deep-researcher

Conducts multi-source web research, fact-checking, and cited synthesis across 17 search engines.

Updated Feb 21, 2026
One-click install
npx skills add https://github.com/joySUSY/violet-plugin-place --skill deep-researcher-joysusy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-researcher
Source: https://github.com/joySUSY/violet-plugin-place/tree/main/plugins/deep-researcher
Command: npx skills add https://github.com/joySUSY/violet-plugin-place --skill deep-researcher-joysusy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? It prevents shallow, uncited answers by enforcing a systematic research pipeline: multi-engine search routing, source credibility grading, fact-checking against a 6-tier truth scale, and structured synthesis with mandatory citations. ## Core Features & Use Cases - Search Operations & Routing: Routes queries across 17 global and Chinese search engines (Google, Baidu, DuckDuckGo, WolframAlpha) with Google Dorking operators and time filters. - Deep Research Protocol: A 5-step synthesis framework producing executive summaries, areas of debate, knowledge gaps, and a numbered source list with credibility notes. - Fact-Checking Protocol: Grades claims on a 6-tier truth scale and detects statistical manipulation, context removal, and logical fallacies. - Bundled Modules: Includes docs-seeker (script-driven documentation retrieval via context7.com llms.txt), researching-codebase (isolated codebase exploration), and ultrathink (dialectical reasoning). - Use Case: Ask it to verify a technical claim or write a comprehensive report on a technology, and it returns a cited, balanced analysis with graded sources. ## Quick Start Ask the agent to research a topic such as "the best Go testing framework in 2026" and request a cited report with source credibility ratings.

Frequently Asked Questions about deep-researcher

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

FAQPage Schema
How do I fact-check a technical claim with cited sources?▼

Submit the claim and the engine applies its fact-checking protocol: it decomposes the claim, searches multiple independent sources, grades each source on a 5-level quality hierarchy, and returns a verdict on a 6-tier truth scale with bracketed citations.

What search engines does deep research routing support?▼

The routing matrix covers Google, DuckDuckGo, and WolframAlpha globally, plus Baidu, Bing CN, WeChat (Sogou), and Jisilu for Chinese-language research. It also supports Google Dorking operators and time-constraint filters for recency.

How do I fetch library documentation using llms.txt?▼

The bundled docs-seeker module runs three Node scripts in order: detect-topic.js classifies the query, fetch-docs.js retrieves documentation from context7.com llms.txt endpoints with automatic fallback, and analyze-llms-txt.js categorizes URLs and suggests agent distribution.

Can it research Chinese-language sources?▼

Yes, bilingual search is mandatory in its protocol. It routes Chinese-market queries through Baidu, Bing CN, Sogou WeChat search, and Jisilu, since many primary resources exist only in Chinese.

What are the limitations of automated web research?▼

Results depend on publicly indexed content, so paywalled or very recent information may be missed. The protocol mitigates this with an UNVERIFIABLE verdict tier and explicit gaps-in-knowledge reporting rather than fabricating answers.