{"id":"1d391839-d774-4fbe-b9d5-666f619f95a9","shortId":"RFuQqg","kind":"skill","title":"sn-search-academic","tagline":"搜索学术论文和百科知识：ArXiv 预印本、Semantic Scholar（含引用数）、PubMed 生医文献、Wikipedia 百科。支持按章节读取 ArXiv HTML 全文和 PMC 开放获取全文，适合学术调研和深度阅读。","description":"# sn-search-academic - 学术搜索\n\n搜索 ArXiv、Semantic Scholar、PubMed、Wikipedia 四个学术平台，并提供 ArXiv 和 PMC 的**全文章节阅读**能力。全部免费，部分脚本有可选 API key 可提升限额。\n\n## 依赖\n\n运行脚本前先安装本 skill 的 Python 依赖：\n\n```bash\npython3 -m pip install -r skills/sn-search-academic/requirements.txt\n```\n\n如果项目使用 `uv` 环境：\n\n```bash\nuv pip install -r skills/sn-search-academic/requirements.txt\n```\n\n`arxiv_paper.py` 需要 `beautifulsoup4` 解析 ArXiv HTML；其他脚本主要依赖 `httpx` 发起请求。\n\n## 可用脚本\n\n| 脚本 | 平台 | 用途 | API key |\n|------|------|------|---------|\n| `arxiv_search.py` | ArXiv | 预印本搜索，支持作者/标题/ID查询 | 无需 |\n| `arxiv_paper.py` | ArXiv HTML | 按章节读取 ArXiv 论文全文 | 无需 |\n| `semantic_scholar_search.py` | Semantic Scholar | 全学科搜索，含引用数和 TLDR | 无需（有 key 限额更高） |\n| `semantic_scholar_refs.py` | Semantic Scholar | 引用追溯：查论文的参考文献（backward）或被引论文（forward） | 无需（有 key 限额更高） |\n| `pubmed_search.py` | PubMed | 生医文献搜索，含结构化摘要和 PMC ID | 无需（有 key 限额更高） |\n| `pmc_paper.py` | PMC | 按章节读取 PMC 开放获取论文全文 | 无需（有 key 限额更高） |\n| `wikipedia_search.py` | Wikipedia | 百科文章搜索，支持多语言 | 无需 |\n\n## 参数说明\n\n### arxiv_search.py\n\n```bash\npython3 scripts/arxiv_search.py <query> [选项]\n```\n\n| 参数 | 说明 | 默认值 |\n|------|------|--------|\n| `query` | 搜索关键词（使用 `--id-list` 时可省略） | — |\n| `--limit`, `-n` | 返回结果数量 | 10 |\n| `--category`, `-c` | ArXiv 分类过滤（见下方\"ArXiv 分类速查\"） | — |\n| `--sort` | 排序方式：`relevance`, `date`, `submitted` | relevance |\n| `--author`, `-a` | 按作者过滤，多个用逗号分隔 | — |\n| `--title-only` | 仅在标题中搜索 | — |\n| `--id-list` | 直接按 arXiv ID 获取元数据，逗号分隔 | — |\n\n```bash\npython3 scripts/arxiv_search.py \"transformer attention mechanism\" --limit 5\npython3 scripts/arxiv_search.py \"diffusion model\" --author \"ho jonathan\" --category cs.CV\npython3 scripts/arxiv_search.py --id-list \"2409.05591,2301.07041\"\n```\n\n**输出字段**：`title`, `url`, `snippet`（摘要）, `arxiv_id`, `authors`, `published`, `updated`, `pdf_url`, `html_url`, `categories`, `primary_category`, `comment`, `journal_ref`, `doi`\n\n### arxiv_paper.py\n\n按章节读取 ArXiv 论文正文（需论文有 HTML 版本，2020 年后多数论文支持）。\n\n```bash\npython3 scripts/arxiv_paper.py <arxiv_id> [--section SECTION_NAME]\n```\n\n| 参数 | 说明 |\n|------|------|\n| `arxiv_id` | arXiv ID（如 `2409.05591` 或 `2409.05591v2`） |\n| `--section`, `-s` | 章节名（大小写不敏感，支持部分匹配）。不指定则列出所有章节。 |\n\n```bash\npython3 scripts/arxiv_paper.py 2409.05591                      # 列出章节\npython3 scripts/arxiv_paper.py 2409.05591 --section introduction\npython3 scripts/arxiv_paper.py 2409.05591 --section method\n```\n\n**列出章节输出字段**：`arxiv_id`, `abs_url`, `html_url`, `pdf_url`, `section_count`, `sections[]`（name, level）\n\n**读取章节输出字段**：`arxiv_id`, `section`, `level`, `content`, `char_count`\n\n### semantic_scholar_search.py\n\n```bash\npython3 scripts/semantic_scholar_search.py <query> [选项]\n```\n\n| 参数 | 说明 | 默认值 |\n|------|------|--------|\n| `query` | 搜索关键词（必填） | — |\n| `--limit`, `-n` | 返回结果数量 | 10 |\n| `--api-key` | Semantic Scholar API Key（也可通过 `S2_API_KEY` 环境变量） | — |\n\n```bash\npython3 scripts/semantic_scholar_search.py \"transformer architecture\" --limit 5\npython3 scripts/semantic_scholar_search.py \"RLHF language model\" --limit 10\n```\n\n**输出字段**：`title`, `url`, `snippet`（摘要，缺失时降级为 tldr）, `tldr`, `authors`, `year`, `venue`, `publication_date`, `citation_count`, `influential_citation_count`, `reference_count`, `is_open_access`, `open_access_pdf`, `fields_of_study`, `publication_types`, `doi`, `arxiv_id`, `paper_id`\n\n### semantic_scholar_refs.py\n\n引用追溯：给定一篇论文，查询它的参考文献（backward）或被引论文（forward）。\n\n```bash\npython3 scripts/semantic_scholar_refs.py <paper_id> <direction> [选项]\n```\n\n| 参数 | 说明 | 默认值 |\n|------|------|--------|\n| `paper_id` | 论文标识符：S2 ID、DOI（`10.xxxx/...`）、ArXiv ID（`2301.07041`）、PMID（`PMID:12345678`） | — |\n| `direction` | `references`=参考文献（backward），`citations`=被引论文（forward） | — |\n| `--limit`, `-n` | 返回结果数量 | 20 |\n| `--min-citations` | 最低引用数过滤 | 0 |\n| `--year-min` | 最早年份过滤 | — |\n| `--year-max` | 最晚年份过滤 | — |\n| `--api-key` | Semantic Scholar API Key（可选） | — |\n\n```bash\n# 查看某篇论文引用了哪些论文（backward：找奠基工作）\npython3 scripts/semantic_scholar_refs.py 2301.07041 references --limit 10\n\n# 查看某篇论文被谁引用（forward：找后续进展）\npython3 scripts/semantic_scholar_refs.py 2301.07041 citations --limit 10 --min-citations 50\n\n# 用 DOI 查引用，限定 2023 年以后\npython3 scripts/semantic_scholar_refs.py \"10.1038/s41586-024-07487-w\" citations --year-min 2023\n\n# 找高引参考文献\npython3 scripts/semantic_scholar_refs.py ARXIV:2005.14165 references --min-citations 100 --limit 5\n```\n\n**输出字段**：`title`, `url`, `snippet`（摘要/tldr）, `authors`, `year`, `venue`, `citation_count`, `influential_citation_count`, `is_open_access`, `open_access_pdf`, `doi`, `arxiv_id`, `paper_id`, `citation_contexts`（引用上下文句子，最多 3 条）, `citation_intents`（引用意图）\n\n**输出额外字段**：`source_paper`（被查询论文的标题/年份/引用数）, `total_available`（该方向总论文数）, `returned`（过滤后返回数）\n\n### pubmed_search.py\n\n支持 PubMed 查询语法，如字段限定（`cancer[Title]`）、日期范围（`2024[pdat]`）。\n\n```bash\npython3 scripts/pubmed_search.py <query> [选项]\n```\n\n| 参数 | 说明 | 默认值 |\n|------|------|--------|\n| `query` | 搜索关键词，支持 PubMed 查询语法 | — |\n| `--limit`, `-n` | 返回结果数量 | 10 |\n| `--api-key` | NCBI API Key（可选，限额从 3 req/s 升至 10 req/s） | — |\n\n```bash\npython3 scripts/pubmed_search.py \"CRISPR gene editing\" --limit 5\npython3 scripts/pubmed_search.py \"Alzheimer[Title] AND treatment[Title]\" --limit 5\n```\n\n**输出字段**：`title`, `url`, `snippet`（结构化摘要）, `authors`, `pmid`, `pmc_id`（有值则可传入 `pmc_paper.py`）, `pmc_url`, `journal`, `pub_date`, `volume`, `issue`, `pages`, `keywords`, `pub_types`, `doi`\n\n### pmc_paper.py\n\n读取 PubMed Central 开放获取全文（约 700 万篇生医论文，占 PubMed 约 35%）。`pubmed_search.py` 结果中 `pmc_id` 为 `null` 的论文无法使用本工具。\n\n```bash\npython3 scripts/pmc_paper.py <pmc_id> [--section SECTION_NAME]\npython3 scripts/pmc_paper.py --pmid <pmid> [--section SECTION_NAME]\n```\n\n| 参数 | 说明 |\n|------|------|\n| `pmc_id` | PMC ID（如 `PMC11119143` 或 `11119143`） |\n| `--pmid` | PubMed ID，自动转换为 PMC ID（与 `pmc_id` 二选一） |\n| `--section`, `-s` | 章节名（大小写不敏感，支持部分匹配）。不指定则列出所有章节。 |\n| `--api-key` | NCBI API Key（可选） |\n\n```bash\npython3 scripts/pmc_paper.py PMC11119143                       # 列出章节\npython3 scripts/pmc_paper.py PMC11119143 --section introduction\npython3 scripts/pmc_paper.py --pmid 38786024 --section conclusion\n```\n\n**列出章节输出字段**：`pmc_id`, `pmid`, `title`, `pmc_url`, `section_count`, `sections[]`（name, level，含子章节层级）\n\n**读取章节输出字段**：`pmc_id`, `section`, `level`, `content`（含子章节文本）, `char_count`\n\n### wikipedia_search.py\n\n```bash\npython3 scripts/wikipedia_search.py <query> [选项]\n```\n\n| 参数 | 说明 | 默认值 |\n|------|------|--------|\n| `query` | 搜索关键词（必填） | — |\n| `--limit`, `-n` | 返回结果数量 | 10 |\n| `--lang`, `-l` | 语言版本（`en`, `zh`, `ja`, `de`, `fr` 等） | en |\n\n```bash\npython3 scripts/wikipedia_search.py \"machine learning\" --limit 5\npython3 scripts/wikipedia_search.py \"深度学习\" --lang zh --limit 5\n```\n\n## 全文阅读工作流\n\n搜索脚本返回摘要，阅读脚本返回正文。两者配合可按需精读，节省 token。\n\n**ArXiv 论文**：\n1. `arxiv_search.py` 搜索 → 获取 `arxiv_id`\n2. `arxiv_paper.py <id>` 列章节 → `arxiv_paper.py <id> --section introduction` 快速判断是否深入\n3. 按需读取 `method` / `experiment` / `conclusion`\n\n**PMC 生医论文**：\n1. `pubmed_search.py` 搜索 → 结果中取 `pmc_id`（非 null 才有全文）\n2. `pmc_paper.py <pmc_id>` 列章节 → 按需读取关键章节\n\n## 引用追溯工作流\n\n通过论文的引用关系发现关键词搜索覆盖不到的相关工作。\n\n**Backward（找奠基工作）**：\n1. 关键词搜索找到高相关论文 → 取其 `paper_id` 或 `arxiv_id`\n2. `semantic_scholar_refs.py <id> references --min-citations 50` → 找到高引参考文献\n3. 筛选与研究问题相关的条目 → 用 `arxiv_paper.py` 或 `pmc_paper.py` 深入阅读\n\n**Forward（找后续进展）**：\n1. 找到领域奠基论文或关键论文 → 取其 ID\n2. `semantic_scholar_refs.py <id> citations --year-min 2024 --min-citations 10` → 找到近期高引跟进工作\n3. 筛选与研究问题相关的条目 → 深入阅读\n\n**Citation Chain（追溯演化路径）**：\n1. 从种子论文 A 出发 → backward 找到 A 的关键参考文献 B\n2. 从 B 出发 → forward 找到引用 B 的后续工作（可能发现 A 没引用的相关论文 C）\n3. 形成 B → A → ... 和 B → C → ... 的知识脉络\n\n## ArXiv 分类速查\n\n顶层领域可直接用（如 `--category cs`），子分类更精确（如 `--category cs.AI`）。\n\n| 领域 | 分类代码 | 说明 |\n|------|---------|------|\n| **计算机科学** | `cs.AI` | 人工智能 |\n| | `cs.LG` | 机器学习 |\n| | `cs.CL` | 计算语言学 / NLP |\n| | `cs.CV` | 计算机视觉 |\n| | `cs.IR` | 信息检索 |\n| | `cs.RO` | 机器人 |\n| | `cs.SE` | 软件工程 |\n| | `cs.DC` | 分布式/并行计算 |\n| | `cs.NI` | 网络与互联网 |\n| | `cs.CR` | 密码学与安全 |\n| | `cs.DB` | 数据库 |\n| | `cs.HC` | 人机交互 |\n| **统计** | `stat.ML` | 统计机器学习 |\n| | `stat.AP` | 应用统计 |\n| | `stat.ME` | 统计方法论 |\n| **数学** | `math.OC` | 优化与控制 |\n| | `math.ST` | 统计理论 |\n| | `math.CO` | 组合数学 |\n| **物理** | `physics` | 物理（全类） |\n| | `cond-mat` | 凝聚态物理 |\n| | `quant-ph` | 量子物理 |\n| | `hep-th` | 高能理论物理 |\n| **经济/金融** | `econ.GN` | 经济学综合 |\n| | `q-fin.CP` | 计算金融 |\n| | `q-fin.ST` | 统计金融 |\n| **生物/医学** | `q-bio.NC` | 神经科学 |\n| | `q-bio.GN` | 基因组学 |\n| | `q-bio.QM` | 定量方法 |\n\n## 输出格式\n\n所有脚本输出标准 JSON：\n\n```json\n{\n  \"success\": true,\n  \"query\": \"...\",\n  \"provider\": \"arxiv|semantic_scholar|pubmed|wikipedia\",\n  \"items\": [{\"title\": \"...\", \"url\": \"...\", \"snippet\": \"...\", ...}],\n  \"error\": null\n}\n```\n\n`arxiv_paper.py` 和 `pmc_paper.py` 不走 `items` 格式，直接返回结构化对象（见各自\"输出字段\"说明）。","tags":["search","academic","sensenova","skills","opensensenova","agent","agent-skills","ai-agents","ai-assistant","data-analysis","document-processing","office-automation"],"capabilities":["skill","source-opensensenova","skill-sn-search-academic","topic-agent","topic-agent-skills","topic-ai-agents","topic-ai-assistant","topic-data-analysis","topic-document-processing","topic-office-automation","topic-presentation-slides"],"categories":["SenseNova-Skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/OpenSenseNova/SenseNova-Skills/sn-search-academic","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add OpenSenseNova/SenseNova-Skills","source_repo":"https://github.com/OpenSenseNova/SenseNova-Skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 1627 github stars · SKILL.md body (8,620 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T18:53:06.106Z","embedding":null,"createdAt":"2026-05-15T06:53:11.187Z","updatedAt":"2026-05-18T18:53:06.106Z","lastSeenAt":"2026-05-18T18:53:06.106Z","tsv":"'/...':406 '/id':88 '/s41586-024-07487-w':477 '/tldr':500 '0':428 '1':768,788,805,830,852 '10':163,321,347,454,463,565,577,735,844 '10.1038':476 '10.xxxx':405 '10.xxxx/...':404 '100':492 '11119143':659 '12345678':412 '2':774,797,813,834,861 '20':423 '2005.14165':487 '2020':245 '2023':472,482 '2024':548,840 '2301.07041':216,409,451,460 '2409.05591':215,260,262,273,277,282 '3':524,574,781,821,846,873 '35':630 '38786024':696 '5':200,340,494,586,595,752,759 '50':467,819 '700':625 'ab':288 'academ':4,25 'access':370,372,511,513 'alzheim':589 'api':43,81,323,327,331,438,442,567,570,677,680 'api-key':322,437,566,676 'architectur':338 'arxiv':6,16,28,35,72,84,92,95,166,169,189,222,240,255,257,286,300,380,407,486,516,766,772,811,881,975 'arxiv_paper.py':68,91,238,775,777,824,986 'arxiv_search.py':83,145,769 'attent':197 'author':177,205,224,356,501,601 'avail':536 'b':860,863,867,875,878 'backward':113,388,416,447,803,856 'bash':52,62,146,193,247,270,308,334,391,445,550,579,638,683,722,746 'beautifulsoup4':70 'c':165,872,879 'cancer':545 'categori':164,208,231,233,885,889 'central':622 'chain':850 'char':305,719 'citat':361,364,417,426,461,466,478,491,504,507,520,526,818,836,843,849 'comment':234 'conclus':698,785 'cond':940 'cond-mat':939 'content':304,717 'context':521 'count':295,306,362,365,367,505,508,707,720 'crispr':582 'cs':886 'cs.ai':890,895 'cs.cl':899 'cs.cr':915 'cs.cv':209,902 'cs.db':917 'cs.dc':910 'cs.hc':919 'cs.ir':904 'cs.lg':897 'cs.ni':913 'cs.ro':906 'cs.se':908 'date':174,360,611 'de':742 'diffus':203 'direct':413 'doi':237,379,403,469,515,618 'econ.gn':953 'edit':584 'en':739,745 'error':984 'experi':784 'field':374 'forward':115,390,419,456,828,865 'fr':743 'gene':583 'hep':948 'hep-th':947 'ho':206 'html':17,73,93,229,243,290 'httpx':75 'id':125,157,186,190,213,223,256,258,287,301,381,383,399,402,408,517,519,604,634,653,655,662,665,668,701,714,773,793,809,812,833 'id-list':156,185,212 'influenti':363,506 'instal':56,65 'intent':527 'introduct':279,692,779 'issu':613 'item':980,990 'ja':741 'jonathan':207 'journal':235,609 'json':969,970 'key':44,82,106,118,128,137,324,328,332,439,443,568,571,678,681 'keyword':615 'l':737 'lang':736,756 'languag':344 'learn':750 'level':298,303,710,716 'limit':160,199,318,339,346,420,453,462,493,562,585,594,732,751,758 'list':158,187,214 'm':54 'machin':749 'mat':941 'math.co':933 'math.oc':929 'math.st':931 'max':435 'mechan':198 'method':284,783 'min':425,431,465,481,490,817,839,842 'min-cit':424,464,489,816,841 'model':204,345 'n':161,319,421,563,733 'name':252,297,643,649,709 'ncbi':569,679 'nlp':901 'null':636,795,985 'open':369,371,510,512 'page':614 'paper':382,398,518,531,808 'pdat':549 'pdf':227,292,373,514 'ph':945 'physic':936 'pip':55,64 'pmc':19,37,124,131,133,603,607,633,652,654,664,667,700,704,713,786,792 'pmc11119143':657,686,690 'pmc_paper.py':130,606,619,798,826,988 'pmid':410,411,602,646,660,695,702 'primari':232 'provid':974 'pub':610,616 'public':359,377 'publish':225 'pubm':11,31,121,542,560,621,628,661,978 'pubmed_search.py':120,540,631,789 'python':50 'python3':53,147,194,201,210,248,271,275,280,309,335,341,392,449,458,474,484,551,580,587,639,644,684,688,693,723,747,753 'q-bio.gn':963 'q-bio.nc':961 'q-bio.qm':965 'q-fin.cp':955 'q-fin.st':957 'quant':944 'quant-ph':943 'queri':153,315,557,729,973 'r':57,66 'ref':236 'refer':366,414,452,488,815 'relev':173,176 'req/s':575,578 'return':538 'rlhf':343 's2':330,401 'scholar':9,30,100,110,326,441,977 'scripts/arxiv_paper.py':249,272,276,281 'scripts/arxiv_search.py':148,195,202,211 'scripts/pmc_paper.py':640,645,685,689,694 'scripts/pubmed_search.py':552,581,588 'scripts/semantic_scholar_refs.py':393,450,459,475,485 'scripts/semantic_scholar_search.py':310,336,342 'scripts/wikipedia_search.py':724,748,754 'search':3,24 'section':250,251,264,278,283,294,296,302,641,642,647,648,670,691,697,706,708,715,778 'semant':8,29,99,109,325,440,976 'semantic_scholar_refs.py':108,384,814,835 'semantic_scholar_search.py':98,307 'skill':48 'skill-sn-search-academic' 'skills/sn-search-academic/requirements.txt':58,67 'sn':2,23 'sn-search-academ':1,22 'snippet':220,351,498,599,983 'sort':171 'sourc':530 'source-opensensenova' 'stat.ap':924 'stat.me':926 'stat.ml':922 'studi':376 'submit':175 'success':971 'th':949 'titl':182,218,349,496,546,590,593,597,703,981 'title-on':181 'tldr':103,354,355 'token':765 'topic-agent' 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-assistant' 'topic-data-analysis' 'topic-document-processing' 'topic-office-automation' 'topic-presentation-slides' 'total':535 'transform':196,337 'treatment':592 'true':972 'type':378,617 'updat':226 'url':219,228,230,289,291,293,350,497,598,608,705,982 'uv':60,63 'v2':263 'venu':358,503 'volum':612 'wikipedia':13,32,140,979 'wikipedia_search.py':139,721 'year':357,430,434,480,502,838 'year-max':433 'year-min':429,479,837 'zh':740,757 '万篇生医论文':626 '不指定则列出所有章节':269,675 '不走':989 '与':666 '两者配合可按需精读':763 '为':635 '也可通过':329 '二选一':669 '人工智能':896 '人机交互':920 '仅在标题中搜索':184 '从':862 '从种子论文':853 '优化与控制':930 '使用':155 '依赖':46,51 '信息检索':905 '全学科搜索':101 '全文和':18 '全文章节阅读':39 '全文阅读工作流':760 '全类':938 '全部免费':41 '关键词搜索找到高相关论文':806 '其他脚本主要依赖':74 '凝聚态物理':942 '出发':855,864 '分布式':911 '分类代码':892 '分类过滤':167 '分类速查':170,882 '列出章节':274,687 '列出章节输出字段':285,699 '列章节':776,799 '医学':960 '升至':576 '占':627 '参数':150,253,312,395,554,650,726 '参数说明':144 '参考文献':415 '发起请求':76 '取其':807,832 '可提升限额':45 '可用脚本':77 '可能发现':869 '可选':444,572,682 '含子章节层级':711 '含子章节文本':718 '含引用数':10 '含引用数和':102 '含结构化摘要和':123 '和':36,877,987 '四个学术平台':33 '基因组学':964 '多个用逗号分隔':180 '大小写不敏感':267,673 '如':259,656,884,888 '如字段限定':544 '如果项目使用':59 '子分类更精确':887 '学术搜索':26 '定量方法':966 '密码学与安全':916 '平台':79 '年以后':473 '年份':533 '年后多数论文支持':246 '并提供':34 '并行计算':912 '应用统计':925 '开放获取全文':20,623 '开放获取论文全文':134 '引用上下文句子':522 '引用意图':528 '引用数':534 '引用追溯':111,385 '引用追溯工作流':801 '形成':874 '必填':317,731 '快速判断是否深入':780 '或':261,658,810,825 '或被引论文':114,389 '所有脚本输出标准':968 '才有全文':796 '找到':857 '找到引用':866 '找到近期高引跟进工作':845 '找到领域奠基论文或关键论文':831 '找到高引参考文献':820 '找后续进展':457,829 '找奠基工作':448,804 '找高引参考文献':483 '按作者过滤':179 '按章节读取':94,132,239 '按需读取':782 '按需读取关键章节':800 '排序方式':172 '搜索':27,770,790 '搜索关键词':154,316,558,730 '搜索学术论文和百科知识':5 '搜索脚本返回摘要':761 '摘要':221,352,499 '支持':541,559 '支持作者':86 '支持多语言':142 '支持按章节读取':15 '支持部分匹配':268,674 '数学':928 '数据库':918 '无需':90,97,104,116,126,135,143 '日期范围':547 '时可省略':159 '最低引用数过滤':427 '最多':523 '最早年份过滤':432 '最晚年份过滤':436 '有':105,117,127,136 '有值则可传入':605 '机器人':907 '机器学习':898 '条':525 '查引用':470 '查看某篇论文引用了哪些论文':446 '查看某篇论文被谁引用':455 '查论文的参考文献':112 '查询':89 '查询它的参考文献':387 '查询语法':543,561 '标题':87 '格式':991 '没引用的相关论文':871 '深入阅读':827,848 '深度学习':755 '版本':244 '物理':935,937 '环境':61 '环境变量':333 '生医文献':12 '生医文献搜索':122 '生医论文':787 '生物':959 '用':468,823 '用途':80 '百科':14 '百科文章搜索':141 '的':38,49 '的关键参考文献':859 '的后续工作':868 '的知识脉络':880 '的论文无法使用本工具':637 '直接按':188 '直接返回结构化对象':992 '神经科学':962 '章节名':266,672 '等':744 '筛选与研究问题相关的条目':822,847 '约':624,629 '组合数学':934 '经济':951 '经济学综合':954 '结构化摘要':600 '结果中':632 '结果中取':791 '给定一篇论文':386 '统计':921 '统计方法论':927 '统计机器学习':923 '统计理论':932 '统计金融':958 '缺失时降级为':353 '网络与互联网':914 '能力':40 '脚本':78 '自动转换为':663 '节省':764 '获取':771 '获取元数据':191 '被引论文':418 '被查询论文的标题':532 '见下方':168 '见各自':993 '解析':71 '计算机科学':894 '计算机视觉':903 '计算语言学':900 '计算金融':956 '论文':767 '论文全文':96 '论文标识符':400 '论文正文':241 '该方向总论文数':537 '语言版本':738 '说明':151,254,313,396,555,651,727,893,995 '读取':620 '读取章节输出字段':299,712 '软件工程':909 '输出字段':217,348,495,596,994 '输出格式':967 '输出额外字段':529 '过滤后返回数':539 '运行脚本前先安装本':47 '返回结果数量':162,320,422,564,734 '追溯演化路径':851 '适合学术调研和深度阅读':21 '选项':149,311,394,553,725 '逗号分隔':192 '通过论文的引用关系发现关键词搜索覆盖不到的相关工作':802 '部分脚本有可选':42 '量子物理':946 '金融':952 '阅读脚本返回正文':762 '限定':471 '限额从':573 '限额更高':107,119,129,138 '需要':69 '需论文有':242 '非':794 '顶层领域可直接用':883 '预印本':7 '预印本搜索':85 '领域':891 '高能理论物理':950 '默认值':152,314,397,556,728","prices":[{"id":"6c903fe9-5fcd-4aa6-8ea6-aa8bc18b309f","listingId":"1d391839-d774-4fbe-b9d5-666f619f95a9","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"OpenSenseNova","category":"SenseNova-Skills","install_from":"skills.sh"},"createdAt":"2026-05-15T06:53:11.187Z"}],"sources":[{"listingId":"1d391839-d774-4fbe-b9d5-666f619f95a9","source":"github","sourceId":"OpenSenseNova/SenseNova-Skills/sn-search-academic","sourceUrl":"https://github.com/OpenSenseNova/SenseNova-Skills/tree/main/skills/sn-search-academic","isPrimary":false,"firstSeenAt":"2026-05-15T06:53:11.187Z","lastSeenAt":"2026-05-18T18:53:06.106Z"}],"details":{"listingId":"1d391839-d774-4fbe-b9d5-666f619f95a9","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"OpenSenseNova","slug":"sn-search-academic","github":{"repo":"OpenSenseNova/SenseNova-Skills","stars":1627,"topics":["agent","agent-skills","ai-agents","ai-assistant","data-analysis","document-processing","office-automation","presentation-slides"],"license":"mit","html_url":"https://github.com/OpenSenseNova/SenseNova-Skills","pushed_at":"2026-05-15T04:43:37Z","description":"Modular SenseNova skills for building AI-powered office assistants and productivity workflows","skill_md_sha":"4b002f3964c07b45d78869dd9500da7217f911e8","skill_md_path":"skills/sn-search-academic/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/OpenSenseNova/SenseNova-Skills/tree/main/skills/sn-search-academic"},"layout":"multi","source":"github","category":"SenseNova-Skills","frontmatter":{"name":"sn-search-academic","description":"搜索学术论文和百科知识：ArXiv 预印本、Semantic Scholar（含引用数）、PubMed 生医文献、Wikipedia 百科。支持按章节读取 ArXiv HTML 全文和 PMC 开放获取全文，适合学术调研和深度阅读。"},"skills_sh_url":"https://skills.sh/OpenSenseNova/SenseNova-Skills/sn-search-academic"},"updatedAt":"2026-05-18T18:53:06.106Z"}}