skills.rest
openJiuwen-ai
openJiuwen-aiOFFICIAL
Explore all skills by this author →
WebsiteGitHub

openJiuwen-DeepSearch

Plan, collect evidence, and synthesize cited research reports in Markdown, Docx, and Html.

2.5k|422|Updated Mar 5, 2026
Search Tags:#information retrieval#web search#report generation#citations#deep research#multi-agent workflow#markdown to docx html
One-click install
npx skills add https://github.com/openJiuwen-ai/jiuwenswarm --skill openjiuwen-deepsearch-openjiuwen-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openJiuwen-DeepSearch
Source: https://github.com/openJiuwen-ai/jiuwenswarm/tree/main/jiuwenswarm/resources/agent/workspace/skills/openJiuwen-DeepSearch
Command: npx skills add https://github.com/openJiuwen-ai/jiuwenswarm --skill openjiuwen-deepsearch-openjiuwen-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python-dotenv, pypandoc, markdown, markdown_mermaid_cli, requests, PIL, and includes scripts (resource) components.

What problem does it solve?

When you need a thorough research report for a complex topic, DeepSearch helps you go beyond quick answers by planning the research, collecting information from multiple sources, analyzing it, and generating a structured report with citations.

Core Features & Use Cases

  • Deep research pipeline: Automatically performs query planning, information collection, understanding/reflection, and final report generation across a multi-agent workflow.
  • Knowledge + web augmentation: Combines local knowledge usage and web search to improve coverage and quality for hard questions.
  • Traceable results: Produces outputs with citation and reference-style traceability so readers can verify sources.
  • Multi-format outputs: Can generate reports in Markdown and convert them to Docx and Html for easy sharing and publishing.
  • Use cases:
    • Finance industry reports (market trends, impact analysis, investment research)
    • Academic and policy research (literature-style summaries, policy impact analysis)
    • Enterprise-grade deep searches (multi-source integration for complex questions)

Quick Start

Ask an AI agent to run the openJiuwen-DeepSearch skill and produce an “AI手机行业研究报告” report by executing the skill’s main script in its folder and waiting for the generated Markdown/Doc/Html outputs.

Frequently Asked Questions about openJiuwen-DeepSearch

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

FAQPage Schema
How do I generate a deep research report with web search citations?▼

To generate a deep research report with web search citations, the skill plans the investigation, collects multi-source evidence, and synthesizes a structured analysis. It outputs Markdown files alongside converted Docx and Html formats with traceable references.

Can I convert markdown research reports to docx and html?▼

Yes, you can convert markdown research reports to docx and html. The skill automatically generates Markdown outputs and converts them into Docx and Html artifacts for easy sharing and publishing.

What's the best way to automate multi-source information integration for complex queries?▼

The best way to automate multi-source information integration is using a multi-agent workflow that combines local knowledge and web search. This improves coverage and quality for complex enterprise queries by planning, collecting, and analyzing data.

Do I need to configure environment variables for LLM and web search providers?▼

Yes, you need to configure environment variables for LLM and web search providers. The skill requires python-dotenv to support configurable settings, allowing you to specify your preferred providers before executing the main script.

Does the deep research pipeline support finance and policy analysis?▼

Yes, the deep research pipeline supports finance and policy analysis. It is applicable for generating industry reports, market trend analysis, investment research, literature summaries, and policy impact analysis with cited evidence.

Why use a multi-agent workflow for information retrieval and report generation?▼

Use a multi-agent workflow for information retrieval to automatically perform query planning, evidence collection, and understanding. This mechanism ensures the final report generation produces traceable, structured results rather than quick, superficial answers.

Related Skills

Explore More Education & Research Skills→
citedycitedy
31

self-setup

Configure LLM providers, models, and API keys via a local management API.

Official
Intermediate
shaprisshapris

theme-factory

Apply font and color themes to slide decks, documents, and HTML artifacts.

Community
Intermediate
riba2534riba2534
1.3k

feishu-cli-write

Convert Markdown into Feishu cloud documents with Mermaid/PlantUML diagrams as boards.

Community
Advanced
Devvraj10Devvraj10

deep-research

Automate in-depth research on complex topics with source credibility scoring.

Community
Advanced