菜单
Use when searching Semantic Scholar for academic papers, citations, authors, similar papers, DOI/arXiv/PMID metadata, BibTeX candidates, citation graphs, or literature discovery for research papers, theses, surveys, or related work.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use when coordinating a full research project, graduation thesis, dissertation, paper pipeline, literature-to-experiment-to-writing workflow, or when deciding which research, notebook, PDF, DOCX, citation, visualization, or audit skill to use next.
Use when planning, implementing, reviewing, or refactoring research experiment code, including experiment architecture, data pipelines, model or algorithm modules, training/evaluation scripts, config management, logging/output conventions, reproducibility checks, and mapping code runs to thesis experiments.
Use when performing final checks before submitting, defending, compiling, or revising a research paper, graduation thesis, dissertation, journal manuscript, conference paper, report, response letter, reference list, figure set, or defense presentation.
Use when planning a research paper, graduation thesis, dissertation, journal manuscript, conference paper, or project report before drafting; especially when the user has an advisor-given topic/title, needs Topic Intake to Research Blueprint, or needs a research question, contribution story, chapter outline, experiment-to-claim map, figure plan, or missing-materials checklist.
Use when building a literature review, related work section, citation matrix, paper search strategy, BibTeX candidate list, or citation plan for a research paper, thesis, dissertation, survey, journal article, or conference paper.
Use when planning, designing, reviewing, or generating research-paper figures, thesis figures, experiment plots, result tables, model diagrams, method pipelines, architecture schematics, Mermaid diagrams, captions, or publication-quality visualizations.
基于 SOC 职业分类
| name | semanticscholar-skill |
| description | Use when searching Semantic Scholar for academic papers, citations, authors, similar papers, DOI/arXiv/PMID metadata, BibTeX candidates, citation graphs, or literature discovery for research papers, theses, surveys, or related work. |
Use this skill for real Semantic Scholar API searches and metadata lookup. It keeps literature discovery grounded in returned API data instead of memory.
requests.S2_API_KEY for higher rate limits.~/.codex/skills/semanticscholar-skill when globally installed.If S2_API_KEY is missing, anonymous requests may still work with stricter rate limits. Do not ask for an API key unless rate limits block the task or the user wants higher throughput.
For real API work, write one temporary Python script that imports s2.py, performs all planned queries in one run, and prints Markdown/JSON/BibTeX output. Avoid many separate API calls from the shell.
Read references/workflow.md for query patterns and examples. Read references/source-map.md for provenance and license notes.
s2.py.For each important paper, include:
source_status: normally candidate until metadata is verified elsewherenext_action: usually verify_metadata, add_to_zotero, check_with_scite, cite_in_related_work, or do_not_cite_yetzotero_status=not_added and scite/support_status=not_checked when handing candidates to a thesis literature matrixMark metadata as unverified if the API result is incomplete or suspicious. Use publisher, DOI, arXiv, PubMed, Scite, or Zotero follow-up for final citation verification.