Agent Skills

Brain in the Fish — Document Evaluation

brain-in-the-fish

Evaluates documents against criteria using multi-agent, ontology-grounded scoring to produce evidence-backed, auditable evaluation reports.

Paper Claim Audit

auto-claude-code-research-in-sleep

Zero-context auditor that verifies every numeric claim in a paper against raw result files to catch rounding, cherry-picks, and config mismatches.