Research & Data skills
Reference lookups, registries, directories and open-data sources, returned as structured records rather than rendered pages.
38 skills
amazon.comKDP Nonfiction Niche Finder
Validate a nonfiction book niche on Amazon against the four KDP niche-finder rules (BSR < 100k, 50-300 reviews, price floor $9.99+, and a 3-star review gap) by gathering market data from book search and product pages. Read-only.
americanreindustrialization.comAmerican Reindustrialization — Discover Companies & Jobs
Discover companies, startups, suppliers, and job opportunities across American reindustrialization — manufacturing, energy, defense, aerospace, robotics, semiconductors, and industrial software — via the site's public JSON REST API at /api/* (companies, jobs, categories, tags).
angeloakcapital.comFind ETF Listings and Sitemaps
Locate Angel Oak Capital Advisors' ETF investment listing and extract sitemap URLs and ETF investment links.
archive.orgWayback Machine Snapshot Search
Find Internet Archive Wayback Machine snapshots for a URL — single closest, date range, host/prefix enumeration, or full history — returning archived URL, capture timestamp, HTTP status, MIME type, SHA-1 digest, and WARC-record length. Read-only.
artificialintelligencecompanies.comFind AI Companies by Niche or Problem
Search artificialintelligencecompanies.com to find AI vendors and startups serving a given niche or addressing a given problem, returning name, canonical URL, and description per match via the site's public JSON API and JSON-LD category pages.
arxiv.orgarXiv Search Papers
Search arXiv for preprints by free-form query, field operators (ti/au/abs/cat/jr/co/rn), category, date range, or arXiv ID, and return structured paper records (title, authors, abstract, primary + cross-listed categories, submitted/updated dates, version, comments, journal_ref, DOI, PDF/abs URLs) plus total result count. Read-only.
binlp.peExtract brand identity colors and typography
Identify a site's primary brand colors and typography from its loaded CSS, computed styles, fonts, and logo assets.
books.google.nlSearch and inspect passages in Google Books scans
Search a Google Books volume by keyword, resolve matching scan pages, and extract page text with scan-page citations.
christianpicks.comSearch ChristianPicks Directory
Search and filter the ChristianPicks directory of 500+ Christian apps, software, businesses, ministries, books, and media by query, category, pricing model, platform, or popularity; surface product details, vendor links, and comparison-ready recommendations.
community.shopify.comRead Shopify Community Threads
Open a Shopify Community discussion directly and extract its title, authors, timestamps, and post text.
data.ontario.caEnumerate CKAN Datasets by Theme
Search and paginate Ontario CKAN catalog datasets matching one or more thematic keywords, optionally scoped to a resolved organization, and return deduplicated dataset metadata.
data.pa.govSearch Pennsylvania Registered Business Entities
Search Pennsylvania registered business records through the Commonwealth's official Socrata open-data system.
elestadodelperu.comFind the Latest Earthquake
Identify the most recent earthquake listed on elestadodelperu.com and return its displayed information and event URL.
embed-v2.testimonial.toExtract testimonials from a Testimonial.to wall
Extract exact testimonial text, brand, role, and headshot URL for named people from a Testimonial.to wall.
exa.aiExa Web Search MCP
Connect an MCP client to Exa's hosted Search MCP server for web search, page fetching, and optional advanced search, with setup snippets for common clients, API-key handling, tool selection, and troubleshooting.
- fairbourne.com
Find Portfolio Property Detail URLs
Extract property detail page URLs from the Fairbourne portfolio gallery.
goodreads.comFind Goodreads Lists Containing a Book
Resolve a book by title on Goodreads, then retrieve the lists that include it from the book-specific lists URL.
horizonsfoundation.orgExtract Organizations from the Horizons Foundation Directory
Extract every organization in the Horizons Foundation organization directory as spreadsheet-ready CSV with contact details and source URLs.
imdb.comFind the First IMDb Title Result with Filters
Resolve and open the first IMDb title result from a title search using technical and runtime filters.
inurdu.pkInUrdu.pk Name & Vocabulary Meaning Lookup
Look up a name's English + Urdu meaning, pronunciation, gender, syllables, origin, and lucky details on inurdu.pk — or fetch curated Urdu vocabulary lists by topic.
israeli.companyFind Israeli Tech Companies and Companies With Israeli Ties
Enumerate brand entries on israeli.company classified in the technology sector — Israeli-founded/owned firms and non-Israeli companies the site has documented as having ties to Israel — with optional per-brand verdict and metadata.
lifewise.orgFetch LifeWise School Name Search JSON
Retrieve and parse the LifeWise school-name search AJAX response using its direct state, charter, and query parameters.
madisonfunds.comInspect Madison Funds Key Highlights Tables
Locate and extract the DOM structure, raw header HTML, and row data of the Key Highlights table on Madison Funds fund or ETF detail pages.
- mcp.data.gouv.fr
data.gouv.fr MCP — Query, Extract & Structure Datasets
Drive the data.gouv.fr MCP server (mcp.data.gouv.fr/mcp, server v1.27.1, MCP protocol 2025-06-18, Streamable HTTP + SSE) to search datasets, organizations, and third-party APIs, then normalize each hit into a clean reusable JSON record (title, description, organization, license, frequency, spatial, temporal, resources, file_urls, api_endpoints, quality_signals, …) by enriching with the data.gouv.fr REST API at /api/1/datasets/{id}/.
mediaexpert.plScrape Media Expert category product listings
Extract complete product records and dynamically revealed attributes from Media Expert category listing pages, including lazy-loaded and unavailable offers.
opencorporates.comOpenCorporates Company & Filings Lookup
Search OpenCorporates for legal-entity records across jurisdictions and return matching companies plus their statutory-filings history (officers, addresses, previous names, branch flags, document URLs) as structured JSON. Read-only.
operator.fyiOperator Business Brain Profile
Resolve any business name, URL, city, or trade into Operator's full public Brain profile: 0-100 brain score with component breakdown, market rank, review sentiment from Google/Yelp/Meta, services + privacy-protected contact, top 3 competitors with scores, AI narrative, USD valuation range (vertical-multiple comparables), per-business MCP endpoint, and canonical /biz/{slug}/ URL. Read-only.
parallel.aiParallel CLI Deep Research
Install and use the Parallel CLI (parallel-cli) to run open-ended, citation-backed Deep Research via the pro/ultra Task API processors, then retrieve analyst-grade reports with sources and confidence levels.
- patents.google.com
Google Patents Search
Search Google Patents (~140M+ worldwide publications) by free-text query, assignee, inventor, country, status, language, or date range — returns publication number, title, priority/filing/grant/publication dates, inventor, assignee, snippet, PDF URL, and canonical landing-page URL for each match.
pepperpong.comPepper Pong Explore Use Cases
Browse pepperpong.com and return a structured catalog of where to play, who to play with, and who to gift the game to — each with verbatim evidence quotes and source URLs. Read-only.
peptideportal.orgPeptide Portal Compound Research
Search peptideportal.org for a peptide by name, alias, CAS number, or mechanism keyword and return a structured profile aggregating vendor pricing range and COA-verified status, the canonical research brief with use-case evidence tables, related dosing-guide blog posts, and the curated bibliography of clinical papers with PubMed outbound links.
preicfes-gratis.comResúmenes y simulacros ICFES SABER 11°
Explora preicfes-gratis.com y devuelve el catálogo completo de documentos gratuitos para ICFES SABER 11°: resúmenes PDF por materia (lectura crítica, filosofía, matemáticas, física, química, biología, sociales, inglés), bancos de simulacros y boletines oficiales del ICFES con URLs de previsualización y descarga directa.
scoutos.comLook Up Scout Product, Pricing, Integration, and Use-Case Info
Read-only research skill that retrieves structured product, pricing, integration, customer, and use-case information from scoutos.com given a topic, and walks the Cal.com demo-booking modal and Clerk-hosted free-trial signup up to (but not including) form submission.
software.nasa.govNASA Software Catalog Lookup
Look up software in NASA's public Software Catalog by free-text keyword or by canonical case number, returning structured records with title, description, NASA field center, category, release type, version, dates, and download URL.
substack.comSubstack Search Newsletters
Search Substack for newsletters / publications matching a topic, keyword, category, language, or author and return matching publications with subscriber-tier signals, multi-currency pricing, recent post samples, and canonical URLs as structured JSON. Read-only.
vecros.comExplore Vecros GPS-Denied Navigation, Drones & Modules
Render the Vecros React SPA to extract a structured overview of its GPS-denied navigation tech, the Athera/Jasper drones, the JETPIX autonomy stack, Vecros Cloud, and the Jetcore hardware modules (via the store.vecros.com Shopify JSON API). Read-only.
wikidata.orgWikidata SPARQL Query
Execute SPARQL against Wikidata's public Query Service and return structured JSON. Accepts raw SPARQL, a Wikidata entity QID (with optional property-PID filter), or a natural-language relational question that the agent translates into SPARQL. Honors output format (JSON/XML/CSV/TSV), label language, LIMIT, and the 60s endpoint timeout. Read-only — mutation queries rejected client-side.
wikipedia.orgWikipedia Get Article
Given a Wikipedia article reference (URL, lang+title, or free-form name), return structured content: canonical URL, title, language, lead summary, full section tree, infobox key/value pairs, thumbnail, image list, outbound article links, external links with section attribution, categories, last-revised timestamp, pageid, and revid. Handles redirects, disambiguation pages, and non-English editions.