Parallel Web Extract

parallel-web/parallel-agent-skillsOfficial

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.

skills.sh installs: 14K
GitHub stars: 91
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

URL Extraction

Extract content from: $ARGUMENTS

Command

Choose a short, descriptive filename based on the URL or content (e.g., vespa-docs, react-hooks-api). Use lowercase with hyphens, no spaces. Substitute it into the command inline — $FILENAME is a placeholder, not a shell variable.

Pass each requested URL as a separate quoted positional argument, up to 20 per call. Do not collapse multiple URLs into one quoted $ARGUMENTS string or use eval to split them. Construct arguments directly from the requested URLs. For example:

parallel-cli extract "https://docs.parallel.ai/integrations/cli" "https://docs.parallel.ai/integrations/cursor-marketplace" --json -o "/tmp/parallel-docs.json"

-o saves JSON. Use a .json extension and inspect an existing path before use because Extract overwrites it. Read the saved file as authoritative; stdout may truncate and human-readable output previews only part of the content. Do not treat a stale file as a successful response after a failed call.

Options if needed:

SKILL.md on GitHub