search-drill-iterate
Deepen a research document across iterations without repeating the same searches.
Deepen a research document across iterations without repeating the same searches.
Provide a topic, an optional research file, and an iteration count. Each fresh subagent reads the document's findings, investigated paths, decision log, and open questions, then spends its rounds only on unresolved gaps before updating the same file. Dead ends are marked `UNFILLABLE`, and the document is the sole handoff between iterations, preventing later passes from rediscovering already covered facts.
Resource types
Use cases
Platforms
Generate study-design-aware clinical Table 1 outputs in HTML, Word, and LaTeX.
Retrieve cited Quran and Sahih hadith texts through a RAG-backed Claude skill.
Capabilities
Public GitHub facts last synced Jul 10, 2026.
Define product problems through six research lenses before proposing solutions.
Review ML and AI papers with evidence-based critiques and verified references.