Search
“data extraction”
Showing 73–96 of 887 for “data extraction”
- 0.566score
agent-browser
raktim-mondol
Browse and interact with live websites — navigate, fill forms, extract data, download datasets/files — when web_search/web_fetch can't reach rendered or…
SkillBFreshness: B★ 4Claude Code +9 - 0.590score
browser
goodfoot-io
Browser automation (navigation, forms, clicks, screenshots, data extraction, testing) using the agent-browser CLI against a Chromium binary set up by this…
SkillAFreshness: A★ 2Claude Code +9 - 0.583score
Refigure
HelgDemidov
Convert DOCX/XLSX to Markdown — native chart-data extraction, optional VLM for figures
ConnectorAFreshness: ARemoteLocal↓ 40/wkClaude Code +5 - 0.443score
parse-json
AMindToThink
Inspect and extract data from unknown JSON files without fumbling
SkillDFreshness: D★ 4Claude Code +9 - 0.431score
document-intelligence
TRRaveendra
Parse documents, extract text from PDFs/images, and use SQL AI functions for intelligent data extraction.
SkillDFreshness: D★ 2Claude Code +9 - 0.562score
RunHarvester
runharvester.comOfficial
Web data extraction and browser workflows for AI assistants.
ConnectorAFreshness: ARemoteClaude Code +3 - 0.562score
TerraLab
terra-lab.aiOfficial
Map data ready for QGIS: open data extracts, GIS files, coordinates, elevation, French parcels.
ConnectorAFreshness: ARemoteClaude Code +3 - 0.461score
crawl4ai
Harmeet10000
Complete toolkit for web crawling and data extraction using Crawl4AI.
SkillDFreshness: D★ 7Claude Code +9 - 0.562score
GrowthVector Pro
growthvector.ioOfficial
GrowthVector knowledge base plus SEO audits and website data extraction.
ConnectorAFreshness: ARemoteClaude Code +3 - 0.562score
PDFBetter
pdfbetter.comOfficial
Fill, convert, OCR, merge, split, extract data from and summarize PDFs.
ConnectorAFreshness: ARemoteClaude Code +3 - 0.562score
ScribeTools
scribetools.comOfficial
OCR, editable Word, tables, translation and data extraction for Arabic-script documents
ConnectorAFreshness: ARemoteClaude Code +3 - 0.533score
Agent Vending Factory
RubenTay
Pay-per-call MCP tools via x402 USDC: ZAR prices, data extraction, Python sandbox, SA flights.
ConnectorBFreshness: BRemoteClaude Code +3 - 0.488score
firecrawl-interact
clodoaldoperito-droid
Control and interact with a live browser session on any scraped page — click buttons, fill forms, navigate flows, and extract data using natural language…
SkillCFreshness: C★ 1Claude Code +9 - 0.558score
BrowsingBee
theindianappguy
Hosted browser for agents: open pages, search the web, extract data, read PDFs and take screenshots.
ConnectorAFreshness: ARemoteClaude Code +3 - 0.740score
scrapecreators-api
ScrapeCreators
Scrape and extract public data from 27+ social media platforms using the ScrapeCreators REST API.
SkillCFreshness: C★ 4.7KClaude Code - 0.551score
multimodal-ai-pipelines
hienpham0344
Production multimodal architectures handling document OCR, vision inspection, image understanding, and structured data extraction.
SkillAFreshness: AClaude Code +9 - 0.524score
browse
iaa2005
Automate browser interactions via CLI commands to navigate web pages, extract data, take screenshots, fill forms, and interact with web apps.
SkillBFreshness: BClaude Code +9 - 0.539score
Analyst
clawic
Extract insights from data with SQL, visualization, and clear communication of findings.
SkillCFreshness: C★ 19Claude Code +9 - 0.673score
instructor
Orchestra-Research
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream…
SkillCFreshness: C★ 13.9KClaude Code +9 - 0.516score
wiki-extract-wikipedia
SkinnnyJay
Extract Wikipedia articles and Wikidata infobox data into raw/ via REST API and SPARQL.
SkillBFreshness: BClaude Code +9 - 0.870score
core
vercel-labsOfficial
Core agent-browser usage guide.
SkillAFreshness: A★ 44.5KClaude Code +9 - 0.766score
extraction-pipeline-patterns
xberg-io
Change or diagnose Xberg's core extraction orchestration, cache semantics, extractor fallback, post-processing, concurrency defaults, or format-wide quality…
SkillAFreshness: A★ 9.4KClaude Code +9 - 0.516score
wiki-extract-crunchbase
SkinnnyJay
Extract Crunchbase company profiles, funding rounds, and investor data into raw/.
SkillBFreshness: BClaude Code +9 - 0.481score
scrapling
archibate
Scrape, crawl, or extract data from websites using Scrapling — anti-bot bypass (Cloudflare Turnstile), stealth headless, spiders, adaptive scraping, JS…
SkillCFreshness: C★ 42Claude Code +9