Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Use when the user wants to build or improve a sales bot's ability to identify emerging objections across campaigns. Also use when the user mentions "objection patterns," "objection learning," "new objection detection," "objection analysis," or "objection flagging."
Use when the user wants to build or improve a sales bot’s ability to enrich prospect data from multiple sources. Also use when the user mentions “prospect research,” “data enrichment,” “lead enrichment,” “prospect intelligence,” or “contact enrichment.”
Use when the user wants to build or improve a sales bot's ability to automatically categorize why deals closed or died. Also use when the user mentions "win/loss analysis," "deal outcome," "loss reason," "closed reason," or "deal categorization."
Use when the user wants to build or improve a sales bot's ability to pull in firmographic or contact data mid-conversation. Also use when the user mentions "data enrichment," "lead enrichment," "pulling company data," "contact data lookup," or "real-time data."
Use SellerSprite’s traffic keyword reverse lookup to query an ASIN for metrics such as keyword traffic sources, traffic share types, conversion types, organic and ad positions. Supports historical months and multidimensional sorting. Trigger this skill when users mention ASIN traffic keyword reverse lookup, traffic keyword lists, keyword traffic structure, organic/ad keyword analysis, keyword conversion types, SellerSprite traffic keyword, Amazon traffic keywords, or reverse ASIN keywords. Trigger it even if the user does not explicitly mention “SellerSprite,” as long as they want to view keyword traffic sources and keyword lists for an ASIN.
When the user wants to build or improve a sales bot's ability to automatically test message variations to optimize conversion. Also use when the user mentions "message testing," "A/B testing bots," "optimizing bot messages," "testing variations," or "message optimization."
Use when the user wants to build or improve a sales bot's ability to extract key data points (budget, timeline, company size, location, requirements) from unstructured prospect responses. Also use when the user mentions “extracting data,” “parsing responses,” “pulling out details,” “structured data from conversations,” or “NER for sales.”
Use SellerSprite’s market-listing capabilities to filter Amazon niche markets by category, with numerous criteria such as market size, competition, top-seller concentration, seller structure, new-product share, and price, rating, and gross-margin ranges. Discover markets to enter and evaluate product-selection directions. Trigger this skill when users mention Amazon market research, niche-category research, market-opportunity screening, market-concentration analysis, new-product opportunities, market selection, SellerSprite market research, or category market research. Even if the user does not explicitly mention “SellerSprite,” trigger this skill whenever the need is to filter and evaluate Amazon markets by category.
Create and modify Power BI report files in PBIR/PBIP format using the `powerbi-report-author` and `powerbi-desktop` CLIs. Use when the user wants to: (1) implement an approved report spec or design brief, (2) add or edit pages, visuals, filters, slicers, bookmarks, themes, or formatting, (3) validate PBIR and verify rendering in Power BI Desktop. For open-ended visual design, use `powerbi-report-design` first. For end-to-end requirements and approval workflow, use `powerbi-report-planning` first. Triggers: “edit PBIR,” “create Power BI report page,” “add visual to PBIP,” “format report visual,” “validate Power BI report,” “reload Desktop screenshot,” “implement an approved PBIP report spec,” “edit PBIR pages/visuals”
Mass-spec proteomics analysis — protein identification, quantification (LFQ, TMT, iTRAQ), differential expression (tumor vs normal, treatment vs control), PTM identification, and pathway enrichment on protein lists. Use when you have proteomics MS output, asking about protein abundance differences, or doing systems-level proteomic interpretation.
Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup.
Search and browse Walmart product listings by keyword, category, price range, and other criteria. Trigger this skill when the user mentions Walmart product search, Walmart product listings, Walmart price comparisons, Walmart competitor analysis, Walmart product selection research, Walmart market data, finding products on Walmart, Walmart search, Walmart products, Walmart product selection, Walmart pricing, Walmart competitors, or Walmart market. Trigger it even if the user does not explicitly mention “Walmart search,” as long as their request involves searching for products on Walmart, checking product availability, comparing Walmart prices, or analyzing Walmart product listings.
Comprehensive drug-target intelligence—tissue expression (GTEx, HPA), pathways, protein interactions (STRING), variant landscape (ClinVar, gnomAD), and druggability (DGIdb, ChEMBL approved drugs). Includes 9 parallel research paths with citations. Use for full target profile reports, target characterization for drug discovery, and “tell me about target X” queries.
When the user wants to build or improve a sales bot's ability to extract market insights from prospect conversations. Also use when the user mentions "competitive intelligence," "market insights," "competitor intel," "market research," or "conversation mining."
Use multimodal AI to analyze product main images and extract visual features and prompts. Trigger this skill when users mention analyzing product images; extracting visual attributes from product images; identifying colors, shapes, materials, or styles in product listings; reverse-engineering image prompts; batch visual feature extraction; turning product image information into structured data; visual attribute statistics; image-based product classification; or main image analysis, image feature extraction, visual attribute recognition, product image analysis, image classification, or batch image analysis. Trigger it even if users do not explicitly mention “image analysis,” as long as their needs involve extracting structured information from product main or secondary images.
Spatial transcriptomics analysis — Visium, MERFISH, seqFISH, Slide-seq. Maps gene expression to tissue architecture, identifies spatially variable genes (SVGs), segments tissue domains, and infers cell-cell interactions. Use for spatial gene-expression questions, tissue architecture analysis, and SVG identification.
Synthesize qualitative and quantitative user research into structured insights and opportunity areas. Use when analyzing interview notes, survey responses, support tickets, or behavioral data to identify themes, build personas, or prioritize opportunities.
Build with D1 serverless SQLite database on Cloudflare's edge. Use when: creating databases, writing SQL migrations, querying D1 from Workers, handling relational data, or troubleshooting D1_ERROR, statement too long, migration failures, or query performance issues. Prevents 14 documented errors
Use when the user wants to build or improve a sales bot's ability to learn from deal outcomes. Also use when the user mentions “feedback loop,” “outcome learning,” “win/loss learning,” “continuous improvement,” or “model training.”
Tokenizes and analyzes product titles to extract attribute dimensions such as word frequency, scene terms, audience terms, and material terms. Use this skill when the user wants to analyze product titles, extract high-frequency title terms, tokenize titles, discover scene or audience terms, compare title keyword usage across products, optimize Listing titles based on word frequency, identify common attribute patterns across a group of ASINs, or perform title tokenization, word frequency analysis, scene keyword extraction, audience keyword analysis, title optimization, attribute keyword extraction, or keyword frequency analysis. Trigger this skill even if the user does not explicitly say “title analysis,” as long as they want to break product titles into meaningful phrases, count keyword frequency, or group products by extracted attributes.
| Nuxt 4 server-side development with Nitro: API routes, server middleware, database integration, and backend patterns. Use when: creating server API routes, implementing server middleware, integrating databases (D1, PostgreSQL, Drizzle), handling file uploads, implementing WebSockets, or building backend logic with Nitro
Use when the user wants to test and optimize sales approaches, outreach sequences, or pitch variations. Also use when the user mentions "test this pitch," "A/B test outreach," "experiment with messaging," "test subject lines," "compare approaches," or "sales experiment." For tracking sales metrics, see analytics-tracking.
Use when the user wants to build or improve a sales bot's ability to test individual message variants. Also use when the user mentions "message testing," "A/B testing messages," "variant testing," "message optimization," or "reply testing."
Search and browse product listings across multiple international eBay sites. Activate when the user mentions eBay product search, eBay listing lookup, eBay price comparison, eBay market browsing, sold items, eBay auction search, eBay product research, eBay search, eBay products, eBay pricing, eBay competitors, sold items, eBay auctions, or eBay market analysis. Also activate even if the user does not explicitly mention "eBay" whenever their request involves searching for products on eBay, comparing eBay prices, finding completed listings, or analyzing eBay market data.
Use when the user wants to build or improve a sales bot's ability to send messages or make calls when prospects are most likely to engage. Also use when the user mentions "best time to send," "send time optimization," "engagement timing," "when to call," or "optimal contact times."
This skill activates for web scraping and Actor development. It proactively discovers APIs via traffic interception, recommends optimal strategy (traffic interception/sitemap/API/DOM scraping/hybrid), and implements iteratively. For production, it guides TypeScript Actor creation via Apify CLI.
When the user wants to build or improve a sales bot's ability to automatically update CRM fields from conversations. Also use when the user mentions "CRM automation," "field population," "data entry automation," "conversation to CRM," or "auto-fill fields."
Use SellerSprite’s market statistics feature to create category-node market dashboards. Includes average ratings, average prices, BSR, sales volume, seller counts, and new-product metrics for top listings, helping quickly assess market quality and competition in a category. Trigger this skill when users mention category market statistics, market selection dashboards, basic market assessment, node market quality, top-product statistics, SellerSprite market statistics, or category statistics. Trigger it even if the user does not explicitly mention "SellerSprite" as long as they want aggregated statistics by category node.
Use SurrealDB from JavaScript and TypeScript with the official surrealdb SDK, covering connecting (WebSocket/HTTP and embedded engines), authentication, CRUD, parameterized queries, and live queries. Use when connecting to SurrealDB from Node, Deno, Bun, or the browser, using the surrealdb npm package, or performing CRUD and real-time operations from JS/TS code. Triggers: surrealdb JS, surrealdb.js, new Surreal(), db.query, db.create, db.live, TypeScript SDK, npm i surrealdb.
Retrieve gene expression and omics datasets from ArrayExpress and BioStudies with gene disambiguation and quality assessment. Use for finding RNA-seq/microarray datasets by organism/tissue/condition, comparing across studies (case-control, time-series, dose-response), and assessing dataset suitability before downloading. Always uses English search terms.
RNA-seq differential expression analysis with DESeq2, edgeR, and limma-voom — DEG lists, fold changes, dispersion estimation, design formulas including covariates, multi-condition contrasts, and Venn-set operations across groups. Routes across DESeq2 (default), edgeR (QL-F / exact test for small replicate counts), and limma-voom (large n / complex designs). Use when you have a count matrix + metadata, want to find DEGs, or need dispersion/PCA/clustering analysis. Includes RULE ZERO precedence (read executed.ipynb if present).
Advanced Amazon product search and filtering based on Keepa data, with multiple criteria including category, price, monthly sales, keywords, BSR rank, review count, rating, package dimensions, weight, and shipping method. Trigger this skill when the user mentions Keepa product selection, Amazon product search, advanced product selection, BSR filtering, selection by sales rank, monthly sales filtering, keyword or category selection, competitor screening, niche product discovery, historical rank filtering, Keepa product selection, advanced product selection, BSR filtering, sales filtering, category search, competitor screening, historical data filtering, or Amazon product selection. Trigger it even without an explicit mention of “Keepa” when the request involves multi-criteria Amazon product search, filtering products by sales metrics, or advanced selection beyond simple keyword search.
For drill-down analysis of products by brand on MPSTATS for Ozon Russia. Returns all products under an Ozon brand display name (in Russian or Latin script), with full metrics including sales volume, revenue, price, rating, inventory, turnover, and lost sales. Supports multidimensional numeric filtering, sorting, and currency conversion. Use for brand benchmarking, competitor analysis, brand assortment research, and analysis of bestsellers at the ASIN (productId) level. Trigger when the user mentions Ozon brand drill-down, Ozon brand products, Ozon competitor brand analysis, brand assortment, brand SKUs, brand bestsellers, Ozon brand sales, MPSTATS brand, Ozon brand products, brand drill-down, brand competitor analysis, Russian marketplace brand SKUs, or brand revenue share. Trigger this skill even if the user does not explicitly mention “MPSTATS,” as long as they intend to view all products under an Ozon brand and their sales, prices, or ratings.
Explains how to query PostHog data, defaulting to typed runners for supported product analytics. Read it before you write HogQL/SQL. Also read it before you call execute-sql against PostHog. Use it to find or aggregate PostHog entities. These entities include insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, warehouse data, and persons. Use it for trends, funnels, retention, lifecycle, paths, stickiness, web analytics, error tracking, logs, sessions, and LLM traces. Before you calculate a governed business or telemetry measure, check system.information_schema.metrics for an approved definition. Examples include MRR, activation, billable usage, active organizations, and failure rates. Use the approved definition before you derive a measure from raw events or use a typed domain tool. It also covers HogQL differences, system table schemas, functions, query examples, and schema discovery
Anti-detection browser automation using Camoufox (Firefox fork with C++ fingerprint spoofing). Use when standard browser tools are blocked by Cloudflare, Akamai, or bot detection. Triggers include “stealth browse”, “anti-detection”, “bypass bot”, “camofox”, “blocked by Cloudflare”, scraping protected sites (X/Twitter, Amazon, Product Hunt), or when agent-browser/playwright fails with bot detection errors.
Guides agents through experiment creation: reading the project's setup with experiment-setup-context, defining the hypothesis, configuring rollout and bucketing, setting up analytics and running time, and reporting which choices are guesses. Delegates rollout decisions to configuring-experiment-rollout and metric setup to configuring-experiment-analytics.\nTRIGGER when: user asks to create a new experiment or A/B test, OR when you are about to call experiment-create.\nDO NOT TRIGGER when: user is updating an existing experiment, managing lifecycle, or only browsing experiments.
Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. Use when working with geographic data for spatial analysis, geometric operations, coordinate transformations, spatial joins, overlay operations, choropleth mapping, or any task involving reading/writing/analyzing vector geographic data. Supports PostGIS databases, interactive maps, and integration with matplotlib/folium/cartopy. Use for tasks like buffer analysis, spatial joins between datasets, dissolving boundaries, clipping data, calculating areas/distances, reprojecting coordinate systems, creating maps, or converting between spatial file formats.
Statistical modeling — linear/logistic/ordinal/Poisson regression, ANOVA, Kruskal-Wallis, chi-square, Mann-Whitney, Cox survival, spline fits (R `ns()`), odds ratios, Cohen's d, F-statistic, and p-value computation. Specializes in clinical-trial AE analysis (SDTM DM/AE), severity ordinal regression, and per-feature statistical workflows.
Query real-time ZenMux account data via the Management API: subscription detail, account status, quota usage (5h/7d/monthly), Flow rate, PAYG balance, per-generation cost/tokens, timeseries trends, model leaderboards, and provider market share. Use when the user wants current usage, remaining quota, credits, balance, bonus credits, Flow rate, generation cost, token/cost trends, top models, rankings, or provider share. Trigger on "check my usage", "quota left", "my balance", "subscription status", "Flow rate", "generation cost", "usage trend", "top models", "leaderboard", "market share", "provider breakdown", "查用量", "余额", "配额", "订阅详情", "Flow 汇率", "额度还剩多少", "使用趋势", "排行榜", "模型排名", "供应商占比". Do not use for docs, setup, top-up, troubleshooting, or code-writing.
When the user wants to build or improve a sales bot's ability to update lead scores dynamically during conversations. Also use when the user mentions "real-time scoring," "dynamic lead scoring," "propensity scoring," "live scoring," or "conversation scoring."
When the user wants to build or improve a sales bot's ability to monitor sentiment over time. Also use when the user mentions "sentiment trends," "tone tracking," "campaign sentiment," "aggregate sentiment," or "sentiment monitoring."
How to query the document_embeddings table for raw signal data using HogQL. Use for semantic search over signals, fetching every signal that contributed to a specific report, or listing signal types. To browse the curated report layer (the Inbox)—list reports, filter by status/source, or drill into a report by ID—use the `inbox-exploration` skill first; use this skill afterward if the user wants the underlying observations
When the user wants to build or improve a sales bot's ability to estimate deal timelines based on conversation patterns. Also use when the user mentions "close prediction," "deal timeline," "sales cycle estimation," "forecast timing," or "deal velocity."
Google Maps scraper for lead generation. Turns a business type and a place into a clean CSV of local businesses by driving the gosom/google-maps-scraper engine, running locally in Docker as a REST API on localhost:8080. Returns 8 lead fields by default (name, phone, email, website, category, address, rating, and review count), plus optional Instagram, Facebook, and LinkedIn profiles or all ~34 raw fields. Use when the user wants a lead list, “a list of [businesses] in [place],” local business data, contact enrichment for places (emails, phones, social profiles), or a whole-city run beyond Google’s ~120 results per search. Do not use for scraping Instagram, TikTok, YouTube, X, or any other social media platform directly
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.