[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EVTXEDEMZHY718T52PDPJN":3,"skill-same:01M7EVTXEDEMZHY718T52PDPJN":46},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7EVTXEDEMZHY718T52PDPJN","search-arxiv",null,"Search arXiv by paper ID or keyword and return title, abstract, authors, and BibTeX. Use when asked to look up an arXiv paper, fetch metadata for a citation, check what a paper is about, generate BibTeX for an arXiv ID, or find papers on a topic.","tdupu\u002Fagent-skills-public","tdupu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3440403?v=4","01M7EV32X9J0EFE5T4P8TKQTCQ","Taylor Dupuy","01M7EV32XZ1Z4MDBYAFRCJD3BP",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-arxiv\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: search-arxiv\ndescription: >\n  Search arXiv by paper ID or keyword and return title, abstract, authors, and BibTeX.\n  Use when asked to look up an arXiv paper, fetch metadata for a citation, check what\n  a paper is about, generate BibTeX for an arXiv ID, or find papers on a topic.\n---\n\n# search-arxiv\n\nUse the Atom API for metadata; optional\n[`arxiv-mcp-server`](https:\u002F\u002Fgithub.com\u002Fblazickjp\u002Farxiv-mcp-server) adds full-paper\naccess (see §MCP enhancement).\n\n---\n\n## Step 1 — Identify the query type\n\n- **arXiv ID** (e.g. `2407.19122`, `math\u002F0603460`, `2407.19122v2`): go to Step 2a.\n- **Keyword \u002F author \u002F title**: go to Step 2b.\n\n---\n\n## Step 2a — Fetch by arXiv ID\n\nWebFetch the Atom endpoint:\n\n```\nhttps:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?id_list=\u003CID>\n```\n\nExample: `https:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?id_list=2407.19122`\n\nPrompt: *\"Extract from this Atom XML: paper title, full abstract\u002Fsummary, all\nauthor names (in order), the complete arXiv ID (strip only the URL prefix from\n`\u003Cid>`), the year from `\u003Cpublished>`, and the `term` attribute of\n`\u003Carxiv:primary_category>`.\"*\n\nRetain legacy prefixes such as `math\u002F` and requested versions such as `v2`\nin requests, metadata, eprint and URL.\n\nFor either lookup path, validate HTTP success and Atom structure. Report fetch,\nparse or `Error` entries (including their summary) as failures. Only a valid,\nsuccessful empty feed establishes no result for the query.\n\n---\n\n## Step 2b — Keyword search\n\nWebFetch:\n\n```\nhttps:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?search_query=\u003CENCODED-QUERY>&max_results=10&sortBy=relevance\n```\n\nURL-encode the entire `all:\u003CQUERY>` parameter value, not just spaces:\n`all:C++` becomes `all%3AC%2B%2B`. Check the feed's echoed query.\n\nPrompt: *\"List the arXiv papers in this Atom XML: for each `\u003Centry>` extract\ntitle, authors (all names), arXiv ID, and primary category. Return as a\nnumbered list.\"*\n\nPresent the numbered list to the user. Ask which paper(s) to retrieve in full\n(or proceed with all if ≤ 3 results). Then run Step 2a for each chosen ID.\n\n---\n\n## Step 3 — Assemble BibTeX\n\nFrom the extracted metadata, generate one `@misc` entry per paper:\n\n```bibtex\n@misc{\u003Ccite-key>,\n  title        = {\u003Ctitle>},\n  author       = {\u003CLast, First and Last, First and ...>},\n  year         = {\u003CYYYY>},\n  eprint       = {\u003CID>},\n  archivePrefix = {arXiv},\n  primaryClass  = {\u003Cprimary-category>},\n  url          = {https:\u002F\u002Farxiv.org\u002Fabs\u002F\u003CID>}\n}\n```\n\n**Cite-key convention:** `\u003Cfirst-author-last-name>\u003Cyear>\u003Cfirst-content-word-of-title>`,\nall lowercase, no spaces. Example: `dupuy2024basic`.\n\n**Author format:** invert each name to `Last, First` (or `Last, First Middle`);\nseparate multiple authors with ` and `.\n\n---\n\n## Step 4 — Return\n\nOutput all four fields for each paper:\n\n1. **Title**\n2. **Abstract** (full text)\n3. **Authors** (comma-separated, natural order)\n4. **BibTeX** (fenced code block)\n\n---\n\n## MCP enhancement (optional)\n\nFor full-paper download and reading, install `blazickjp\u002Farxiv-mcp-server`:\n\n```bash\nuv tool install arxiv-mcp-server\n```\n\nRegister in the project root's `.mcp.json` via:\n\n```bash\nclaude mcp add --scope project --transport stdio arxiv-mcp-server -- arxiv-mcp-server\n```\n\nRestart; check `claude mcp list` for connection status and discover session tools.\n\nWhen connected, the tools `mcp__arxiv-mcp-server__search_papers`,\n`mcp__arxiv-mcp-server__download_paper`, and `mcp__arxiv-mcp-server__read_paper`\nsupport download\u002Fread and local caching. Citation graphs use `citation_graph`;\n`semantic_search` additionally requires the optional `arxiv-mcp-server[pro]`\ninstall. The Atom path remains available.\n\n---\n\n## Simple test\n\n```\nQuery: arXiv ID 2407.19122\nExpected title: \"The Basic Theory of Clifford-Bianchi Groups for Hyperbolic n-Space\"\nExpected authors: non-empty list matching the arXiv API response\nExpected BibTeX: @misc with eprint containing 2407.19122; retain requested version\n```\n","# search-arxiv\n\nUse the Atom API for metadata; optional\n[`arxiv-mcp-server`](https:\u002F\u002Fgithub.com\u002Fblazickjp\u002Farxiv-mcp-server) adds full-paper\naccess (see §MCP enhancement).\n\n---\n\n## Step 1 — Identify the query type\n\n- **arXiv ID** (e.g. `2407.19122`, `math\u002F0603460`, `2407.19122v2`): go to Step 2a.\n- **Keyword \u002F author \u002F title**: go to Step 2b.\n\n---\n\n## Step 2a — Fetch by arXiv ID\n\nWebFetch the Atom endpoint:\n\n```\nhttps:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?id_list=\u003CID>\n```\n\nExample: `https:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?id_list=2407.19122`\n\nPrompt: *\"Extract from this Atom XML: paper title, full abstract\u002Fsummary, all\nauthor names (in order), the complete arXiv ID (strip only the URL prefix from\n`\u003Cid>`), the year from `\u003Cpublished>`, and the `term` attribute of\n`\u003Carxiv:primary_category>`.\"*\n\nRetain legacy prefixes such as `math\u002F` and requested versions such as `v2`\nin requests, metadata, eprint and URL.\n\nFor either lookup path, validate HTTP success and Atom structure. Report fetch,\nparse or `Error` entries (including their summary) as failures. Only a valid,\nsuccessful empty feed establishes no result for the query.\n\n---\n\n## Step 2b — Keyword search\n\nWebFetch:\n\n```\nhttps:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?search_query=\u003CENCODED-QUERY>&max_results=10&sortBy=relevance\n```\n\nURL-encode the entire `all:\u003CQUERY>` parameter value, not just spaces:\n`all:C++` becomes `all%3AC%2B%2B`. Check the feed's echoed query.\n\nPrompt: *\"List the arXiv papers in this Atom XML: for each `\u003Centry>` extract\ntitle, authors (all names), arXiv ID, and primary category. Return as a\nnumbered list.\"*\n\nPresent the numbered list to the user. Ask which paper(s) to retrieve in full\n(or proceed with all if ≤ 3 results). Then run Step 2a for each chosen ID.\n\n---\n\n## Step 3 — Assemble BibTeX\n\nFrom the extracted metadata, generate one `@misc` entry per paper:\n\n```bibtex\n@misc{\u003Ccite-key>,\n  title        = {\u003Ctitle>},\n  author       = {\u003CLast, First and Last, First and ...>},\n  year         = {\u003CYYYY>},\n  eprint       = {\u003CID>},\n  archivePrefix = {arXiv},\n  primaryClass  = {\u003Cprimary-category>},\n  url          = {https:\u002F\u002Farxiv.org\u002Fabs\u002F\u003CID>}\n}\n```\n\n**Cite-key convention:** `\u003Cfirst-author-last-name>\u003Cyear>\u003Cfirst-content-word-of-title>`,\nall lowercase, no spaces. Example: `dupuy2024basic`.\n\n**Author format:** invert each name to `Last, First` (or `Last, First Middle`);\nseparate multiple authors with ` and `.\n\n---\n\n## Step 4 — Return\n\nOutput all four fields for each paper:\n\n1. **Title**\n2. **Abstract** (full text)\n3. **Authors** (comma-separated, natural order)\n4. **BibTeX** (fenced code block)\n\n---\n\n## MCP enhancement (optional)\n\nFor full-paper download and reading, install `blazickjp\u002Farxiv-mcp-server`:\n\n```bash\nuv tool install arxiv-mcp-server\n```\n\nRegister in the project root's `.mcp.json` via:\n\n```bash\nclaude mcp add --scope project --transport stdio arxiv-mcp-server -- arxiv-mcp-server\n```\n\nRestart; check `claude mcp list` for connection status and discover session tools.\n\nWhen connected, the tools `mcp__arxiv-mcp-server__search_papers`,\n`mcp__arxiv-mcp-server__download_paper`, and `mcp__arxiv-mcp-server__read_paper`\nsupport download\u002Fread and local caching. Citation graphs use `citation_graph`;\n`semantic_search` additionally requires the optional `arxiv-mcp-server[pro]`\ninstall. The Atom path remains available.\n\n---\n\n## Simple test\n\n```\nQuery: arXiv ID 2407.19122\nExpected title: \"The Basic Theory of Clifford-Bianchi Groups for Hyperbolic n-Space\"\nExpected authors: non-empty list matching the arXiv API response\nExpected BibTeX: @misc with eprint containing 2407.19122; retain requested version\n```\n",{"name":5,"description":7},"main","8d13efb5e66306aeae6e3b948bc463e7e2db1b65","skills\u002Fsearch-arxiv","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public","https:\u002F\u002Fgithub.com\u002Ftdupu","https:\u002F\u002Ftdupu.github.io\u002Findex.html","Associate Professor, Department of Mathematics and Statistics, University of Vermont --- last updated Fall 2019","2026-11-13 09:07:19",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add tdupu\u002Fagent-skills-public --skill search-arxiv",{"tool":38,"command":39},"bunx","bunx skills add tdupu\u002Fagent-skills-public --skill search-arxiv",{"tool":41,"command":42},"pnpm","pnpm dlx skills add tdupu\u002Fagent-skills-public --skill search-arxiv","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-arxiv\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7EW4PT586KKE7VRCAD80Z9K","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7EW4HV5V74AF3PTV8N4T0PS","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7EW4DNKGP5CR1RAJP2J9PHA","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fverification-before-completion\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7EW4BA2QP88VBFVXDVJM7XQ","using-superpowers","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fusing-superpowers\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7EW47F2JG5FBESDJNP3PKMV","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Fusing-git-worktrees\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7EW44N8556Y556NX9HJT4KP","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002Ftdupu\u002Fagent-skills-public\u002Fblob\u002Fmain\u002Fsuperpowers\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[]]