메뉴
Deep analysis of a single paper: download PDF, extract figures, generate structured 20+ section note, fill LLM placeholders.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
严谨执行论文搜索、文献综述、related work、paper search、literature review、survey synthesis、baseline comparison 与研究路线设计。Use when the user asks for papers, SOTA, baselines, related work, or research planning.
Use when deciding where a knowledge card should live in the knowledge tree, choosing a major domain and subdomain, designing routing policy, or diagnosing why a card was routed to the wrong folder. Reads the repository routing guide and policy before deciding.
Daily paper discovery workflow: search arXiv + Semantic Scholar, score, deduplicate, and generate a recommendation note. Also handles individual paper searches by topic.
| name | paper-analysis |
| description | Deep analysis of a single paper: download PDF, extract figures, generate structured 20+ section note, fill LLM placeholders. |
| allowed-tools | Bash |
Generate a comprehensive analysis note for a single paper.
download_paper(paper_id="2510.24701", title="Paper Title", domain="LLM")
This caches the PDF locally under paper-notes/<title>/.
extract_paper_images(paper_id="2510.24701")
Auto-detects the local PDF. Images go to paper-notes/<title>/images/.
analyze_paper(paper_json='{"title": "...", "authors": [...], "arxiv_id": "..."}', language="zh")
Returns:
note_path: path to the generated markdown notequality_check: whether the note has unfilled placeholderspdf_text: full text extracted from the PDF (if available)instructions: if placeholders exist, instructions to fill themThe generated note contains <!-- LLM: describe method --> style placeholders. When instructions is non-null, you MUST fill all placeholders using the pdf_text field:
note_path.<!-- LLM: ... --> placeholder, replace it with substantive content drawn from pdf_text.| Section | What to write |
|---|---|
| Core information | One-sentence contribution, key result, paper type |
| Abstract translation | Translate or paraphrase the abstract with domain context |
| Research background | What problem existed, why it matters |
| Research questions | List the explicit or implicit questions the paper addresses |
| Method overview | Architecture, algorithm, pipeline — with specifics |
| Experimental results | Datasets, metrics, comparisons, ablation findings |
| Deep analysis | Strengths, weaknesses, assumptions, limitations |
| Comparison with related work | Position vs. prior art |
| Technical roadmap | Where this fits in the broader research trajectory |
| Future work | Open questions the paper raises |
| Comprehensive evaluation | Your own 1-5 rating with justification |
| My notes | Leave empty for user to fill |
paper_to_card(paper_json='...', note_path='/path/to/note.md')
link_paper_keywords()
Scans all notes and auto-creates [[wiki-links]] for technical terms.