Parallel Web Search

This is your default search skill for anything requiring current information. It runs parallel web queries and returns structured JSON with excerpts, URLs, and dates. The skill template enforces inline citations for every claim and auto-saves results to /tmp for follow-up questions without re-searching. It supports time filters, domain scoping, and keyword queries alongside natural language objectives. There's an advanced mode for multi-step research, but basic mode handles most cases. Requires parallel-cli installed and authenticated. The instruction set is thorough about parsing the JSON file instead of stdout to avoid truncation, which suggests the authors learned that lesson the hard way.

Install to Claude Code

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