[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74MVW8FZTHTE6GG3D34P53G":3,"skill-same:01M74MVW8FZTHTE6GG3D34P53G":91},{"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},"01M74MVW8FZTHTE6GG3D34P53G","pubmed-database",null,"Search PubMed for scientific literature, including published clinical trials. Fetch abstracts and full text. Link published research to biological databases (gene, protein, nucleotide, PubChem) to discover associations between papers and specific compounds or genes. Verify medical spelling, match raw citations, and cache result sets for bulk processing. Interfaces NCBI E-utilities and PMC BioC APIs.","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\u002Fscience-skills\u002Fpubmed_database\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: pubmed-database\ndescription: >-\n  Search PubMed for scientific literature, including published clinical trials.\n  Fetch abstracts and full text. Link published research to biological databases\n  (gene, protein, nucleotide, PubChem) to discover associations between papers\n  and specific compounds or genes. Verify medical spelling, match raw citations,\n  and cache result sets for bulk processing. Interfaces NCBI E-utilities and PMC\n  BioC APIs.\n---\n\n# PubMed API\n\n## Prerequisites\n\n1.  **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure\n    `uv` is installed and on PATH.\n2.  **User Notification**: If .licenses\u002Fpubmed_database_LICENSE.txt does not\n    already exist in the workspace root directory then (1) prominently notify\n    the user to check the terms at https:\u002F\u002Fpubmed.ncbi.nlm.nih.gov\u002Fdisclaimer\u002F\n    and https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fhome\u002Fabout\u002Fpolicies\u002F and to always check\n    the license of the papers retrieved by the skill for any restrictions, then\n    (2) create the file recording the notification text and timestamp.\n3.  **`.env` file**: Make sure the `.env` file exists in your home directory.\n    Create one if it does not exist.\n4.  **`NCBI_API_KEY`** (optional): Raises the NCBI E-utilities rate limit from 3\n    to 10 requests\u002Fsecond. The skill works without it, but a key is recommended\n    if the user plans many queries or encounters a 429 error. You can register\n    for a key for free at https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Faccount\u002Fsettings\u002F. You\n    **MUST** use the safe credentials protocol in the `credentials` skill to\n    check for and request this key if this skill looks relevant to the user's\n    request.\n5.  **`USER_EMAIL`** (optional): Identifies the caller to NCBI (recommended by\n    their Terms of Use). You **MUST** use the safe credentials protocol in the\n    `credentials` skill to check for and request this credential if this skill\n    looks relevant to the user's request.\n\nThis skill provides CLI access to the NCBI PubMed and PubMed Central APIs via\n`scripts\u002Fpubmed_api.py` — a single CLI with 10 functions covering search, fetch,\nlinking, full text, spelling, discovery, citation matching, and caching.\n\n## Core Rules\n\n-   **API Use**: Always use the provided wrapper `scripts\u002Fpubmed_api.py` which\n    manages rate limits automatically and prevents API abuse. Setting the\n    `NCBI_API_KEY` environment variable raises the rate limit from 3 to 10\n    requests\u002Fsecond. Querying the API any other way (e.g. via curl, wget, or\n    hand-written code) is strictly forbidden.\n-   **JSON Processing**: Use `jq` to filter and transform JSON output (or python\n    equivalents if `jq` is not available) to prevent hallucinations and context\n    overflow.\n-   **Temporary Files**: To avoid polluting the working directory with JSON\n    files, use a temporary directory inside the current directory. When running\n    multiple agents or tasks in parallel, ensure each uses a unique subdirectory\n    name (e.g., `tmp_$TASK_ID\u002F`) to avoid file collisions.\n-   **Notification**: If this skill is used, ensure this is mentioned in the\n    output AND list the URLs of all papers that were used in producing the\n    output.\n\n## Structure of the skill folder\n\n-   `SKILL.md` - This file\n-   `scripts\u002Fpubmed_api.py` - The skill CLI\n-   `references\u002F` - Directory with detailed function specifications\n    -   `advanced-linking.md`\n    -   `advanced-search.md`\n    -   `bulk-workflows.md`\n    -   `citation-matching.md`\n    -   `cross-database-linking.md`\n    -   `fetch-and-resolve.md`\n    -   `search-and-discovery.md`\n    -   `utilities.md`\n\n## CLI Usage\n\n```bash\nuv run scripts\u002Fpubmed_api.py \u003Coutput_file> \u003Cfunction_name> \u003Crequired_args> [--flag value ...]\n```\n\n-   **Positional Arguments**: Arguments are positional; list arguments are\n    passed as comma-separated strings without spaces (e.g.\n    `\"35113657,31234568\"`).\n-   **Flag Options**: Optional arguments can be passed as `--flag value` instead\n    of positional args.\n-   **Output Handling**: On success, JSON is written to `output_file`. On error,\n    the process exits with a non-zero code and no output file is written.\n\n### Example Usage\n\n```bash\nuv run scripts\u002Fpubmed_api.py .\u002Fsearch_results.json search_pubmed \"BRCA1\" --max_results 5\ncat .\u002Fsearch_results.json | jq '.[]' -r\nuv run scripts\u002Fpubmed_api.py .\u002Fabstracts.json fetch_article_abstracts \"35113657\"\ncat .\u002Fabstracts.json | jq '.[0].title' -r\n```\n\n## Essential Recipes\n\n**Join PMIDs for the next call (most common chaining pattern):**\n\n```bash\ncat .\u002Fsearch_results.json | jq -r 'join(\",\")'\n```\n\n**Slim abstracts to essential fields and truncate long abstracts:**\n\n```bash\ncat .\u002Fabstracts.json | jq '[.[] | {pmid, title, snippet: (.abstract \u002F\u002F \"\")[:500]}]'\n```\n\n**Filter by keyword (null-safe):**\n\n```bash\ncat .\u002Fabstracts.json | jq '[.[] | select((.title \u002F\u002F \"\") | contains(\"Review\"))]'\n```\n\n### Context Management & Accuracy\n\nWhen processing larger result sets (>10 abstracts):\n\n1.  **Filter Early**: Use `jq` to verify keywords in abstracts *before* reading\n    the full JSON into context.\n2.  **Slimming**: Extract only `title` and `abstract` fields unless explicitly\n    instructed otherwise. Author lists and metadata contribute to noise.\n3.  **Bulk Operations (N > 10)**: Avoid fetching or processing IDs one-by-one.\n    The API and History Server are designed for bulk retrieval. Fetch all data\n    in a **single turn** and use shell pipelines to slim the results before\n    reading into context. This prevents turn exhaustion and context overflow.\n4.  **Grounding**: Never use internal knowledge to provide specific identifiers\n    (PMIDs, CIDs, Gene IDs) if no results are found. Report the tool's output\n    accurately to ensure results are grounded in the current database state.\n5.  **Search Termination**: When asked to find papers that may not exist, limit\n    exploration to 3–5 high-quality, varied search queries. If no results match\n    after these attempts, conclude that no papers meet the criteria rather than\n    continuing to iterate — unless explicitly instructed to be thorough.\n\n## Functions\n\n> **⚠️ MANDATORY**: You **MUST** read the linked reference file for a function\n> group **before calling any function** in that group. The tables below only\n> describe *what* each function does — not *how* to call it. Argument names,\n> argument order, flags, and output schemas are **only** documented in the\n> reference files. **Do NOT guess or infer arguments from function names.** If\n> you call a function without first reading its reference, you **will** produce\n> incorrect invocations.\n\n### [Search](references\u002Fsearch-and-discovery.md)\n\n-   `search_pubmed`: Find PMIDs matching a free-text or structured NCBI query.\n-   `global_database_discovery`: Count how many records match a query across\n    every NCBI database.\n\n### [Fetch & Resolve](references\u002Ffetch-and-resolve.md)\n\n-   `fetch_article_abstracts`: Retrieve metadata and abstracts for a batch of\n    PMIDs.\n-   `get_full_text_pmc`: Retrieve open-access full text from PMC.\n-   `fetch_database_summary`: Resolve opaque UIDs from any NCBI database into\n    human-readable metadata.\n\n### [Cross-Database Linking](references\u002Fcross-database-linking.md)\n\n-   `find_linked_biological_data`: Find records in other NCBI databases linked\n    to a source record.\n-   `discover_available_links`: List all available ELink linknames for a given\n    record.\n\n### [Bulk Workflows](references\u002Fbulk-workflows.md)\n\nWhen working with **more than ~10 PMIDs**, avoid processing IDs one-by-one.\nUpload them to the NCBI History Server via `cache_results_history` to get a\nsession handle (`webenv` + `query_key`), then pass that handle to\n`fetch_article_abstracts` or `find_linked_biological_data` for a single bulk\ncall. Chain with `jq` shell pipelines to slim results before reading into\ncontext. This prevents turn exhaustion and context overflow. See the reference\nfor complete workflow recipes (search→fetch, cross-db exploration, citation\nresolution, and bulk retrieval with data slimming).\n\n-   `cache_results_history`: Upload PMIDs to the NCBI History Server for bulk\n    retrieval.\n\n### [Utilities](references\u002Futilities.md)\n\n-   `verify_medical_spelling`: Spell-check biomedical terms before searching.\n-   `match_raw_citations`: Resolve incomplete bibliographic citations to PMIDs.\n","# PubMed API\n\n## Prerequisites\n\n1.  **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure\n    `uv` is installed and on PATH.\n2.  **User Notification**: If .licenses\u002Fpubmed_database_LICENSE.txt does not\n    already exist in the workspace root directory then (1) prominently notify\n    the user to check the terms at https:\u002F\u002Fpubmed.ncbi.nlm.nih.gov\u002Fdisclaimer\u002F\n    and https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fhome\u002Fabout\u002Fpolicies\u002F and to always check\n    the license of the papers retrieved by the skill for any restrictions, then\n    (2) create the file recording the notification text and timestamp.\n3.  **`.env` file**: Make sure the `.env` file exists in your home directory.\n    Create one if it does not exist.\n4.  **`NCBI_API_KEY`** (optional): Raises the NCBI E-utilities rate limit from 3\n    to 10 requests\u002Fsecond. The skill works without it, but a key is recommended\n    if the user plans many queries or encounters a 429 error. You can register\n    for a key for free at https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Faccount\u002Fsettings\u002F. You\n    **MUST** use the safe credentials protocol in the `credentials` skill to\n    check for and request this key if this skill looks relevant to the user's\n    request.\n5.  **`USER_EMAIL`** (optional): Identifies the caller to NCBI (recommended by\n    their Terms of Use). You **MUST** use the safe credentials protocol in the\n    `credentials` skill to check for and request this credential if this skill\n    looks relevant to the user's request.\n\nThis skill provides CLI access to the NCBI PubMed and PubMed Central APIs via\n`scripts\u002Fpubmed_api.py` — a single CLI with 10 functions covering search, fetch,\nlinking, full text, spelling, discovery, citation matching, and caching.\n\n## Core Rules\n\n-   **API Use**: Always use the provided wrapper `scripts\u002Fpubmed_api.py` which\n    manages rate limits automatically and prevents API abuse. Setting the\n    `NCBI_API_KEY` environment variable raises the rate limit from 3 to 10\n    requests\u002Fsecond. Querying the API any other way (e.g. via curl, wget, or\n    hand-written code) is strictly forbidden.\n-   **JSON Processing**: Use `jq` to filter and transform JSON output (or python\n    equivalents if `jq` is not available) to prevent hallucinations and context\n    overflow.\n-   **Temporary Files**: To avoid polluting the working directory with JSON\n    files, use a temporary directory inside the current directory. When running\n    multiple agents or tasks in parallel, ensure each uses a unique subdirectory\n    name (e.g., `tmp_$TASK_ID\u002F`) to avoid file collisions.\n-   **Notification**: If this skill is used, ensure this is mentioned in the\n    output AND list the URLs of all papers that were used in producing the\n    output.\n\n## Structure of the skill folder\n\n-   `SKILL.md` - This file\n-   `scripts\u002Fpubmed_api.py` - The skill CLI\n-   `references\u002F` - Directory with detailed function specifications\n    -   `advanced-linking.md`\n    -   `advanced-search.md`\n    -   `bulk-workflows.md`\n    -   `citation-matching.md`\n    -   `cross-database-linking.md`\n    -   `fetch-and-resolve.md`\n    -   `search-and-discovery.md`\n    -   `utilities.md`\n\n## CLI Usage\n\n```bash\nuv run scripts\u002Fpubmed_api.py \u003Coutput_file> \u003Cfunction_name> \u003Crequired_args> [--flag value ...]\n```\n\n-   **Positional Arguments**: Arguments are positional; list arguments are\n    passed as comma-separated strings without spaces (e.g.\n    `\"35113657,31234568\"`).\n-   **Flag Options**: Optional arguments can be passed as `--flag value` instead\n    of positional args.\n-   **Output Handling**: On success, JSON is written to `output_file`. On error,\n    the process exits with a non-zero code and no output file is written.\n\n### Example Usage\n\n```bash\nuv run scripts\u002Fpubmed_api.py .\u002Fsearch_results.json search_pubmed \"BRCA1\" --max_results 5\ncat .\u002Fsearch_results.json | jq '.[]' -r\nuv run scripts\u002Fpubmed_api.py .\u002Fabstracts.json fetch_article_abstracts \"35113657\"\ncat .\u002Fabstracts.json | jq '.[0].title' -r\n```\n\n## Essential Recipes\n\n**Join PMIDs for the next call (most common chaining pattern):**\n\n```bash\ncat .\u002Fsearch_results.json | jq -r 'join(\",\")'\n```\n\n**Slim abstracts to essential fields and truncate long abstracts:**\n\n```bash\ncat .\u002Fabstracts.json | jq '[.[] | {pmid, title, snippet: (.abstract \u002F\u002F \"\")[:500]}]'\n```\n\n**Filter by keyword (null-safe):**\n\n```bash\ncat .\u002Fabstracts.json | jq '[.[] | select((.title \u002F\u002F \"\") | contains(\"Review\"))]'\n```\n\n### Context Management & Accuracy\n\nWhen processing larger result sets (>10 abstracts):\n\n1.  **Filter Early**: Use `jq` to verify keywords in abstracts *before* reading\n    the full JSON into context.\n2.  **Slimming**: Extract only `title` and `abstract` fields unless explicitly\n    instructed otherwise. Author lists and metadata contribute to noise.\n3.  **Bulk Operations (N > 10)**: Avoid fetching or processing IDs one-by-one.\n    The API and History Server are designed for bulk retrieval. Fetch all data\n    in a **single turn** and use shell pipelines to slim the results before\n    reading into context. This prevents turn exhaustion and context overflow.\n4.  **Grounding**: Never use internal knowledge to provide specific identifiers\n    (PMIDs, CIDs, Gene IDs) if no results are found. Report the tool's output\n    accurately to ensure results are grounded in the current database state.\n5.  **Search Termination**: When asked to find papers that may not exist, limit\n    exploration to 3–5 high-quality, varied search queries. If no results match\n    after these attempts, conclude that no papers meet the criteria rather than\n    continuing to iterate — unless explicitly instructed to be thorough.\n\n## Functions\n\n> **⚠️ MANDATORY**: You **MUST** read the linked reference file for a function\n> group **before calling any function** in that group. The tables below only\n> describe *what* each function does — not *how* to call it. Argument names,\n> argument order, flags, and output schemas are **only** documented in the\n> reference files. **Do NOT guess or infer arguments from function names.** If\n> you call a function without first reading its reference, you **will** produce\n> incorrect invocations.\n\n### [Search](references\u002Fsearch-and-discovery.md)\n\n-   `search_pubmed`: Find PMIDs matching a free-text or structured NCBI query.\n-   `global_database_discovery`: Count how many records match a query across\n    every NCBI database.\n\n### [Fetch & Resolve](references\u002Ffetch-and-resolve.md)\n\n-   `fetch_article_abstracts`: Retrieve metadata and abstracts for a batch of\n    PMIDs.\n-   `get_full_text_pmc`: Retrieve open-access full text from PMC.\n-   `fetch_database_summary`: Resolve opaque UIDs from any NCBI database into\n    human-readable metadata.\n\n### [Cross-Database Linking](references\u002Fcross-database-linking.md)\n\n-   `find_linked_biological_data`: Find records in other NCBI databases linked\n    to a source record.\n-   `discover_available_links`: List all available ELink linknames for a given\n    record.\n\n### [Bulk Workflows](references\u002Fbulk-workflows.md)\n\nWhen working with **more than ~10 PMIDs**, avoid processing IDs one-by-one.\nUpload them to the NCBI History Server via `cache_results_history` to get a\nsession handle (`webenv` + `query_key`), then pass that handle to\n`fetch_article_abstracts` or `find_linked_biological_data` for a single bulk\ncall. Chain with `jq` shell pipelines to slim results before reading into\ncontext. This prevents turn exhaustion and context overflow. See the reference\nfor complete workflow recipes (search→fetch, cross-db exploration, citation\nresolution, and bulk retrieval with data slimming).\n\n-   `cache_results_history`: Upload PMIDs to the NCBI History Server for bulk\n    retrieval.\n\n### [Utilities](references\u002Futilities.md)\n\n-   `verify_medical_spelling`: Spell-check biomedical terms before searching.\n-   `match_raw_citations`: Resolve incomplete bibliographic citations to PMIDs.\n",{"name":5,"description":7},"main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fscience-skills\u002Fpubmed_database",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 pubmed-database",{"tool":39,"command":40},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill pubmed-database",{"tool":42,"command":43},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill pubmed-database","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fpubmed_database\u002FSKILL.md",true,[47,53,57,61,65,69,73,77,81,85],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fadvanced-linking.md","REFERENCE","参考文档",5520,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fpubmed_database\u002Freferences\u002Fadvanced-linking.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fadvanced-search.md",3660,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fpubmed_database\u002Freferences\u002Fadvanced-search.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fbulk-workflows.md",3599,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fpubmed_database\u002Freferences\u002Fbulk-workflows.md",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fcitation-matching.md",5344,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fpubmed_database\u002Freferences\u002Fcitation-matching.md",{"path":66,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fcitation.bib",1809,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fpubmed_database\u002Freferences\u002Fcitation.bib",{"path":70,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fcross-database-linking.md",4025,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fpubmed_database\u002Freferences\u002Fcross-database-linking.md",{"path":74,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Ffetch-and-resolve.md",5606,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fpubmed_database\u002Freferences\u002Ffetch-and-resolve.md",{"path":78,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fsearch-and-discovery.md",4948,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fpubmed_database\u002Freferences\u002Fsearch-and-discovery.md",{"path":82,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Futilities.md",1357,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fpubmed_database\u002Freferences\u002Futilities.md",{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Fpubmed_api.py","SCRIPT","脚本",21444,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fpubmed_database\u002Fscripts\u002Fpubmed_api.py",[92,99,106,113,120,127],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"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":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"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":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"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":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"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":121,"name":122,"nameZh":6,"description":123,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"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":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"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",[],[]]