Extracting documentation from a website can be hard when the site uses complex features. This skill uses the Firecrawl browser to handle JavaScript-heavy pages, login-gated portals, and pagination. It works well for help centers, support knowledge bases, and documentation sites.
You simply provide the portal URL and your Firecrawl API key. The tool will navigate the site, follow links, and collect all article content. It can also handle authentication if needed. The output is clean markdown or structured JSON with metadata like title, section, and last updated date.
This skill is ideal for developers, technical writers, and AI agents who want to ingest knowledge from any docs portal. It preserves code examples and tables while removing navigation chrome and footers. The final deliverable includes a summary, section details, and any failed pages.
Global
mkdir -p ~/.claude/skills/firecrawl-knowledge-ingestProject
mkdir -p .claude/skills/firecrawl-knowledge-ingestSource Repository
Lark Baselarksuite/cli
Simplify your Lark Base data with tables, fields, records, and views
Lark Wikilarksuite/cli
Manage your Lark Wiki spaces, members, and documents with simple commands
Paper Context Resolverlllllllama/ai-paper-reproduction-skill
Resolve deep learning paper reproduction gaps with precise primary source evidence
Repo Intake And Planlllllllama/ai-paper-reproduction-skill
Scan a repo, extract commands, and get a minimal reproduction plan
Minimal Run And Auditlllllllama/ai-paper-reproduction-skill
Run commands and capture normalized evidence for reproducible deep learning research
Firecrawl Searchfirecrawl/cli
Search the web and extract full page content as markdown for deeper research
Ai Research Reproductionlllllllama/rigorpilot-skills
Faithful reproduction of deep learning research with auditable steps and minimal changes
Minimal Run And Auditlllllllama/rigorpilot-skills
Capture evidence from deep learning runs and create standardized audit reports