deep-research

Solid

Multi-source research on a topic with citations

AI & Automation 148 stars 60 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 82/100

Stars 20%
72
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
69
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Deep Research Conduct thorough multi-source research on a topic, verify claims, and produce a cited report. ## Instructions 1. Clarify the research question. If the user's query is too broad or ambiguous, ask 2-3 focused questions to narrow the scope before proceeding. 2. Search for information across multiple sources using varied search queries. Use at least 3 different query phrasings to ensure breadth. 3. Fetch and read the most relevant sources. Prioritize authoritative sources: official documentation, peer-reviewed papers, reputable publications, primary data. 4. Cross-reference key claims across at least 2 independent sources. Flag any contradictions or disputed points. 5. Verify factual claims (statistics, dates, technical specifications) against primary sources where possible. 6. Synthesize findings into a structured report: - **Summary**: Key findings in 2-3 sentences. - **Detailed Analysis**: Organized by subtopic with evidence and reasoning. - **Considerations**: Trade-offs, limitations, or open questions. - **Sources**: Full list of sources with titles and URLs. 7. Cite sources inline using numbered references (e.g., [1], [2]) linked to the sources list. 8. Distinguish between well-established facts, expert opinions, and uncertain claims. 9. If the user requests, write the report to a file. Otherwise, present it directly.

Details

Author
prapaa-ai
Repository
prapaa-ai/agav
Created
1 months ago
Last Updated
today
Language
TypeScript
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category