[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7356NP9WARPR0B1AAYF0C76":3,"skill-same:01M7356NP9WARPR0B1AAYF0C76":54},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M7356NP9WARPR0B1AAYF0C76","alterlab-arxiv",null,"Search and retrieve preprints from arXiv via the Atom API. Use this skill when searching for papers in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, or economics by keywords, authors, arXiv IDs, date ranges, or categories. Part of the AlterLab Academic Skills suite.","roohe\u002Fagentic-super-skills","roohe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99054084?v=4","01M734WCDFP6RZVT5CNM00QR26","01M734WCE4BD0T4NZS5PCV9V5F",10,"MIT","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Falterlab-arxiv\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: alterlab-arxiv\ndescription: Search and retrieve preprints from arXiv via the Atom API. Use this skill when searching for papers in physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering, or economics by keywords, authors, arXiv IDs, date ranges, or categories. Part of the AlterLab Academic Skills suite.\nlicense: MIT\nmetadata:\n    skill-author: AlterLab\n    version: \"1.0.0\"\n---\n\n# arXiv Database\n\n## Overview\n\nThis skill provides Python tools for searching and retrieving preprints from arXiv.org via its public Atom API. It supports keyword search, author search, category filtering, arXiv ID lookup, and PDF download. Results are returned as structured JSON with titles, abstracts, authors, categories, and links.\n\n## When to Use This Skill\n\nUse this skill when:\n- Searching for preprints in CS, ML, AI, physics, math, statistics, q-bio, q-fin, or economics\n- Looking up specific papers by arXiv ID (e.g., `2309.10668`)\n- Tracking an author's recent preprints\n- Filtering papers by arXiv category (e.g., `cs.LG`, `cs.CL`, `stat.ML`)\n- Downloading PDFs for full-text analysis\n- Building literature review datasets for AI\u002FML research\n- Monitoring new submissions in a subfield\n\nConsider alternatives when:\n- Searching for biomedical literature specifically -> Use **pubmed-database** or **biorxiv-database**\n- You need citation counts or impact metrics -> Use **openalex-database**\n- You need peer-reviewed journal articles only -> Use **pubmed-database**\n\n## Core Search Capabilities\n\n### 1. Keyword Search\n\nSearch for papers by keywords in titles, abstracts, or all fields.\n\n```bash\npython scripts\u002Farxiv_search.py \\\n  --keywords \"sparse autoencoders\" \"mechanistic interpretability\" \\\n  --max-results 20 \\\n  --output results.json\n```\n\nWith category filter:\n```bash\npython scripts\u002Farxiv_search.py \\\n  --keywords \"transformer\" \"attention mechanism\" \\\n  --category cs.LG \\\n  --max-results 50 \\\n  --output transformer_papers.json\n```\n\nSearch specific fields:\n```bash\n# Title only\npython scripts\u002Farxiv_search.py \\\n  --keywords \"GRPO\" \\\n  --search-field ti \\\n  --max-results 10\n\n# Abstract only\npython scripts\u002Farxiv_search.py \\\n  --keywords \"reward model\" \"RLHF\" \\\n  --search-field abs \\\n  --max-results 30\n```\n\n### 2. Author Search\n\n```bash\npython scripts\u002Farxiv_search.py \\\n  --author \"Anthropic\" \\\n  --max-results 50 \\\n  --output anthropic_papers.json\n```\n\n```bash\npython scripts\u002Farxiv_search.py \\\n  --author \"Ilya Sutskever\" \\\n  --category cs.LG \\\n  --max-results 20\n```\n\n### 3. arXiv ID Lookup\n\nRetrieve metadata for specific papers:\n\n```bash\npython scripts\u002Farxiv_search.py \\\n  --ids 2309.10668 2406.04093 2310.01405 \\\n  --output sae_papers.json\n```\n\nFull arXiv URLs also accepted:\n```bash\npython scripts\u002Farxiv_search.py \\\n  --ids \"https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.10668\"\n```\n\n### 4. Category Browsing\n\nList recent papers in a category:\n```bash\npython scripts\u002Farxiv_search.py \\\n  --category cs.AI \\\n  --max-results 100 \\\n  --sort-by submittedDate \\\n  --output recent_cs_ai.json\n```\n\n### 5. PDF Download\n\n```bash\npython scripts\u002Farxiv_search.py \\\n  --ids 2309.10668 \\\n  --download-pdf papers\u002F\n```\n\nBatch download from search results:\n```python\nimport json\nfrom scripts.arxiv_search import ArxivSearcher\n\nsearcher = ArxivSearcher()\n\n# Search first\nresults = searcher.search(query=\"ti:sparse autoencoder\", max_results=5)\n\n# Download all\nfor paper in results:\n    arxiv_id = paper[\"arxiv_id\"]\n    searcher.download_pdf(arxiv_id, f\"papers\u002F{arxiv_id.replace('\u002F', '_')}.pdf\")\n```\n\n## arXiv Categories\n\n### Computer Science (cs.*)\n| Category | Description |\n|----------|-------------|\n| `cs.AI` | Artificial Intelligence |\n| `cs.CL` | Computation and Language (NLP) |\n| `cs.CV` | Computer Vision |\n| `cs.LG` | Machine Learning |\n| `cs.NE` | Neural and Evolutionary Computing |\n| `cs.RO` | Robotics |\n| `cs.CR` | Cryptography and Security |\n| `cs.DS` | Data Structures and Algorithms |\n| `cs.IR` | Information Retrieval |\n| `cs.SE` | Software Engineering |\n\n### Statistics & Math\n| Category | Description |\n|----------|-------------|\n| `stat.ML` | Machine Learning (Statistics) |\n| `stat.ME` | Methodology |\n| `math.OC` | Optimization and Control |\n| `math.ST` | Statistics Theory |\n\n### Other Relevant Categories\n| Category | Description |\n|----------|-------------|\n| `q-bio.BM` | Biomolecules |\n| `q-bio.GN` | Genomics |\n| `q-bio.QM` | Quantitative Methods |\n| `q-fin.ST` | Statistical Finance |\n| `eess.SP` | Signal Processing |\n| `physics.comp-ph` | Computational Physics |\n\nFull list: see [references\u002Fapi_reference.md](references\u002Fapi_reference.md).\n\n## Query Syntax\n\nThe arXiv API uses prefix-based field searches combined with Boolean operators.\n\n**Field prefixes:**\n- `ti:` - Title\n- `au:` - Author\n- `abs:` - Abstract\n- `cat:` - Category\n- `all:` - All fields (default)\n- `co:` - Comment\n- `jr:` - Journal reference\n- `id:` - arXiv ID\n\n**Boolean operators** (must be UPPERCASE):\n```\nti:transformer AND abs:attention\nau:bengio OR au:lecun\ncat:cs.LG ANDNOT cat:cs.CV\n```\n\n**Grouping with parentheses:**\n```\n(ti:sparse AND ti:autoencoder) AND cat:cs.LG\nau:anthropic AND (abs:interpretability OR abs:alignment)\n```\n\n**Examples:**\n```python\nfrom scripts.arxiv_search import ArxivSearcher\n\nsearcher = ArxivSearcher()\n\n# Papers about SAEs in ML\nresults = searcher.search(\n    query=\"ti:sparse autoencoder AND cat:cs.LG\",\n    max_results=50,\n    sort_by=\"submittedDate\"\n)\n\n# Specific author in specific field\nresults = searcher.search(\n    query=\"au:neel nanda AND cat:cs.LG\",\n    max_results=20\n)\n\n# Complex boolean query\nresults = searcher.search(\n    query=\"(abs:RLHF OR abs:reinforcement learning from human feedback) AND cat:cs.CL\",\n    max_results=100\n)\n```\n\n## Output Format\n\nAll searches return structured JSON:\n\n```json\n{\n  \"query\": \"ti:sparse autoencoder AND cat:cs.LG\",\n  \"result_count\": 15,\n  \"results\": [\n    {\n      \"arxiv_id\": \"2309.10668\",\n      \"title\": \"Towards Monosemanticity: Decomposing Language Models With Dictionary Learning\",\n      \"authors\": [\"Trenton Bricken\", \"Adly Templeton\", \"...\"],\n      \"abstract\": \"Full abstract text...\",\n      \"categories\": [\"cs.LG\", \"cs.AI\"],\n      \"primary_category\": \"cs.LG\",\n      \"published\": \"2023-09-19T17:58:00Z\",\n      \"updated\": \"2023-10-04T14:22:00Z\",\n      \"doi\": \"10.48550\u002FarXiv.2309.10668\",\n      \"pdf_url\": \"http:\u002F\u002Farxiv.org\u002Fpdf\u002F2309.10668v1\",\n      \"abs_url\": \"http:\u002F\u002Farxiv.org\u002Fabs\u002F2309.10668v1\",\n      \"comment\": \"42 pages, 30 figures\",\n      \"journal_ref\": \"\"\n    }\n  ]\n}\n```\n\n## Common Usage Patterns\n\n### Literature Review Workflow\n\n```python\nfrom scripts.arxiv_search import ArxivSearcher\nimport json\n\nsearcher = ArxivSearcher()\n\n# 1. Broad search\nresults = searcher.search(\n    query=\"abs:mechanistic interpretability AND cat:cs.LG\",\n    max_results=200,\n    sort_by=\"submittedDate\"\n)\n\n# 2. Save results\nwith open(\"interp_papers.json\", \"w\") as f:\n    json.dump({\"result_count\": len(results), \"results\": results}, f, indent=2)\n\n# 3. Filter and analyze\nimport pandas as pd\ndf = pd.DataFrame(results)\nprint(f\"Total papers: {len(df)}\")\nprint(f\"Date range: {df['published'].min()} to {df['published'].max()}\")\nprint(f\"\\nTop categories:\")\nprint(df[\"primary_category\"].value_counts().head(10))\n```\n\n### Track a Research Group\n\n```python\nsearcher = ArxivSearcher()\n\ngroups = {\n    \"anthropic\": \"au:anthropic AND (cat:cs.LG OR cat:cs.CL)\",\n    \"openai\": \"au:openai AND cat:cs.CL\",\n    \"deepmind\": \"au:deepmind AND cat:cs.LG\",\n}\n\nfor name, query in groups.items():\n    results = searcher.search(query=query, max_results=50, sort_by=\"submittedDate\")\n    print(f\"{name}: {len(results)} recent papers\")\n```\n\n### Monitor New Submissions\n\n```python\nsearcher = ArxivSearcher()\n\n# Most recent ML papers\nresults = searcher.search(\n    query=\"cat:cs.LG\",\n    max_results=50,\n    sort_by=\"submittedDate\",\n    sort_order=\"descending\"\n)\n\nfor paper in results[:10]:\n    print(f\"[{paper['published'][:10]}] {paper['title']}\")\n    print(f\"  {paper['abs_url']}\\n\")\n```\n\n## Python API\n\n```python\nfrom scripts.arxiv_search import ArxivSearcher\n\nsearcher = ArxivSearcher(verbose=True)\n\n# Free-form query (uses arXiv query syntax)\nresults = searcher.search(query=\"...\", max_results=50)\n\n# Lookup by ID\npapers = searcher.get_by_ids([\"2309.10668\", \"2406.04093\"])\n\n# Download PDF\nsearcher.download_pdf(\"2309.10668\", \"paper.pdf\")\n\n# Build query from components\nquery = ArxivSearcher.build_query(\n    title=\"sparse autoencoder\",\n    author=\"anthropic\",\n    category=\"cs.LG\"\n)\nresults = searcher.search(query=query, max_results=20)\n```\n\n## Best Practices\n\n1. **Respect rate limits**: The API requests 3-second delays between calls. The script handles this automatically.\n2. **Use category filters**: Dramatically reduces noise. `cs.LG` is where most ML papers live.\n3. **Cache results**: Save to JSON to avoid re-fetching.\n4. **Use `sort_by=submittedDate`** for recent papers, `relevance` for keyword searches.\n5. **Max 300 results per query**: arXiv API caps at this. For larger sets, paginate with `start` parameter.\n6. **arXiv IDs**: Use bare IDs (`2309.10668`), not full URLs, in programmatic code.\n7. **Combine with openalex-database**: For citation counts and impact metrics arXiv doesn't provide.\n\n## Limitations\n\n- **No full-text search**: Only searches metadata (title, abstract, authors, comments)\n- **No citation data**: Use openalex-database or Semantic Scholar for citations\n- **Max 300 results**: Per query. Use pagination for larger sets.\n- **Rate limited**: ~1 request per 3 seconds recommended\n- **Atom XML responses**: The script parses these into JSON automatically\n- **Search lag**: New papers may take hours to appear in API results\n\n## Reference Documentation\n\n- **API Reference**: See [references\u002Fapi_reference.md](references\u002Fapi_reference.md) for full endpoint specs, all categories, and response schemas\n","# arXiv Database\n\n## Overview\n\nThis skill provides Python tools for searching and retrieving preprints from arXiv.org via its public Atom API. It supports keyword search, author search, category filtering, arXiv ID lookup, and PDF download. Results are returned as structured JSON with titles, abstracts, authors, categories, and links.\n\n## When to Use This Skill\n\nUse this skill when:\n- Searching for preprints in CS, ML, AI, physics, math, statistics, q-bio, q-fin, or economics\n- Looking up specific papers by arXiv ID (e.g., `2309.10668`)\n- Tracking an author's recent preprints\n- Filtering papers by arXiv category (e.g., `cs.LG`, `cs.CL`, `stat.ML`)\n- Downloading PDFs for full-text analysis\n- Building literature review datasets for AI\u002FML research\n- Monitoring new submissions in a subfield\n\nConsider alternatives when:\n- Searching for biomedical literature specifically -> Use **pubmed-database** or **biorxiv-database**\n- You need citation counts or impact metrics -> Use **openalex-database**\n- You need peer-reviewed journal articles only -> Use **pubmed-database**\n\n## Core Search Capabilities\n\n### 1. Keyword Search\n\nSearch for papers by keywords in titles, abstracts, or all fields.\n\n```bash\npython scripts\u002Farxiv_search.py \\\n  --keywords \"sparse autoencoders\" \"mechanistic interpretability\" \\\n  --max-results 20 \\\n  --output results.json\n```\n\nWith category filter:\n```bash\npython scripts\u002Farxiv_search.py \\\n  --keywords \"transformer\" \"attention mechanism\" \\\n  --category cs.LG \\\n  --max-results 50 \\\n  --output transformer_papers.json\n```\n\nSearch specific fields:\n```bash\n# Title only\npython scripts\u002Farxiv_search.py \\\n  --keywords \"GRPO\" \\\n  --search-field ti \\\n  --max-results 10\n\n# Abstract only\npython scripts\u002Farxiv_search.py \\\n  --keywords \"reward model\" \"RLHF\" \\\n  --search-field abs \\\n  --max-results 30\n```\n\n### 2. Author Search\n\n```bash\npython scripts\u002Farxiv_search.py \\\n  --author \"Anthropic\" \\\n  --max-results 50 \\\n  --output anthropic_papers.json\n```\n\n```bash\npython scripts\u002Farxiv_search.py \\\n  --author \"Ilya Sutskever\" \\\n  --category cs.LG \\\n  --max-results 20\n```\n\n### 3. arXiv ID Lookup\n\nRetrieve metadata for specific papers:\n\n```bash\npython scripts\u002Farxiv_search.py \\\n  --ids 2309.10668 2406.04093 2310.01405 \\\n  --output sae_papers.json\n```\n\nFull arXiv URLs also accepted:\n```bash\npython scripts\u002Farxiv_search.py \\\n  --ids \"https:\u002F\u002Farxiv.org\u002Fabs\u002F2309.10668\"\n```\n\n### 4. Category Browsing\n\nList recent papers in a category:\n```bash\npython scripts\u002Farxiv_search.py \\\n  --category cs.AI \\\n  --max-results 100 \\\n  --sort-by submittedDate \\\n  --output recent_cs_ai.json\n```\n\n### 5. PDF Download\n\n```bash\npython scripts\u002Farxiv_search.py \\\n  --ids 2309.10668 \\\n  --download-pdf papers\u002F\n```\n\nBatch download from search results:\n```python\nimport json\nfrom scripts.arxiv_search import ArxivSearcher\n\nsearcher = ArxivSearcher()\n\n# Search first\nresults = searcher.search(query=\"ti:sparse autoencoder\", max_results=5)\n\n# Download all\nfor paper in results:\n    arxiv_id = paper[\"arxiv_id\"]\n    searcher.download_pdf(arxiv_id, f\"papers\u002F{arxiv_id.replace('\u002F', '_')}.pdf\")\n```\n\n## arXiv Categories\n\n### Computer Science (cs.*)\n| Category | Description |\n|----------|-------------|\n| `cs.AI` | Artificial Intelligence |\n| `cs.CL` | Computation and Language (NLP) |\n| `cs.CV` | Computer Vision |\n| `cs.LG` | Machine Learning |\n| `cs.NE` | Neural and Evolutionary Computing |\n| `cs.RO` | Robotics |\n| `cs.CR` | Cryptography and Security |\n| `cs.DS` | Data Structures and Algorithms |\n| `cs.IR` | Information Retrieval |\n| `cs.SE` | Software Engineering |\n\n### Statistics & Math\n| Category | Description |\n|----------|-------------|\n| `stat.ML` | Machine Learning (Statistics) |\n| `stat.ME` | Methodology |\n| `math.OC` | Optimization and Control |\n| `math.ST` | Statistics Theory |\n\n### Other Relevant Categories\n| Category | Description |\n|----------|-------------|\n| `q-bio.BM` | Biomolecules |\n| `q-bio.GN` | Genomics |\n| `q-bio.QM` | Quantitative Methods |\n| `q-fin.ST` | Statistical Finance |\n| `eess.SP` | Signal Processing |\n| `physics.comp-ph` | Computational Physics |\n\nFull list: see [references\u002Fapi_reference.md](references\u002Fapi_reference.md).\n\n## Query Syntax\n\nThe arXiv API uses prefix-based field searches combined with Boolean operators.\n\n**Field prefixes:**\n- `ti:` - Title\n- `au:` - Author\n- `abs:` - Abstract\n- `cat:` - Category\n- `all:` - All fields (default)\n- `co:` - Comment\n- `jr:` - Journal reference\n- `id:` - arXiv ID\n\n**Boolean operators** (must be UPPERCASE):\n```\nti:transformer AND abs:attention\nau:bengio OR au:lecun\ncat:cs.LG ANDNOT cat:cs.CV\n```\n\n**Grouping with parentheses:**\n```\n(ti:sparse AND ti:autoencoder) AND cat:cs.LG\nau:anthropic AND (abs:interpretability OR abs:alignment)\n```\n\n**Examples:**\n```python\nfrom scripts.arxiv_search import ArxivSearcher\n\nsearcher = ArxivSearcher()\n\n# Papers about SAEs in ML\nresults = searcher.search(\n    query=\"ti:sparse autoencoder AND cat:cs.LG\",\n    max_results=50,\n    sort_by=\"submittedDate\"\n)\n\n# Specific author in specific field\nresults = searcher.search(\n    query=\"au:neel nanda AND cat:cs.LG\",\n    max_results=20\n)\n\n# Complex boolean query\nresults = searcher.search(\n    query=\"(abs:RLHF OR abs:reinforcement learning from human feedback) AND cat:cs.CL\",\n    max_results=100\n)\n```\n\n## Output Format\n\nAll searches return structured JSON:\n\n```json\n{\n  \"query\": \"ti:sparse autoencoder AND cat:cs.LG\",\n  \"result_count\": 15,\n  \"results\": [\n    {\n      \"arxiv_id\": \"2309.10668\",\n      \"title\": \"Towards Monosemanticity: Decomposing Language Models With Dictionary Learning\",\n      \"authors\": [\"Trenton Bricken\", \"Adly Templeton\", \"...\"],\n      \"abstract\": \"Full abstract text...\",\n      \"categories\": [\"cs.LG\", \"cs.AI\"],\n      \"primary_category\": \"cs.LG\",\n      \"published\": \"2023-09-19T17:58:00Z\",\n      \"updated\": \"2023-10-04T14:22:00Z\",\n      \"doi\": \"10.48550\u002FarXiv.2309.10668\",\n      \"pdf_url\": \"http:\u002F\u002Farxiv.org\u002Fpdf\u002F2309.10668v1\",\n      \"abs_url\": \"http:\u002F\u002Farxiv.org\u002Fabs\u002F2309.10668v1\",\n      \"comment\": \"42 pages, 30 figures\",\n      \"journal_ref\": \"\"\n    }\n  ]\n}\n```\n\n## Common Usage Patterns\n\n### Literature Review Workflow\n\n```python\nfrom scripts.arxiv_search import ArxivSearcher\nimport json\n\nsearcher = ArxivSearcher()\n\n# 1. Broad search\nresults = searcher.search(\n    query=\"abs:mechanistic interpretability AND cat:cs.LG\",\n    max_results=200,\n    sort_by=\"submittedDate\"\n)\n\n# 2. Save results\nwith open(\"interp_papers.json\", \"w\") as f:\n    json.dump({\"result_count\": len(results), \"results\": results}, f, indent=2)\n\n# 3. Filter and analyze\nimport pandas as pd\ndf = pd.DataFrame(results)\nprint(f\"Total papers: {len(df)}\")\nprint(f\"Date range: {df['published'].min()} to {df['published'].max()}\")\nprint(f\"\\nTop categories:\")\nprint(df[\"primary_category\"].value_counts().head(10))\n```\n\n### Track a Research Group\n\n```python\nsearcher = ArxivSearcher()\n\ngroups = {\n    \"anthropic\": \"au:anthropic AND (cat:cs.LG OR cat:cs.CL)\",\n    \"openai\": \"au:openai AND cat:cs.CL\",\n    \"deepmind\": \"au:deepmind AND cat:cs.LG\",\n}\n\nfor name, query in groups.items():\n    results = searcher.search(query=query, max_results=50, sort_by=\"submittedDate\")\n    print(f\"{name}: {len(results)} recent papers\")\n```\n\n### Monitor New Submissions\n\n```python\nsearcher = ArxivSearcher()\n\n# Most recent ML papers\nresults = searcher.search(\n    query=\"cat:cs.LG\",\n    max_results=50,\n    sort_by=\"submittedDate\",\n    sort_order=\"descending\"\n)\n\nfor paper in results[:10]:\n    print(f\"[{paper['published'][:10]}] {paper['title']}\")\n    print(f\"  {paper['abs_url']}\\n\")\n```\n\n## Python API\n\n```python\nfrom scripts.arxiv_search import ArxivSearcher\n\nsearcher = ArxivSearcher(verbose=True)\n\n# Free-form query (uses arXiv query syntax)\nresults = searcher.search(query=\"...\", max_results=50)\n\n# Lookup by ID\npapers = searcher.get_by_ids([\"2309.10668\", \"2406.04093\"])\n\n# Download PDF\nsearcher.download_pdf(\"2309.10668\", \"paper.pdf\")\n\n# Build query from components\nquery = ArxivSearcher.build_query(\n    title=\"sparse autoencoder\",\n    author=\"anthropic\",\n    category=\"cs.LG\"\n)\nresults = searcher.search(query=query, max_results=20)\n```\n\n## Best Practices\n\n1. **Respect rate limits**: The API requests 3-second delays between calls. The script handles this automatically.\n2. **Use category filters**: Dramatically reduces noise. `cs.LG` is where most ML papers live.\n3. **Cache results**: Save to JSON to avoid re-fetching.\n4. **Use `sort_by=submittedDate`** for recent papers, `relevance` for keyword searches.\n5. **Max 300 results per query**: arXiv API caps at this. For larger sets, paginate with `start` parameter.\n6. **arXiv IDs**: Use bare IDs (`2309.10668`), not full URLs, in programmatic code.\n7. **Combine with openalex-database**: For citation counts and impact metrics arXiv doesn't provide.\n\n## Limitations\n\n- **No full-text search**: Only searches metadata (title, abstract, authors, comments)\n- **No citation data**: Use openalex-database or Semantic Scholar for citations\n- **Max 300 results**: Per query. Use pagination for larger sets.\n- **Rate limited**: ~1 request per 3 seconds recommended\n- **Atom XML responses**: The script parses these into JSON automatically\n- **Search lag**: New papers may take hours to appear in API results\n\n## Reference Documentation\n\n- **API Reference**: See [references\u002Fapi_reference.md](references\u002Fapi_reference.md) for full endpoint specs, all categories, and response schemas\n",{"name":5,"license":14,"metadata":23,"description":7},{"version":24,"skill-author":25},"1.0.0","AlterLab","master","f483e54f3ad5f202a77d45f2e57f8d970b71195f","skills_library\u002Falterlab-arxiv",2,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills","https:\u002F\u002Fgithub.com\u002Froohe","yoou.link","2026-05-19 15:56:07",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add roohe\u002Fagentic-super-skills --skill alterlab-arxiv",{"tool":40,"command":41},"bunx","bunx skills add roohe\u002Fagentic-super-skills --skill alterlab-arxiv",{"tool":43,"command":44},"pnpm","pnpm dlx skills add roohe\u002Fagentic-super-skills --skill alterlab-arxiv","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Falterlab-arxiv\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fapi_reference.md","REFERENCE","参考文档",12860,"https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Falterlab-arxiv\u002Freferences\u002Fapi_reference.md",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M73D865CZME2FCMKA4PQM348","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":18},"01M73D7Z64J4ABWZJD7P44XBBF","youtube-downloader","Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars; research content curation","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyoutube-downloader\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M73D7K8778TGZV3GJFR3703D","yc-pitch-deck","Create a compelling startup pitch deck that follows the structure proven to raise billions from top investors. Master the YC and Sequoia formats that get founders funded. Use when: **Fundraising** to create investor pitch decks; **YC application** to structure your narrative; **Demo Day prep** to craft your 2-minute pitch; **Angel investors** to communicate your opportunity; **Partnership pitches** to structure compelling asks","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fyc-pitch-deck\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M73D70KJSE0E8Z28YMNNRT04","x-twitter-scraper","Use when the user needs X (Twitter) data or confirmation-gated X actions through Xquik: tweet search, user lookup, follower extraction, media download, monitoring, webhooks, MCP, SDKs, posting, likes, DMs, and profile updates. Requires a Xquik API key. Never ask for X login material.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fx-twitter-scraper\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":18},"01M73D6ED01GV077R7K4NZNFZJ","write-vignette","Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-vignette\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":18},"01M73D69YJR0BK3NFHE0CYG3EF","write-validation-documentation","Write IQ\u002FOQ\u002FPQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and approval workflows. Use when validating R or other software for regulated use, preparing for a regulatory audit, documenting qualification of computing environments, or creating and updating validation protocols and reports for new or re-qualified systems.","https:\u002F\u002Fgithub.com\u002Froohe\u002Fagentic-super-skills\u002Fblob\u002Fmaster\u002Fskills_library\u002Fwrite-validation-documentation\u002FSKILL.md",[],[]]