Verwendung
- Installationsbefehl kopieren und das Quellpaket vor der Installation in der eigenen Agentenumgebung prüfen.
- Benötigte Werkzeuge, Zugangsdaten und Hosts im Original prüfen.
- Eingabe und gewünschtes Ergebnis beschreiben und die Ausgabe mit den Quellen abgleichen.
npx skills add https://github.com/bytedance/deer-flow --skill deep-researchVor dem Start
- Die Installation umfasst weder Modellabo noch API-Kontingent oder Dateizugriffsrechte.
- Sterne und Installationen zeigen Aktivität, keine unabhängige Qualitäts- oder Sicherheitsprüfung.
Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.
Deep Research Skill
Overview
This skill provides a systematic methodology for conducting thorough web research. Use it when the requested claims need external verification; use supplied material and stable knowledge where sufficient.
When to Use This Skill
Consider this skill when depth and external verification are needed:
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
Choose effort according to freshness, uncertainty, consequence, and scope. A focused question may be resolved by one authoritative source; broad or disputed claims need independent checks. Stop when requested claims have sufficient support and state remaining gaps.
Research Methodology
Phase 1: Broad Exploration
Start with broad searches to understand the landscape:
- Initial Survey: Search for the main topic to understand the overall context
- Identify Dimensions: From initial results, identify key subtopics, themes, angles, or aspects that need deeper exploration
- 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 considerationsPhase 2: Deep Dive
For each important dimension identified, conduct targeted research:
- Specific Queries: Search with precise keywords for each subtopic
- Multiple Phrasings: Try different keyword combinations and phrasings
- Fetch Full Content: Use
web_fetchto read important sources in full, not just snippets - 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 studiesPhase 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 covered the dimensions needed to answer the request?
- [ ] Have I fetched and read the most important sources in full?
- [ ] Do I have concrete data, examples, and expert perspectives?
- [ ] Have I explored both positive aspects and challenges/limitations?
- [ ] Is my information current and from authoritative sources?
Investigate material evidence gaps; omit irrelevant checklist items and disclose unresolved limits.
Search Strategy Tips
Effective Query Patterns
# Be specific with context
❌ "AI trends"
✅ "enterprise AI adoption trends 2024"
# Include authoritative source hints
"[topic] research paper"
"[topic] McKinsey report"
"[topic] industry analysis"
# Search for specific content types
"[topic] case study"
"[topic] statistics"
"[topic] expert interview"
# Use temporal qualifiers — always use the ACTUAL current year from <current_date>
"[topic] 2026" # ← replace with real current year, never hardcode a past year
"[topic] latest"
"[topic] recent developments"Temporal Awareness
For time-sensitive questions, use the actual current date and the requested time range when choosing search filters.
<current_date> gives you the full date: year, month, day, and weekday (e.g. 2026-02-28, Saturday). Use the right level of precision depending on what the user is asking:
| User intent | Temporal precision needed | Example query |
|---|---|---|
| "today / this morning / just released" | Month + Day | "tech news February 28 2026" |
| "this week" | Week range | "technology releases week of Feb 24 2026" |
| "recently / latest / new" | Month | "AI breakthroughs February 2026" |
| "this year / trends" | Year | "software trends 2026" |
Rules:
- When the user asks about "today" or "just released", use month + day + year in your search queries to get same-day results
- Never drop to year-only when day-level precision is needed —
"tech news 2026"will NOT surface today's news - Try multiple phrasings: numeric form (
2026-02-28), written form (February 28 2026), and relative terms (today,this week) across different queries
❌ User asks "what's new in tech today" → searching "new technology 2026" → misses today's news ✅ User asks "what's new in tech today" → searching "new technology February 28 2026" + "tech news today Feb 28" → gets today's results
When to Use web_fetch
Use web_fetch to read full content when:
- A search result looks highly relevant and authoritative
- You need detailed information beyond the snippet
- The source contains data, case studies, or expert analysis
- You want to understand the full context of a finding
Iterative Refinement
Research is iterative. After initial searches:
- Review what you've learned
- Identify gaps in your understanding
- Formulate new, more targeted queries
- Repeat until you have comprehensive coverage
Quality Bar
Your research is sufficient when you can confidently answer:
- What are the key facts and data points?
- What are 2-3 concrete real-world examples?
- What do experts say about this topic?
- What are the current trends and future directions?
- What are the challenges or limitations?
- What makes this topic relevant or important now?
Common Mistakes to Avoid
- Stopping before important claims have sufficient evidence
- ❌ Relying on search snippets without reading full sources
- ❌ Searching only one aspect of a multi-faceted topic
- ❌ Ignoring contradicting viewpoints or challenges
- ❌ Using outdated information when current data exists
- Presenting unsupported claims as established findings
Output
After completing research, you should have:
- A comprehensive understanding of the topic from multiple angles
- Specific facts, data points, and statistics
- Real-world examples and case studies
- Expert perspectives and authoritative sources
- Current trends and relevant context
Produce the requested output once its factual claims have adequate support; adapt these phases to the task.
