deep-reviewlisted

# Deep Review Use this skill to review papers and other technical artifacts with the depth of a serious referee, domain expert, or adversarial collaborator. ## Start Here 1. Identify the artifact source: local PDF, arXiv URL, markdown/text draft, repository artifact, or pasted content. 2. Check for local review memory in `.deep-review/`. If present, read it before the calibration interview and summarize any preferences you plan to apply. 3. If the artifact is a local PDF or arXiv URL and text extraction is needed, prefer the scripts in `scripts/`. 4. Before doing substantive review, read `references/orchestrator_protocol.md`. 5. Ask a short calibration interview before reviewing. Use `references/calibration_questions.md` to select questions. 6. Choose the review depth: - `quick`: at least 2 specialist passes, 1 self-critique round. - `standard`: at least 4 specialist passes, 1 self-critique round. - `deep`: at least 8 specialist passes, 2 self-critique rounds. 7. Produce the final report using `references/output_format.md` and the taxonomy in `references/review_rubric.md`. 8. At the end, ask whether to save or update review memory. Only write to `.deep-review/` after explicit user approval. Script examples: ```bash python3 .claude/skills/deep-review/scripts/fetch_arxiv_pdf.py https://arxiv.org/abs/2405.20194 --out /tmp/paper.pdf python3 .claude/skills/deep-review/scripts/extract_pdf_text.py /tmp/paper.pdf --json ``` If a helper script fails because of network,