Produce a rigorous academic peer review of a research paper, manuscript, or preprint (PDF, markdown, TeX, DOCX, HTML, or EPUB) using the full coarse pipeline with the user's local Claude Code subscription doing all the LLM reasoning. Every pipeline stage — structure analysis, overview synthesis, per-section review, proof verification, editorial pass — is served by a headless `claude -p` subprocess instead of a paid API. Use when the user asks to review, critique, referee, or provide feedback on an academic paper. Takes 10-25 minutes. Do NOT use for code review, blog posts, or non-academic documents.
Produce a rigorous academic peer review of a research paper, manuscript, or preprint (PDF, markdown, TeX, DOCX, HTML, or EPUB) using the full coarse pipeline with the user's local Codex CLI (ChatGPT subscription) doing all the LLM reasoning. Every pipeline stage — structure analysis, overview synthesis, per-section review, proof verification, editorial pass — is served by a headless `codex exec` subprocess instead of a paid API. Use when the user asks to review, critique, referee, or provide feedback on an academic paper. Takes 10-25 minutes.
Produce a rigorous academic peer review of a research paper, manuscript, or preprint (PDF, markdown, TeX, DOCX, HTML, or EPUB) using the full coarse pipeline with the user's local Gemini CLI (Google AI subscription) doing all the LLM reasoning. Every pipeline stage — structure analysis, overview synthesis, per-section review, proof verification, editorial pass — is served by a headless `gemini -p` subprocess instead of a paid API. Use when the user asks to review, critique, referee, or provide feedback on an academic paper. Takes 10-25 minutes.