Parallel Web Extract

Fetches webpage content, PDFs, and JS-heavy sites in parallel without burning your main context window. Runs in a forked context using parallel-cli, so you can extract from a dozen URLs and keep your primary conversation clean. Returns structured content with titles, excerpts, and optional full-text if you need it. Has sensible guardrails for failed fetches instead of hallucinating content. The objective and keyword flags let you steer what gets prioritized in excerpts. If you're doing research or scraping documentation across multiple sources, this beats making sequential WebFetch calls and cluttering your token budget. Requires parallel-cli installed and authenticated.

Install to Claude Code

npx -y skills add parallel-web/parallel-agent-skills --skill parallel-web-extract --agent claude-code