journal-club-reviewlisted

Produce a journal-club-style paper presentation (9 sections: TL;DR, Problem, Key Idea, How It Works, Key Results, Why It Matters, Strengths/Limitations/Open Questions, Discussion Questions, Takeaways) from an arXiv ID/URL, a PDF, raw text/markdown, or a local LaTeX source (.tex / project dir). Helps a reading group UNDERSTAND and DISCUSS the paper — not score or accept/reject it. Grounds every claim in the source, renders math as LaTeX, auto-matches the source language (Korean source -> Korean review). When LaTeX source is available (arXiv e-print or local .tex), embeds the paper's real figures with captions; optionally generates two friendly-whiteboard infographic figures via the bundled codex image_generation tool. Use when the user wants a journal-club review, paper walkthrough/presentation, or paper explainer, to "review this PDF/paper like a journal club", or 논문 저널클�� 리뷰/발표자료/논문 설명. For an OpenReview referee report use workshop-paper-review; for an adversarial pre-submission audit use adversarial-review.
Axect/skills · ★ 3 · AI & Automation · score 76

Install: claude install-skill Axect/skills

# Journal-Club Review Turn any paper (arXiv ID/URL, PDF, text, or a local LaTeX source) into a journal-club presentation: a warm, accurate, discussion-oriented walkthrough in nine sections, with LaTeX math, the paper's real figures (when source is available), and two optional infographic figures. This is a teaching/discussion artifact, not a referee report: no scores, no accept/reject. ## When to use - "Give me a journal-club review of 2401.00001" - "Review this PDF like a journal club" / "make presentation notes for this paper" - "이 논문 저널클럽 리뷰 만들어줘" / "발표자료처럼 정리해줘" - Any text or markdown draft the user wants walked through for a reading group. If the user wants a peer-review referee report (rating, confidence, weaknesses for OpenReview) use `workshop-paper-review`. For an adversarial pre-submission audit of their own draft use `adversarial-review`. ## Inputs One of: - arXiv id (`2401.00001`, `2401.00001v2`, `hep-ph/0101001`) or arXiv URL - a local PDF path - a local `.md` / `.txt` path, or pasted text - a local LaTeX source: a `.tex` file or a project directory (e.g. an Overleaf checkout). Figures referenced by the source are harvested automatically. ## Workflow ### 1. Ingest the source Run the extractor to get a uniform working directory with `source.md`: ```bash uv run scripts/extract_text.py "<arxiv-id | url | path>" ``` (`scripts/extract_text.py` is relative to this skill's base directory; pass an absolute path if your cwd is elsewhere.) It prints a JSON su