parallel-searchAI-powered web search via Parallel API. Returns ranked results with LLM-optimized excerpts. Use for up-to-date research, fact-checking, and domain-scoped searching.
Install via ClawdBot CLI:
clawdbot install NormallyGaussian/parallel-searchHigh-accuracy web search built for AI agents. Returns ranked results with intelligent excerpts optimized for LLM consumption.
Trigger this skill when the user asks for:
parallel-cli search "your query" --json --max-results 5parallel-cli search "<objective>" [options]| Flag | Description |
|------|-------------|
| -q, --query " | Add keyword filter (repeatable, 3-8 recommended) |
| --max-results N | Number of results (1-20, default: 10) |
| --json | Output as JSON |
| --after-date YYYY-MM-DD | Filter for recent content |
| --include-domains domain.com | Limit to specific domains (repeatable, max 10) |
| --exclude-domains domain.com | Exclude domains (repeatable, max 10) |
| --excerpt-max-chars-total N | Limit total excerpt size (default: 8000) |
Basic search:
parallel-cli search "When was the United Nations founded?" --json --max-results 5With keyword filters:
parallel-cli search "Latest developments in quantum computing" \
-q "quantum" -q "computing" -q "2026" \
--json --max-results 10Domain-scoped search:
parallel-cli search "React hooks best practices" \
--include-domains react.dev --include-domains github.com \
--json --max-results 5Recent news only:
parallel-cli search "AI regulation news" \
--after-date 2026-01-01 \
--json --max-results 10Write 1-3 sentences describing:
Add 3-8 keyword queries including:
Returns structured JSON with:
search_id — unique identifierresults[] — array of results:url — source URLtitle — page titleexcerpts[] — relevant text excerptspublish_date — when availableWhen turning results into a user-facing answer:
For long conversations, save results and use sessions_spawn:
parallel-cli search "<query>" --json -o /tmp/search-<topic>.jsonThen spawn a sub-agent:
{
"tool": "sessions_spawn",
"task": "Read /tmp/search-<topic>.json and synthesize a summary with sources.",
"label": "search-summary"
}| Exit Code | Meaning |
|-----------|---------|
| 0 | Success |
| 1 | Unexpected error (network, parse) |
| 2 | Invalid arguments |
| 3 | API error (non-2xx) |
curl -fsSL https://parallel.ai/install.sh | bash
export PARALLEL_API_KEY=your-keyGenerated Mar 1, 2026
Startups can use Parallel Search to gather up-to-date market intelligence, competitor analysis, and industry trends. By filtering results with recent dates and specific domains like news sites or official reports, they can quickly validate business ideas and identify opportunities.
Researchers and students can leverage this skill to find recent scholarly articles, conference papers, and domain-specific sources for literature reviews. Using keyword filters and include-domains flags, they can scope searches to academic repositories and ensure citation accuracy.
Journalists and media professionals can employ Parallel Search to verify claims, gather sources for articles, and track breaking news. The ability to filter by after-date and exclude-domains helps ensure timely and credible information from primary sources.
IT support teams can use this skill to search for error messages, software documentation, and community forums to resolve technical issues. Keyword queries with specific terms and version numbers enable precise results from official docs and developer sites.
Legal professionals can utilize Parallel Search to find case law, regulatory updates, and legal precedents. Domain-scoping to government or legal databases and filtering by date ensures access to current and authoritative information for case preparation.
Parallel Search can be offered as a paid API service, charging based on usage tiers such as number of searches or results. This model targets developers and businesses integrating search capabilities into their applications, with revenue from subscription fees.
Sell enterprise licenses to large organizations for internal use, such as research departments or customer support teams. This includes custom integrations, higher rate limits, and dedicated support, generating revenue from annual contracts.
Provide white-labeled versions of the search tool for other companies to rebrand and resell. This model leverages partnerships with SaaS platforms or content providers, with revenue from setup fees and ongoing royalties.
💬 Integration Tip
Start by testing with the CLI examples to understand output formats, then integrate the JSON responses into your AI agent's workflow for automated search and synthesis.
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
Search indexed Discord community discussions via Answer Overflow. Find solutions to coding problems, library issues, and community Q&A that only exist in Discord conversations.
Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.