crawl all pages', or 'site audit spider'.
This skill helps users extract structured product listings from Amazon, including titles, ASINs, prices, ratings, and specifications. Use this skill when users want to search for products on Amazon, find the best selling brand products, track price changes for items, get a list of categories with high ratings, compare different brand products on Amazon, extract Amazon product data for market research, look for products in a specific language or marketplace, analyze competitor pricing for keywords, find featured products for search terms, get technical specifications like material or color for product lists.
Call Newton's C 2.6 fusion model (`Newton::c2_6_8b_fp8_260424d7a55d5e`) on the prod `/query` endpoint with text, image, and video inputs in a single stateless request — no session, no batch job, no SSE plumbing. Use this skill when the user wants per-call multimodal reasoning (describe an image, summarize a clip, classify a state from sensor + visual context) without managing session lifecycle, or when they need the Newton C checkpoint that reasons over video frames via `/query`. Covers the request shape per modality, the two image-attachment paths (file_ids vs base64), multi-image mode, both video paths (`.mp4` + `max_frames`, and client-sampled frames + `query_metadata`), generation parameters, JSON-output prompting, latency budgets, and the C 2.6 identifier gotcha. Do NOT use for streaming / session-based activity monitoring, large multi-file batch jobs, or time-series embedding (KNN / anomaly) classification.
World-class backend engineering - distributed systems, database architecture, API design, and the battle scars from scaling systems that handle millions of requestsUse when "backend, api, database, postgres, mysql, mongodb, redis, graphql, rest, authentication, authorization, caching, queue, background job, webhook, migration, transaction, n+1, rate limit, server, node.js, python, go, backend, api, database, architecture, performance, reliability, security" mentioned.
Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs. Use when developing trading algorithms, validating strategies, or building backtesting infrastructure.
Fit Bayesian regression models with PyMC using the Hogg approach — start simple, diagnose problems, upgrade the likelihood. Use when the user needs regression with proper uncertainty quantification, heteroscedastic errors, outlier robustness, or model comparison. Covers Normal, Student-t, and GLM likelihoods with ArviZ diagnostics and LOO-CV.
CLI for VCF/BCF: filter, merge, annotate, query, normalize, compute stats. Core post-variant-calling: quality filtering, multi-sample merging, rsID annotation, genotype extraction. Samtools companion in HTSlib. Use GATK for complex indel realignment during calling; use VCFtools for population genetics stats.
BettaFish (微舆) multi-agent public opinion analysis system — based on a three-engine parallel architecture with QueryAgent, MediaAgent, and InsightAgent, using ForumEngine to enable collaborative discussion among Agents, and generating dual-format reports: Word/PDF plus high-design-quality HTML. Trigger this skill when the user needs the following analyses: - Analyze the social media reputation and word-of-mouth of a brand/company/product - Track trending public opinion events (such as a car company being criticized or a celebrity controversy) - Mine the content and influence data of specific social media accounts - Monitor competitor public opinion dynamics and compare multiple brands - Analyze public sentiment and attitudes toward a topic - Generate public opinion monitoring reports or crisis warning analyses - Need formal reports in Word document/PDF format - Need high-design-quality interactive HTML visualization reports - Need in-depth public opinion analysis based on real data This skill uses the QueryAgent + MediaAgent + InsightAgent parallel architecture, enables discussion and collaboration among Agents via ForumEngine, runs 3 rounds of reflection loops to optimize analysis results, and finally outputs: 1. **Word/PDF documents** — generated with the docx/pdf subskill, suitable for formal reporting, printing, and archiving 2. **High-design-quality HTML reports** — using the frontend-design subskill, with a distinctive editorial magazine style and interactive visualizations **No databases or mock data are used**; all data is fetched in real time via WebSearch/WebFetch/Browser/Curl. Even for complex multi-step analysis needs, integration of multiple data sources, or generating professionally formatted public opinion reports, be sure to use this skill.
Use this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts, validating compliance, converting DICOM to BIDS, writing metadata sidecars, or creating BIDS derivatives.
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases
Primary Python toolkit for molecular biology. Preferred for Python-based PubMed/NCBI queries (Bio.Entrez), sequence manipulation, file parsing (FASTA, GenBank, FASTQ, PDB), advanced BLAST workflows, structures, phylogenetics. For quick BLAST, use gget. For direct REST API, use pubmed-database.
Fast short-read DNA aligner for WGS/WES/ChIP-seq. 2× faster BWA-MEM successor; outputs SAM/BAM with read group headers for GATK. Primary plus supplementary records for chimeric reads. Use STAR for RNA-seq splice-aware alignment; Bowtie2 is a comparable alternative.
Designs and optimizes Clay-powered GTM workflows for prospecting, signal detection, outbound email sequences, enrichment pipelines, and account-based marketing. Use when the user mentions 'Clay,' 'GTM engineering,' 'prospecting,' 'signal detection,' 'enrichment,' 'Claygent,' 'outbound automation,' or wants to build Clay tables or integrate with sequencing tools like Lemlist, Smartlead, or Instantly.
Build, review, debug, configure, migrate, teach, or plan ClickHouse analytics work from TypeScript with current docs and a full usage guide. Use for @clickhouse/client, @clickhouse/client-web, createClient, query, insert, command, exec, JSONEachRow, query_params, streaming, MergeTree family, ORDER BY/PARTITION BY, materialized views, projections, async_insert, FINAL, lightweight deletes and updates, 26.x server upgrades, ClickHouse Cloud HTTPS, system.query_log, and TS schema/ingest patterns. TypeScript/Node SDKs only — not Python/Go/Java clients.
Query the ClinPGx (formerly PharmGKB) REST API plus the CPIC PostgREST companion API for pharmacogenomic clinical annotations, CPIC/DPWG dosing guidelines, gene-drug pairs, variant-drug associations, FDA/EMA drug labels, and PGx pathways. Two-host architecture: api.clinpgx.org for annotation records, api.cpicpgx.org for genotype→recommendation lookups. No auth. For germline pathogenicity use clinvar-database; for somatic cancer PGx use cosmic-database or opentargets-database; for drug bioactivity use chembl-database-bioactivity.
Use this skill when the user asks to "convert this page to markdown", "extract this webpage", "save this article", "grab content from URL", "get markdown from this link", "scrape this page", provides a URL to extract, or wants clean web content without ads and clutter
Paid API marketplace for AI agents via Corbits. Search hundreds of premium API proxies, call them with automatic USDC micropayments (x402 protocol), and fund the payment wallet with MoonPay. Use when the user wants to access paid data APIs (crypto prices, weather, financial data, etc.) with per-request billing and no API key management.
This skill should be used when users need to analyze CSV or Excel files, understand data patterns, generate statistical summaries, or create data visualizations. Trigger keywords include "analyze CSV", "analyze Excel", "data analysis", "CSV analysis", "Excel analysis", "data statistics", "generate charts", "data visualization", "分析CSV", "分析Excel", "数据分析", "CSV分析", "Excel分析", "数据统计", "生成图表", "数据可视化".
Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts. BOOTSTRAP MODE - Triggers: "Create a data context skill", "Set up data analysis for our warehouse", "Help me create a skill for our database", "Generate a data skill for [company]" → Discovers schemas, asks key questions, generates initial skill with reference files ITERATION MODE - Triggers: "Add context about [domain]", "The skill needs more info about [topic]", "Update the data skill with [metrics/tables/terminology]", "Improve the [domain] reference" → Loads existing skill, asks targeted questions, appends/updates reference files Use when data analysts want Claude to understand their company's specific data warehouse, terminology, metrics definitions, and common query patterns
Check preprocessing, splits, leakage, augmentation, label noise, and distribution mismatch before blaming the model. Use for new datasets, suspicious gains, brittle generalization, unexplained train-test gaps, or any result that may be caused by data pipeline bugs rather than model behavior.
World-class database schema design - data modeling, migrations, relationships, and the battle scars from scaling databases that store billions of rowsUse when "database schema, data model, migration, prisma schema, drizzle schema, create table, add column, foreign key, primary key, uuid, auto increment, soft delete, normalization, denormalization, one to many, many to many, junction table, polymorphic, enum type, index strategy, database, schema, migration, data-model, prisma, drizzle, typeorm, postgresql, mysql, sqlite" mentioned
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.