skills.rest
otrebu
otrebuCOMMUNITY
Explore all skills by this author →
GitHub

parallel-search

Run parallel web research queries via the Parallel Search API and output LLM-ready markdown.

4|Updated Oct 6, 2025
Search Tags:#automation#markdown#RAG#web research#parallel-search
One-click install
npx skills add https://github.com/otrebu/agents --skill parallel-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: parallel-search
Source: https://github.com/otrebu/agents/tree/main/plugins/knowledge-work/skills/parallel-search
Command: npx skills add https://github.com/otrebu/agents --skill parallel-search

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires parallel-web, chalk, ora, and includes scripts (resource) components.

What problem does it solve?

Enables comprehensive, multi-angle web research via a single API call, returning ranked URLs and long-form excerpts suitable for downstream analysis.

Core Features & Use Cases

  • Multi-Angle Queries: Generates 3-5 targeted angles and aggregates results.
  • Extended Excerpts: Up to 30k chars per result for deep analysis.
  • LLM Ready Output: Markdown including metadata, domain distribution, and ranked results.
  • Persistence: Saves reports to docs/research/parallel with timestamped naming.

Quick Start

cd plugins/knowledge-work/skills/parallel-search pnpm tsx scripts/search.ts --objective "Production RAG system architecture" --queries "RAG chunking strategies" "RAG evaluation metrics"

Frequently Asked Questions about parallel-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform multi-angle web research across multiple queries in a single API call?▼

Parallel web research aggregates 3-5 targeted query angles via the Parallel Search API in one call, returning ranked URLs and extended excerpts suitable for downstream analysis without manual query iteration.

Can I use parallel web research for RAG system evaluation and current events analysis?▼

Yes. The Skill handles deep multi-angle research, technical analysis, current events, and comparative studies, returning LLM-ready markdown with extended excerpts up to 30k characters per result for comprehensive evaluation.

What's required to set up parallel web research with the Parallel Search API?▼

You need a valid PARALLEL_API_KEY, up to 5 search queries, and optional processor level selection (lite/base/pro/ultra) to configure depth and result volume before execution.

How does the Skill handle duplicate results across multiple search queries?▼

Parallel web research automatically deduplicates results across all queries, ensuring each source appears once in the final ranked output with domain distribution metadata.

What output format does parallel web research produce for LLM integration?▼

The Skill generates timestamped markdown reports saved to docs/research/parallel/ with titles, URLs, domains, and extended excerpts formatted for immediate downstream analysis and model input.

Do I need markdown processing knowledge to use parallel web research?▼

No. The Skill outputs LLM-ready markdown automatically; you provide search objectives and queries, and receive formatted reports without additional processing steps required.

Related Skills

Explore More Data & Analytics Skills→
harshanandakharshanandak
4

parallel-deep-research

Generate comprehensive research reports with citations via the Parallel AI task endpoint.

Community
Intermediate
orbrunoorbruno
1

Docling Fundamentals

Convert unstructured PDFs, DOCX, and HTML documents into structured Markdown or JSON.

Community
Basic
saleorsaleor
29

implementing-cli-patterns

Implement CLI UX patterns for Node/TypeScript applications with chalk, ora, and prompts.

Official
Advanced
clinecline
19

exa-search

Orchestrate parallel Exa searches and synthesize cited, structured research results.

Official
Advanced