@firecrawl

firecrawl-build-onboarding guides credential setup and sdk installation for firecrawl integration, covering auth flow, env config, and initial smoke testing across multiple languages.

firecrawl-build-scrape integrates the /scrape endpoint for extracting single-page content (markdown, html, links) from known urls. covers common patterns like knowledge ingestion and pricing extraction with clear escalation rules to related skills.

firecrawl-research-index locates research papers answering queries via semantic search, structural graph traversal, and intent-driven ranking across citation networks and reference sets.

firecrawl-dashboard-reporting extracts metrics from web dashboards using browser automation, handling authenticated access and multi-dashboard parallel collection with structured json output and audit trails.

firecrawl-deep-research orchestrates multi-angle web scraping and synthesis to produce sourced research reports. it scales from quick 3-5 query sweeps to exhaustive multi-source investigations with parallel angle workers, then assembles findings into structured markdown with explicit source citations and uncertainty flagging.

firecrawl-download maps and scrapes entire websites into organized local file trees, supporting markdown, screenshots, and multi-format output per page with path filtering and format control.

firecrawl-interact enables browser automation on previously scraped pages via natural language commands or code, supporting form fills, clicks, pagination, and multi-step navigation with session persistence through profiles.

firecrawl-shop orchestrates web research across product sites and review sources to build shopping recommendations, with optional cart integration when user consent is confirmed.

firecrawl-competitive-intel monitors competitor pricing, features, and product changes over time using firecrawl scraping. it structures findings into alerts, per-competitor breakdowns, and cross-competitor matrices with source attribution for diffing.

firecrawl-company-directories extracts structured company lists from web directories using browser automation or static scraping, with flexible field capture and json/csv export, though lacks explicit failure handling.

firecrawl-knowledge-ingest crawls documentation portals using browser automation, handling authentication and pagination. it extracts markdown content and metadata but lacks concrete procedural detail and error handling guidance.

firecrawl-parse converts local documents (pdf, docx, xlsx, html, etc) to markdown with optional ai summarization and qa. outputs to disk to avoid context bloat.

firecrawl-market-research extracts financial and industry data via web scraping and search, producing structured market overviews with company profiles and trend analysis. limited guidance on failure modes and source reliability.

firecrawl-monitor detects website content changes and delivers notifications via webhook or email, with per-field diffs and change classification (same, new, changed, removed, error).

firecrawl-research-papers orchestrates literature review assembly by inferring topic constraints from context, searching paper corpora via firecrawl research tools, expanding via related-paper graphs, and synthesizing findings into a sourced markdown report with themes, debates, and emerging trends.

firecrawl-lead-research gathers company and person intelligence via firecrawl search and scrape to produce pre-meeting briefs. requires manual interpretation of outputs and lacks procedural rigor.

firecrawl-lead-gen automates prospect extraction from web directories and databases using firecrawl's browser tool, with role, industry, and company filters. scope and field coverage remain incomplete in provided docs.

firecrawl-website-design-clone extracts a website's visual design system into a markdown file ready for agent consumption. it combines firecrawl scraping with structured synthesis of colors, fonts, spacing, and components.

firecrawl-build-crawl covers bulk page extraction across site sections using the /crawl endpoint, with guidance on scope constraints and when to prefer /scrape or /map instead.

firecrawl-browser provides browser interaction capabilities for scraping javascript-heavy pages and handling multi-step workflows, but the documentation cuts off mid-quickstart without completing procedural steps.

firecrawl-instruct enables browser-based interaction with scraped pages via natural language commands, targeting javascript-dependent content and multi-step workflows. incomplete procedural documentation limits practical utility.

Convert a local file (PDF, DOCX, XLSX, HTML, …) to markdown, or answer questions about its content. Use whenever the input is a file path, not a URL.

Save a site or section as local files (markdown, screenshots). Use for "download the site", offline docs, or a local copy for reference.

Alert by webhook/email on web changes — use for "monitor/watch/track/alert me when": recurring checks on known URLs (prefer over repeated one-off scrapes) or…

Drive a live browser on a scraped page: click, fill forms, log in, paginate, infinite-scroll. Use when content requires interaction or a scrape failed or…

Discover and list a site's URLs, with search filtering. Use for "map the site" or "find the URL for" requests — when the user knows the site but not the exact…

Bulk-extract many pages from one site or section. Use for "crawl", "everything under /docs", or content spanning linked pages.

Read a known webpage or execute a discovered workflow or data-provider capability. Use for page content or structured results once the URL or tool is selected.

Autonomously navigate websites and extract structured data across pages. Use when the task requires navigation or no suitable ready-made workflow or data…

Find web sources with query-relevant page excerpts and optional full-page content, and discover workflows, data APIs, and indexes. Use for web research or…

Any live-web task via the Firecrawl CLI — including ordinary web research: searching the web, reading or extracting pages, gathering sources, discovering site…

Search an index of public repositories, GitHub issues, merged pull requests, repository READMEs, and curated documentation sites. Use when a programming…

Convert Word (.doc, .docx), PowerPoint (.ppt, .pptx), Excel (.xls, .xlsx), OpenDocument (.odt, .ods, .odp), RTF, EPUB, CSV, and PDF files to GitHub-Flavored…

Walk through a product's key flows with Firecrawl browser and produce a structured UX/product walkthrough. Use for signup, onboarding, pricing, docs,…

QA test a live website with Firecrawl browser and scrape evidence. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive…

Audit a website's SEO with Firecrawl. Use when the user asks for an SEO audit, metadata and heading review, sitemap/site-structure analysis, keyword…

Build a knowledge base from web content with Firecrawl. Use for local reference docs, RAG-ready chunks, fine-tuning datasets, documentation mirrors, topic…

Run outcome-focused Firecrawl workflows that produce deliverables such as research reports, literature reviews over published papers, SEO audits, QA reports,…

Integrate Firecrawl `/interact` into product code for dynamic pages and browser actions after scraping. Use when a feature needs clicks, form fills,…

Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query…

Discover and list a site's URLs, with search filtering. Use for "map the site" or "find the URL for" requests — when the user knows the site but not the exact…

Bulk-extract many pages from one site or section. Use for "crawl", "everything under /docs", or content spanning linked pages.

Autonomously navigate websites and extract structured data across pages. Use when the task requires navigation or no suitable ready-made workflow or data…

Read a known webpage or execute a discovered workflow or data-provider capability. Use for page content or structured results once the URL or tool is selected.

Find web sources with query-relevant page excerpts and optional full-page content, and discover workflows, data APIs, and indexes. Use for web research or…

Any live-web task via the Firecrawl CLI — including ordinary web research: searching the web, reading or extracting pages, gathering sources, discovering site…

Integrate Firecrawl `/map` into product code for URL discovery on a known site. Use when a feature needs to find pages before scraping or crawling, especially…