
Deep Research
- 11 installs
- 1.2k repo stars
- Updated April 19, 2026
- firecrawl/firecrawl-agent
deep-research runs multi-source research with triangulation and fact-checking for topics needing three or more sources.
About
deep-research runs multi-source research with triangulation and fact-checking for topics needing three or more sources. Splits topics into search angles, uses site-targeted queries, extracts metadata from targeted scrapes, cross-references claims, assigns confidence levels, and outputs subtopic-structured citations.
- Three to five search angles per topic.
- Targeted extraction with source metadata.
- Cross-source fact-checking and confidence ratings.
- Subtopic output with inline citations.
Deep Research by the numbers
- 11 all-time installs (skills.sh)
- Ranked #11,740 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
deep-research capabilities & compatibility
- Capabilities
- deep research quick start · deep research when to use guidance · deep research integration patterns
- Use cases
- research · web search
What deep-research says it does
- Break the topic into 3-5 distinct angles
- 2-3 queries per angle using different terminology
npx skills add https://github.com/firecrawl/firecrawl-agent --skill deep-researchAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 11 |
|---|---|
| repo stars | ★ 1.2k |
| Last updated | April 19, 2026 |
| Repository | firecrawl/firecrawl-agent ↗ |
How do I use deep-research correctly?
Multi-source research with source triangulation and fact-checking. Use for any research task requiring 3+ sources.
Who is it for?
Teams implementing deep-research workflows from the research catalog.
Skip if: Skip when requirements clearly match a different specialized stack.
When should I use this skill?
User asks about deep-research, multi-source research with source triangulation and fact-checking. use for any r.
What you get
Working deep-research setup with validated configuration and next steps.
Files
Deep Research
Search Strategy
- Break the topic into 3-5 distinct angles
- 2-3 queries per angle using different terminology
- Use
site:operator for targeted searches (e.g.site:arxiv.org,site:github.com) - Include official, comparison, and review-oriented queries
- Aim for 5-10 unique, high-quality sources
Extraction
- Scrape each source with a targeted query parameter -- don't dump full pages into context
- Extract: key claims, data points, dates, attributed quotes
- Record author, publication, date, and URL for every source
Fact-Checking
- Cross-reference claims across 2+ sources
- Flag single-source claims explicitly
- Assign confidence: high (3+ sources agree), medium (2), low (1 or conflicting)
- Include contrarian viewpoints -- don't confirmation-bias the results
Output
- Structure by subtopic, not by source
- Inline citations for every claim
- Call formatOutput with the structured data
Related skills
FAQ
What does deep-research do?
deep-research runs multi-source research with triangulation and fact-checking for topics needing three or more sources.
When should I use deep-research?
User asks about deep-research, multi-source research with source triangulation and fact-checking. use for any r.
Is this skill safe to install?
Review the Security Audits panel on this page before installing in production.