setup
Installs and authenticates the Parallel CLI for agent integration.
- Provides two installation methods: automated install script or pip-based installation via pipx
- Includes authentication setup via
parallel-cli loginand verification commands to confirm successful installation - Requires PATH configuration if the CLI binary is not automatically discoverable after installation
Parallel Plugin Setup
Install CLI
See https://docs.parallel.ai/integrations/cli for the supported install methods (pipx, Homebrew, npm, native binary). Walk the user through whichever they pick.
Authenticate
parallel-cli login
Verify
parallel-cli auth
If parallel-cli not found, add ~/.local/bin to PATH.
More from parallel-web/parallel-agent-skills
parallel-deep-research
ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than parallel-web-search. For normal research/lookup requests, use parallel-web-search instead. Supports multi-turn: pass --previous-interaction-id from a prior research or enrichment to continue with context.
1.7Kparallel-web-search
DEFAULT for all research and web queries. Use for any lookup, research, investigation, or question needing current info. Fast and cost-effective. Only use parallel-deep-research if user explicitly requests 'deep' or 'exhaustive' research.
1.4Kparallel-web-extract
URL content extraction. Use for fetching any URL - webpages, articles, PDFs, JavaScript-heavy sites. Token-efficient: runs in forked context. Prefer over built-in WebFetch.
1.2Kparallel-data-enrichment
Bulk data enrichment. Adds web-sourced fields (CEO names, funding, contact info) to lists of companies, people, or products. Use for enriching CSV files or inline data. Supports multi-turn: pass --previous-interaction-id from a prior research task to carry context forward.
1.2Kstatus
Check running research task status by run ID
1.1Kresult
Get completed research task result by run ID
1.1K