
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.
- skills.sh installs
- 14.8K
- GitHub stars
- 91
- last updated
- Aug 21, 2026
Install
$ npx -y skills add parallel-web/parallel-agent-skills --skill parallel-web-search --agent claude-codeInstalls into .claude/skills of the current project.
Files
Web Search
Search the web for: $ARGUMENTS
Command
Choose a short, descriptive filename based on the query (e.g., ai-chip-news, react-vs-vue). Use lowercase with hyphens, no spaces. Substitute it into the command inline — $FILENAME and <keyword> below are placeholders, not shell variables; do not copy them verbatim.
parallel-cli search "$ARGUMENTS" -q "<keyword1>" -q "<keyword2>" --json --max-results 10 --excerpt-max-chars-total 27000 -o "/tmp/$FILENAME.json"
Concrete example for a query about React 19:
parallel-cli search "latest React 19 features and adoption" -q "React 19" -q "concurrent rendering" --json --max-results 10 --excerpt-max-chars-total 27000 -o "/tmp/react-19-features.json"
The first argument is the objective — a natural language description of what you're looking for. It replaces multiple keyword searches with a single call for broad or complex queries. Add -q flags for specific keyword queries to supplement the objective. The -o flag saves the full results to a JSON file for follow-up questions.
Options if needed:
Sponsors