[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74MHQESBCFK1PF3VFEPVGMX":3,"skill-same:01M74MHQESBCFK1PF3VFEPVGMX":47},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M74MHQESBCFK1PF3VFEPVGMX","deepxiv-baseline-table",null,"Build a markdown baseline table for a research topic using deepxiv search, brief, head, and experiment-section reads, extracting paper title, URL, open-source status, datasets, benchmark scores, and other comparison-ready details.","pengqianhan\u002FAI-Human-Research-OS","pengqianhan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4286531?v=4","01M74M3DT9HNZ6HPAK8TX69EX9","PengqianHan","01M74M3DTVSN2GXW0JH2W396FK",3,"MIT","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fcollected-skills\u002Fdeepxiv-baseline-table\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: deepxiv-baseline-table\ndescription: Build a markdown baseline table for a research topic using deepxiv search, brief, head, and experiment-section reads, extracting paper title, URL, open-source status, datasets, benchmark scores, and other comparison-ready details.\n---\n\n# DeepXiv Baseline Table\n\nUse this skill when the user wants to map a topic into a comparison table, baseline survey, benchmark roundup, or \"what papers evaluated on which datasets with what scores and whether code is open\".\n\nTypical requests:\n- \"Find recent baseline papers on agentic memory\"\n- \"What papers in the last month evaluated on dataset X?\"\n- \"Make me a markdown table of methods, datasets, and scores\"\n\n## Goal\n\nTurn a topic search into a structured markdown table:\n\n1. Search recent papers with `deepxiv search`\n2. Brief all candidates with `deepxiv paper \u003Cid> --brief`\n3. Keep the relevant papers, prioritizing papers with GitHub\u002Fcode\n4. Inspect promising papers with `deepxiv paper \u003Cid> --head`\n5. Read experiment-related sections with `deepxiv paper \u003Cid> --section ...`\n6. Extract datasets, evaluation setup, and reported scores\n7. Write a markdown table summarizing the baselines\n\n## Default Workflow\n\n### 1. Search by topic and date range\n\nUse a broad search first.\n\n```bash\ndeepxiv search \"agentic memory\" --date-from 2026-03-01 --limit 100 --format json\n```\n\nDefault heuristics:\n- Use the user’s exact topic phrase first\n- Keep `--limit` high enough to avoid missing relevant papers\n- If results are noisy, refine the query with close variants\n\nExamples:\n\n```bash\ndeepxiv search \"agentic memory\" --date-from 2026-03-01 --limit 100 --format json\ndeepxiv search \"memory agents long-horizon\" --date-from 2026-03-01 --limit 100 --format json\ndeepxiv search \"agent memory benchmark\" --date-from 2026-03-01 --limit 100 --format json\n```\n\n### 2. Brief all candidates\n\nFor each arXiv ID, fetch:\n\n```bash\ndeepxiv paper \u003Carxiv_id> --brief\n```\n\nCapture:\n- title\n- arXiv ID\n- publish date\n- TLDR\n- keywords\n- GitHub URL\n- PDF\u002Fsource URL\n\nThis is the screening step. Do not read full sections yet.\n\n### 3. Filter and prioritize\n\nKeep papers that are actually about the topic, not just adjacent terms.\n\nPrioritize:\n- papers directly centered on the topic\n- empirical papers over purely conceptual ones\n- papers with GitHub\u002Fcode\n- benchmark or comparison papers\n- papers with clear experiment sections\n\nDe-prioritize:\n- purely opinion or survey papers unless the user asked for surveys\n- papers with no clear evaluation evidence\n- papers only loosely related to the topic\n\nIf the list is still large, keep a primary set and a secondary set:\n- Primary: strongest and most relevant baselines\n- Secondary: adjacent or weaker evidence\n\n### 4. Inspect paper structure\n\nFor retained papers:\n\n```bash\ndeepxiv paper \u003Carxiv_id> --head\n```\n\nUse `--head` to find experiment-bearing sections such as:\n- Experiments\n- Evaluation\n- Results\n- Benchmark\n- Main Results\n- Analysis\n\nAlso capture:\n- abstract\n- total token count\n- section names\n\n### 5. Read only experiment-relevant sections\n\nOnce the right sections are known, read only those:\n\n```bash\ndeepxiv paper \u003Carxiv_id> --section Experiments\ndeepxiv paper \u003Carxiv_id> --section Evaluation\ndeepxiv paper \u003Carxiv_id> --section Results\n```\n\nSection selection guidance:\n- Start with `Experiments` or `Evaluation`\n- Read `Results` if the metrics are not clear\n- Read `Introduction` only if the task setup is still ambiguous\n- Read `Appendix` only if benchmark details are missing from the main paper\n\nAvoid reading the entire paper unless the user explicitly asks for it.\n\n## Extraction Targets\n\nFor each retained paper, try to extract:\n\n- Title\n- arXiv ID\n- Paper URL\n- GitHub\u002Fcode URL\n- Open-source status: `Yes`, `No`, or `Unknown`\n- Main task\n- Evaluation datasets \u002F benchmarks\n- Key metrics\n- Best reported scores\n- Notes on experimental setting\n\nIf exact scores are not clearly available from the inspected sections:\n- leave the score field as `Not clearly stated`\n- do not invent or infer a number\n\nIf datasets are only partially visible:\n- include the datasets you can verify\n- mention that the list may be incomplete\n\n## Markdown Output\n\nWrite a markdown file in the workspace unless the user specifies another path.\n\nRecommended filename:\n\n```text\n\u003Ctopic>-baseline-table-YYYY-MM-DD.md\n```\n\nExample:\n\n```text\nagentic-memory-baseline-table-2026-04-01.md\n```\n\nRecommended output structure:\n\n```md\n# Agentic Memory Baseline Table\n\nTopic: agentic memory\nDate range: 2026-03-01 to 2026-04-01\nSearch source: deepxiv\n\n## Summary\n\n- Number of search results\n- Number of relevant papers retained\n- Number with public code\n- Main recurring datasets or benchmark families\n\n## Baseline Table\n\n| Title | arXiv | URL | Open Source | Code URL | Datasets \u002F Benchmarks | Metrics \u002F Scores | Notes |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n| ... | ... | ... | ... | ... | ... | ... | ... |\n\n## Inclusion Notes\n\n- Which papers were excluded and why\n- Which rows are based only on `--brief`\n- Which rows were verified through `--head` and experiment\u002Fresult sections\n\n## Observations\n\n- Common evaluation datasets\n- Which papers appear strongest\n- Where the benchmark story is still fragmented\n```\n\n## Writing Rules\n\n- Prefer verified facts over broad summaries\n- Separate \"paper is relevant\" from \"paper has strong benchmark evidence\"\n- Be explicit when a row is missing score details\n- Mark open-source status conservatively\n- Keep the table compact but useful\n- Add short notes when comparisons are not apples-to-apples\n\n## Decision Rules\n\n- Always start with search and brief\n- Prefer papers with GitHub when deciding which ones to inspect first\n- Use `--head` before `--section`\n- Read only the sections needed to recover datasets and scores\n- If the topic is broad, tell the user when the table mixes multiple subtask types\n\n## Minimal Example\n\n```bash\ndeepxiv search \"agentic memory\" --date-from 2026-03-01 --limit 100 --format json\ndeepxiv paper 2603.21489 --brief\ndeepxiv paper 2603.21489 --head\ndeepxiv paper 2603.21489 --section Experiments\n```\n\nThen write a markdown table with:\n- title\n- paper URL\n- open-source status\n- code URL\n- datasets \u002F benchmarks\n- metrics \u002F scores\n- short notes on what was actually verified\n","# DeepXiv Baseline Table\n\nUse this skill when the user wants to map a topic into a comparison table, baseline survey, benchmark roundup, or \"what papers evaluated on which datasets with what scores and whether code is open\".\n\nTypical requests:\n- \"Find recent baseline papers on agentic memory\"\n- \"What papers in the last month evaluated on dataset X?\"\n- \"Make me a markdown table of methods, datasets, and scores\"\n\n## Goal\n\nTurn a topic search into a structured markdown table:\n\n1. Search recent papers with `deepxiv search`\n2. Brief all candidates with `deepxiv paper \u003Cid> --brief`\n3. Keep the relevant papers, prioritizing papers with GitHub\u002Fcode\n4. Inspect promising papers with `deepxiv paper \u003Cid> --head`\n5. Read experiment-related sections with `deepxiv paper \u003Cid> --section ...`\n6. Extract datasets, evaluation setup, and reported scores\n7. Write a markdown table summarizing the baselines\n\n## Default Workflow\n\n### 1. Search by topic and date range\n\nUse a broad search first.\n\n```bash\ndeepxiv search \"agentic memory\" --date-from 2026-03-01 --limit 100 --format json\n```\n\nDefault heuristics:\n- Use the user’s exact topic phrase first\n- Keep `--limit` high enough to avoid missing relevant papers\n- If results are noisy, refine the query with close variants\n\nExamples:\n\n```bash\ndeepxiv search \"agentic memory\" --date-from 2026-03-01 --limit 100 --format json\ndeepxiv search \"memory agents long-horizon\" --date-from 2026-03-01 --limit 100 --format json\ndeepxiv search \"agent memory benchmark\" --date-from 2026-03-01 --limit 100 --format json\n```\n\n### 2. Brief all candidates\n\nFor each arXiv ID, fetch:\n\n```bash\ndeepxiv paper \u003Carxiv_id> --brief\n```\n\nCapture:\n- title\n- arXiv ID\n- publish date\n- TLDR\n- keywords\n- GitHub URL\n- PDF\u002Fsource URL\n\nThis is the screening step. Do not read full sections yet.\n\n### 3. Filter and prioritize\n\nKeep papers that are actually about the topic, not just adjacent terms.\n\nPrioritize:\n- papers directly centered on the topic\n- empirical papers over purely conceptual ones\n- papers with GitHub\u002Fcode\n- benchmark or comparison papers\n- papers with clear experiment sections\n\nDe-prioritize:\n- purely opinion or survey papers unless the user asked for surveys\n- papers with no clear evaluation evidence\n- papers only loosely related to the topic\n\nIf the list is still large, keep a primary set and a secondary set:\n- Primary: strongest and most relevant baselines\n- Secondary: adjacent or weaker evidence\n\n### 4. Inspect paper structure\n\nFor retained papers:\n\n```bash\ndeepxiv paper \u003Carxiv_id> --head\n```\n\nUse `--head` to find experiment-bearing sections such as:\n- Experiments\n- Evaluation\n- Results\n- Benchmark\n- Main Results\n- Analysis\n\nAlso capture:\n- abstract\n- total token count\n- section names\n\n### 5. Read only experiment-relevant sections\n\nOnce the right sections are known, read only those:\n\n```bash\ndeepxiv paper \u003Carxiv_id> --section Experiments\ndeepxiv paper \u003Carxiv_id> --section Evaluation\ndeepxiv paper \u003Carxiv_id> --section Results\n```\n\nSection selection guidance:\n- Start with `Experiments` or `Evaluation`\n- Read `Results` if the metrics are not clear\n- Read `Introduction` only if the task setup is still ambiguous\n- Read `Appendix` only if benchmark details are missing from the main paper\n\nAvoid reading the entire paper unless the user explicitly asks for it.\n\n## Extraction Targets\n\nFor each retained paper, try to extract:\n\n- Title\n- arXiv ID\n- Paper URL\n- GitHub\u002Fcode URL\n- Open-source status: `Yes`, `No`, or `Unknown`\n- Main task\n- Evaluation datasets \u002F benchmarks\n- Key metrics\n- Best reported scores\n- Notes on experimental setting\n\nIf exact scores are not clearly available from the inspected sections:\n- leave the score field as `Not clearly stated`\n- do not invent or infer a number\n\nIf datasets are only partially visible:\n- include the datasets you can verify\n- mention that the list may be incomplete\n\n## Markdown Output\n\nWrite a markdown file in the workspace unless the user specifies another path.\n\nRecommended filename:\n\n```text\n\u003Ctopic>-baseline-table-YYYY-MM-DD.md\n```\n\nExample:\n\n```text\nagentic-memory-baseline-table-2026-04-01.md\n```\n\nRecommended output structure:\n\n```md\n# Agentic Memory Baseline Table\n\nTopic: agentic memory\nDate range: 2026-03-01 to 2026-04-01\nSearch source: deepxiv\n\n## Summary\n\n- Number of search results\n- Number of relevant papers retained\n- Number with public code\n- Main recurring datasets or benchmark families\n\n## Baseline Table\n\n| Title | arXiv | URL | Open Source | Code URL | Datasets \u002F Benchmarks | Metrics \u002F Scores | Notes |\n| --- | --- | --- | --- | --- | --- | --- | --- |\n| ... | ... | ... | ... | ... | ... | ... | ... |\n\n## Inclusion Notes\n\n- Which papers were excluded and why\n- Which rows are based only on `--brief`\n- Which rows were verified through `--head` and experiment\u002Fresult sections\n\n## Observations\n\n- Common evaluation datasets\n- Which papers appear strongest\n- Where the benchmark story is still fragmented\n```\n\n## Writing Rules\n\n- Prefer verified facts over broad summaries\n- Separate \"paper is relevant\" from \"paper has strong benchmark evidence\"\n- Be explicit when a row is missing score details\n- Mark open-source status conservatively\n- Keep the table compact but useful\n- Add short notes when comparisons are not apples-to-apples\n\n## Decision Rules\n\n- Always start with search and brief\n- Prefer papers with GitHub when deciding which ones to inspect first\n- Use `--head` before `--section`\n- Read only the sections needed to recover datasets and scores\n- If the topic is broad, tell the user when the table mixes multiple subtask types\n\n## Minimal Example\n\n```bash\ndeepxiv search \"agentic memory\" --date-from 2026-03-01 --limit 100 --format json\ndeepxiv paper 2603.21489 --brief\ndeepxiv paper 2603.21489 --head\ndeepxiv paper 2603.21489 --section Experiments\n```\n\nThen write a markdown table with:\n- title\n- paper URL\n- open-source status\n- code URL\n- datasets \u002F benchmarks\n- metrics \u002F scores\n- short notes on what was actually verified\n",{"name":5,"description":7},"main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fcollected-skills\u002Fdeepxiv-baseline-table",0,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS","https:\u002F\u002Fpengqianhan.github.io\u002FAI-Human-Research-OS\u002F","https:\u002F\u002Fgithub.com\u002Fpengqianhan","Ph.D. candidate of The University of Auckland, New Zealand","2026-11-14 18:08:16",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add pengqianhan\u002FAI-Human-Research-OS --skill deepxiv-baseline-table",{"tool":39,"command":40},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill deepxiv-baseline-table",{"tool":42,"command":43},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill deepxiv-baseline-table","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fcollected-skills\u002Fdeepxiv-baseline-table\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M74MWYTHT498SVMN823896T7","workflow-skill-creator","Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say \"make this a skill\", \"create a skill from what we just did\", \"package this workflow\" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fworkflow_skill_creator\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M74MWWVCFZ8HQS8840F1V1FT","uv","Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fuv\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M74MWRH5BTSWZ2C5PCTD5FV9","uniprot-database","Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funiprot_database\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M74MWN1D3ER9F1FZPWH8HQC1","unibind-database","Queries the UniBind database for experimentally validated transcription factor (TF) binding sites. Use when retrieving direct TF-DNA interaction datasets, downloading binding site coordinates (BED\u002FFASTA) for local analysis, or listing available datasets by species, cell line, or TF name. Don't use to query specific intervals, locations, genes, motif models or expression data.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Funibind_database\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M74MWHHB5QZY3NR2FYA1EK4N","ucsc-conservation-and-tfbs","Fetch Evolutionary Conservation scores (phyloP, phastCons) and Transcription Factor Binding Sites (TFBS) from the UCSC Genome Browser. Use when analyzing whether genomic variants or regions are evolutionarily conserved, functionally important, or bounded by TF regulators across major projects (ENCODE, JASPAR, ReMap).","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fucsc_conservation_and_tfbs\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M74MWERYHSY87P21FDMVE6BA","string-database","Query the STRING database for protein-protein interactions (PPIs), functional enrichment, and homology. Use when the user asks about interactions between specific proteins, interaction evidence, confidence scores, protein interaction partners, or pathway enrichments.","https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fstring_database\u002FSKILL.md",[],[]]