Deep Research
Run systematic multi-source web research before answering hard questions or generating slides, UI, articles, or other content that needs current facts.
Overview
Deep Research is a journey-wide agent skill that runs systematic multi-angle web research instead of a single superficial search—usable whenever a solo builder needs grounded facts before answering or generating content.
Install
npx skills add https://github.com/bytedance/deer-flow --skill deep-researchWhat is this skill?
- Explicit substitute for one-off WebSearch on any question needing online information
- Multi-angle methodology: breadth, depth, and multiple sources instead of a single hit
- Mandatory pre-step before presentations, frontend designs, articles, reports, video scripts, and similar generation
- Triggers on what is X, explain X, compare X and Y, and research X phrasing
- Core rule: do not generate content from general knowledge alone
Adoption & trust: 1.6k installs on skills.sh; 70.7k GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You risk shallow or outdated answers when your agent does one quick web search or relies on training data alone.
Who is it for?
Builders who want a repeatable research ritual before explainers, comparisons, decks, UI mockups, articles, or any task that needs current external evidence.
Skip if: Purely local code refactors, secrets-only workflows, or questions answerable from the repo without web grounding.
When should I use this skill?
Use for ANY question requiring web research—including what is X, explain X, compare X and Y, research X—or proactively before content generation tasks.
What do I get? / Deliverables
You get multi-source, angle-aware research summaries that can safely inform answers, specs, and content drafts across the journey.
- Multi-angle research notes
- Synthesis suitable for answers or downstream content
- Source-aware context for generation tasks
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Compare two agent frameworks with multiple sources before picking a stack.
Gather pricing and competitor patterns before locking an MVP scope.
Research API behavior and examples before writing public documentation.
Collect current SERP and topic angles before drafting launch content.
Refresh narrative posts with up-to-date stats instead of model memory.
How it compares
Use instead of a single WebSearch call when the user asks what is, compare, or research-style questions or before generative content work.
Common Questions / FAQ
Who is deep-research for?
Solo and indie builders using Claude Code, Cursor, or Codex who need trustworthy online research before decisions or creative outputs.
When should I use deep-research?
Use it in Idea/research for market and concept questions; in Validate when scoping needs external proof; in Build and Launch before docs, UI, or SEO copy; and in Grow when content needs fresh data—anytime web depth beats one search.
Is deep-research safe to install?
It drives networked research; review the Security Audits panel on this page and restrict browsing in agents that should not reach untrusted sites.
SKILL.md
READMESKILL.md - Deep Research
# Deep Research Skill ## Overview This skill provides a systematic methodology for conducting thorough web research. **Load this skill BEFORE starting any content generation task** to ensure you gather sufficient information from multiple angles, depths, and sources. ## When to Use This Skill **Always load this skill when:** ### Research Questions - User asks "what is X", "explain X", "research X", "investigate X" - User wants to understand a concept, technology, or topic in depth - The question requires current, comprehensive information from multiple sources - A single web search would be insufficient to answer properly ### Content Generation (Pre-research) - Creating presentations (PPT/slides) - Creating frontend designs or UI mockups - Writing articles, reports, or documentation - Producing videos or multimedia content - Any content that requires real-world information, examples, or current data ## Core Principle **Never generate content based solely on general knowledge.** The quality of your output directly depends on the quality and quantity of research conducted beforehand. A single search query is NEVER enough. ## Research Methodology ### Phase 1: Broad Exploration Start with broad searches to understand the landscape: 1. **Initial Survey**: Search for the main topic to understand the overall context 2. **Identify Dimensions**: From initial results, identify key subtopics, themes, angles, or aspects that need deeper exploration 3. **Map the Territory**: Note different perspectives, stakeholders, or viewpoints that exist Example: ``` Topic: "AI in healthcare" Initial searches: - "AI healthcare applications 2024" - "artificial intelligence medical diagnosis" - "healthcare AI market trends" Identified dimensions: - Diagnostic AI (radiology, pathology) - Treatment recommendation systems - Administrative automation - Patient monitoring - Regulatory landscape - Ethical considerations ``` ### Phase 2: Deep Dive For each important dimension identified, conduct targeted research: 1. **Specific Queries**: Search with precise keywords for each subtopic 2. **Multiple Phrasings**: Try different keyword combinations and phrasings 3. **Fetch Full Content**: Use `web_fetch` to read important sources in full, not just snippets 4. **Follow References**: When sources mention other important resources, search for those too Example: ``` Dimension: "Diagnostic AI in radiology" Targeted searches: - "AI radiology FDA approved systems" - "chest X-ray AI detection accuracy" - "radiology AI clinical trials results" Then fetch and read: - Key research papers or summaries - Industry reports - Real-world case studies ``` ### Phase 3: Diversity & Validation Ensure comprehensive coverage by seeking diverse information types: | Information Type | Purpose | Example Searches | |-----------------|---------|------------------| | **Facts & Data** | Concrete evidence | "statistics", "data", "numbers", "market size" | | **Examples & Cases** | Real-world applications | "case study", "example", "implementation" | | **Expert Opinions** | Authority perspectives | "expert analysis", "interview", "commentary" | | **Trends & Predictions** | Future direction | "trends 2024", "forecast", "future of" | | **Comparisons** | Context and alternatives | "vs", "comparison", "alternatives" | | **Challenges & Criticisms** | Balanced view | "challenges", "limitations", "criticism" | ### Phase 4: Synthesis Check Before proceeding to content generation, verify: - [ ] Have I searched from at least 3-5 different angles? - [ ] Have I fetched and read the most i