depth-search

Query local ~/.topos notes and academic MCPs in parallel for multi-source research.

60|13|Updated Dec 22, 2025
One-click install
npx skills add https://github.com/plurigrid/asi --skill depth-search
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: depth-search
Source: https://github.com/plurigrid/asi/tree/main/skills/depth-search
Command: npx skills add https://github.com/plurigrid/asi --skill depth-search

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables deep multi-source research by integrating academic MCPs (arxiv, semantic-scholar, paper-search, deepwiki), Exa semantic search, and a local ~/.topos knowledge base. It is designed for comprehensive research that requires pulling data from multiple sources while leveraging cached local notes. It explicitly avoids using generic web search fallback and instead prompts you for context when sources are exhausted.

Core Features & Use Cases

  • Multi-source research orchestration: Synchronously and asynchronously query local files and four academic MCPs to gather diverse perspectives.
  • Parallel source querying: Run arxiv, semantic-scholar, paper-search, and deepwiki in parallel to maximize speed.
  • Local knowledge-first caching: Prioritize local notes in ~/.topos before turning to external sources, ensuring efficiency and consistency.

Quick Start

depth-search for "world models for LLMs" using ~/.topos, arxiv, semantic-scholar, paper-search, and deepwiki; if nothing is found, ask for a link or more context.

Frequently Asked Questions about depth-search

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

FAQPage Schema
How do I perform comprehensive research across multiple academic sources at once?

Comprehensive multi-source research queries local knowledge bases and academic MCPs—arxiv, semantic-scholar, paper-search, and deepwiki—in parallel. depth-search orchestrates these sources synchronously, prioritizing cached local notes in ~/.topos before consulting external databases, then prompts for context if sources are exhausted.

Can I search my local research notes alongside academic databases?

Yes. depth-search integrates a local ~/.topos knowledge base with four academic MCPs and Exa semantic search. Local files are queried first using glob and grep, ensuring cached notes are consulted before external sources, maximizing efficiency and consistency across your research.

What's the best way to conduct literature review across arxiv, semantic-scholar, and other academic sources?

depth-search automates literature review by orchestrating parallel queries to arxiv, semantic-scholar, paper-search, and deepwiki alongside Exa semantic search. This multi-source synthesis pulls diverse perspectives simultaneously, reducing manual source-hopping and enabling comprehensive cross-source analysis.

How does local knowledge-first caching improve research efficiency?

Local knowledge-first caching prioritizes ~/.topos notes before querying external academic MCPs. depth-search checks cached local data first using glob and grep, reducing redundant external queries, speeding results, and maintaining consistency by referencing existing research context before consulting new sources.

Can I use depth-search for in-depth investigations that require pulling from multiple knowledge sources?

Yes. depth-search is designed for in-depth investigations requiring synthesis across ~/.topos, arxiv, semantic-scholar, paper-search, deepwiki, and Exa. Parallel subagent orchestration queries all sources simultaneously, then prompts you for additional context if initial sources don't fully answer your query.

What happens when academic databases don't have results for my research query?

When arxiv, semantic-scholar, paper-search, deepwiki, and Exa return insufficient results, depth-search explicitly prompts you for a relevant link or additional context rather than falling back to generic web search, ensuring research quality remains high and aligned with academic sources.