Parallel Web (gated)

Upstream parallel-web/parallel-agent-skills (MIT), all skills unchanged as modules.

Gate: Parallel's CLI and APIs need an installed, authenticated and funded parallel-cli, or a configured Parallel Search MCP. Use this skill only when the user explicitly asks for Parallel or it is already configured. Otherwise ordinary research belongs to research-analyst. Never create accounts or keys; parallel-cli-setup explains setup when the user asks for it.

Modules

• choose-your-parallel-api — Choose the right Parallel API and configuration for cost, latency, and answer quality.
• migrate-to-parallel — Migrate Exa, Tavily, Perplexity, or Firecrawl web-data integrations completely to the appropriate Parallel products while preserving applic…
• parallel-cli-setup — Set up and maintain the Parallel CLI (install, auth, balance, skills install)
• parallel-data-enrichment — Bulk data enrichment.
• parallel-deep-research — ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'.
• parallel-findall — Discover entities (companies, people, products, etc.) matching a natural-language description.
• parallel-mcp-setup — Use when installing, configuring, or troubleshooting an authenticated Parallel Search MCP connection in Bifrost, including gateway-level se…
• parallel-memory — Recall past Parallel Task, Monitor, and FindAll runs when they may help; evict runs or clear memory when asked.
• parallel-monitor — Continuously track the web for changes on a recurring cadence.
• parallel-search-setup — Use when verifying, using, or troubleshooting the anonymous Parallel Search MCP server bundled with this plugin — when the user installs th…
• parallel-web-extract — CLI-backed URL extraction.
• parallel-web-search — CLI-backed web search.
• result — Get completed research task result by run ID
• status — Check running research task status by run ID