deep-research

Installation
SKILL.md

Deep Research

Execute a high-intensity research protocol focused on exhaustive discovery, continuous recursive reflection, and high-density analytical reporting. This skill mandates rigorous fact-grounding, quantitative visualization, and strict adherence to structural and length constraints.

đź“‚ Output Path

Final report destination: /mnt/agents/output/report.md

🚀 Research & Discovery Phase (The 10+ Step Loop)

  1. Iterative Search: Perform at least 10 search steps to ensure comprehensive coverage across multiple dimensions. Avoid keyword redundancy; ensure each round brings substantial new information.
  2. Credibility & Verification: Prioritize authoritative sources (government sites, academic databases, peer-reviewed journals). Never fabricate data. Every statistic and claim must be accurate and traceable.
  3. Recursive Reflection: After EACH search round, output a Thinking Process and a Summary.
    • Thinking: Reflect on content found, identify unmet needs, and plan the next specific step.
    • Summary: Concise recap of key findings.
    • Constraint: Both sections must be short and concise.
  4. Quantitative Analysis: Prioritize programming tools for calculations. Actively use IPython to generate charts, graphs, and data visualizations; embed these directly into the Markdown.

📝 Report Engineering Standards

Installs
19
GitHub Stars
16
First Seen
Apr 29, 2026
deep-research — haomingz/kimi-skills