deep-review-skill
Stress-test papers and technical artifacts with specialist reviews.
Stress-test papers and technical artifacts with specialist reviews.
Deep Review is an experimental Claude skill for finding problems that a generic file pass may miss. After a short calibration interview, it decomposes a paper or technical artifact into specialist checks, tests claims against sources and computations where possible, and returns a severity-ranked report. Optional review memory is written only after approval, and the tool is best treated as preparation for expert judgment rather than a replacement.
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.