Claude-Mini

Convert a PDF (or any document) to clean markdown so Claude can read it efficiently. Tries Microsoft MarkItDown first; falls back to OpenDataLoader-PDF for complex layouts (multi-column papers, dense tables, math). Use when user says "convert this PDF", "make this document readable", "turn paper.pdf into markdown", "preprocess this document", or before reading any PDF for analysis.

Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.

Deep consistency audit of the entire repository infrastructure. Launches 4 parallel specialist agents to find factual errors, code bugs, count mismatches, and cross-document inconsistencies. Then fixes all issues and loops until clean. Use when: after making broad changes, before releases, or when user says "audit", "find inconsistencies", "check everything".

Draft a structured preregistration document (OSF, AsPredicted, or AEA RCT Registry style) from a research spec or free-form study description. Output is a Markdown file with hypotheses, design, sampling plan, analysis plan, exclusions, and inference criteria — annotated with MUST / SHOULD / MAY clarity flags. Use when user says "preregister", "draft a preregistration", "OSF preregistration", "AsPredicted", "AEA RCT registry", "PAP", "preanalysis plan", or before launching an experiment / data collection / analysis on data the analyst has not yet seen. NOT a registry submission tool — produces a document the user uploads to OSF / AsPredicted / AEA themselves.

Adversarial QA workflow comparing Quarto HTML against Beamer PDF benchmark. Iterates between critic (finds issues) and fixer (applies fixes) until APPROVED or max iterations reached.

Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated peer-review pipeline (editor + 2 dispositioned referees + editorial decision, calibrated to a target journal). R&R continuation via --peer --r2/--r3; hostile-editor stress test via --peer --stress. Auto-invokes /review-r + /audit-reproducibility on referenced scripts unless --no-cross-artifact.

Comprehensive slide excellence review combining visual audit, pedagogical review, and proofreading. Produces three reports and a combined summary.

Validate bibliography entries against citations in all lecture files. Structural checks (missing/unused entries, malformed fields) by default; `--semantic` adds citation-drift detection, DOI verification, and style-consistency checks.

Run Chain-of-Verification (CoVe) on a draft or a block of text with factual claims. Spawns the `claim-verifier` agent in a forked (fresh) context so it never sees the draft — then reports which claims are supported, contradicted, or unverifiable. Use when user says "verify these citations", "check the claims in X", "did I hallucinate anything", "fact-check this draft", "run CoVe on this", or after any text generation that asserts facts about papers, datasets, or numerical results. NOT for style/grammar review (use `/proofread`) or substance review (use `/review-paper`).

Run holistic pedagogical review on lecture slides. Checks narrative arc, PhD student prerequisites, worked examples, notation clarity, and deck pacing.

Perform adversarial visual audit of Quarto or Beamer slides checking for overflow, font consistency, box fatigue, and layout issues.