[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74MVCTHZKD6Y50ZKCVPNKGG":3,"skill-same:01M74MVCTHZKD6Y50ZKCVPNKGG":63},{"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},"01M74MVCTHZKD6Y50ZKCVPNKGG","opentargets-database",null,"Query Open Targets Platform for target-disease associations, drug target discovery, tractability\u002Fsafety data, genetics\u002Fomics evidence, known drugs, for therapeutic target identification.","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\u002Fopentargets_database\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: opentargets-database\ndescription: >\n  Query Open Targets Platform for target-disease associations, drug target\n  discovery, tractability\u002Fsafety data, genetics\u002Fomics evidence, known drugs,\n  for therapeutic target identification.\n---\n\n# Open Targets Database Skill\n\n## Overview\n\nThis skill provides access to the Open Targets Platform GraphQL API. It\naggregates multi-modal evidence from genetics (GWAS\u002FeQTL), pathways, animal\nmodels, and clinical trials to rank target-disease associations and identify\ndruggable genes.\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\u002Fopentargets_database_LICENSE.txt does\n    not already exist in the workspace root directory then (1) prominently\n    notify the user to check the terms at\n    https:\u002F\u002Fplatform-docs.opentargets.org\u002Flicence, then (2) create the file\n    recording the notification text and timestamp.\n\n## Core Rules\n\n-   **Use the Wrapper**: ALWAYS execute the provided helper scripts to query the\n    database rather than accessing the database directly. The scripts\n    automatically enforce fair use and implement retry logic.\n-   **Output Flag**: The `--output` flag is always required as output can be\n    very large. Use `jq` or write your own code to process this JSON file.\n-   **Notification**: If this skill is used, ensure this is mentioned in the\n    output.\n\n## Quick Reference\n\nAlways use the provided Python script `scripts\u002Fquery_opentargets.py` to quickly\nquery the database. It handles API communication, retries, formatting, and\nautomatically truncates overly large responses. NEVER write your own curl or\nsimilar requests.\n\n**Usage:**\n\n```bash\nuv run scripts\u002Fquery_opentargets.py --output \u002Ftmp\u002Fopentargets_results.json [OPTIONS] COMMAND [ARGS]...\n```\n\n**Common Options:**\n\n-   `--output PATH`: **Required**. Path to write the JSON output file.\n-   `--limit N`: Limit the number of items returned in arrays (default is 50).\n    Use a smaller number like 10 when doing preliminary exploration.\n-   `--page-size N`: Set the API pagination size (default is 200). Increase if\n    you need more results (e.g., a study with many credible sets).\n\n**Available Commands:**\n\n-   **`get-gwas-studies`** *`efo_id`*: Fetches all GWAS studies associated with\n    a specific disease ontology EFO ID (e.g. `EFO_0000685`).\n-   **`get-study-credible-sets`** *`study_id`*: Fetches all credible sets for a\n    given study ID (e.g. `FINNGEN_R12_RX_CROHN_2NDLINE`). Returns confidence,\n    finemapping method, variant, and p-value info.\n-   **`get-qtl-credible-sets`** *`variant_id`*: Retrieves QTL credible sets for\n    a specific variant ID (e.g. `19_44908822_C_T`).\n-   **`get-l2g`** *`variant_id [--study-id ID]`*: Returns Locus-to-Gene (L2G)\n    predictions\u002Fscores for a locus to identify the most likely causal gene. Only\n    `variant_id` is required; use `--study-id` to filter to a specific study.\n    Accepts `chr` prefix (e.g. `chr1_113834946_A_G`).\n-   **`get-target-druggability`** *`ensembl_id`*: Provides tractability data\n    (small molecule, antibody, etc.) and clinical trial safety info for a\n    gene\u002Ftarget.\n-   **`get-associated-targets`** *`efo_id`*: Find all target genes associated\n    with a specific disease EFO ID.\n-   **`get-associated-diseases`** *`ensembl_id`*: Find all diseases associated\n    with a specific target Ensembl ID.\n-   **`search-disease`** *`query_string`*: Search for a disease by name to find\n    its EFO ID and other metadata.\n-   **`get-credible-sets-near-target`** *`ensembl_id [--window N]`*: Fetches\n    credible sets for a target and filters them to those within a genomic window\n    around the target. Useful for finding variants \"nearby\" a gene.\n-   **`custom-query`** *`query [--variables '{}']`*: Run a raw GraphQL query for\n    any other Open Targets data.\n\n## L2G Query Usage\n\nThe `get-l2g` command has two modes:\n\n*   **Variant only** (`get-l2g \u003Cvariant_id>`): Returns L2G predictions from\n    **all credible sets across all studies** where that variant is the lead\n    variant. This can return a large number of results (e.g., hundreds). Use\n    this when the user wants a broad view of which gene is most likely causal at\n    a locus, or when no specific study is mentioned.\n*   **Variant + study** (`get-l2g \u003Cvariant_id> --study-id \u003Cstudy_id>`): Returns\n    L2G predictions only for credible sets from that specific study. Use this\n    when the user asks about a specific GWAS study or when you need to narrow\n    down the results.\n\n> **Incomplete results warning:** The variant-only mode can return hundreds of\n> credible sets. The default `--page-size` is 200, so if the API reports a\n> `count` higher than the number of `rows` returned, **you are seeing incomplete\n> results**. Always compare `count` to the actual number of rows. If they\n> differ, either increase `--page-size` or inform the user that only a subset\n> was retrieved.\n\n## Querying by Region\n\nTo find studies with variants \"nearby\" a gene, use\n`get-credible-sets-near-target`, which improves upon the base API by performing\na flexible search based on genomic position: `uv run\nscripts\u002Fquery_opentargets.py --output \u002Ftmp\u002Fresults.json\nget-credible-sets-near-target ENSG00000156515 --window 500000`\n\nNote that the Open Targets GraphQL schema includes a `regions` parameter for\n`credibleSets`, however it performs an exact match against pre-computed region\nstrings (e.g., `chr10:68769984-69903496`) and there is some missing data. Use\nget-credible-sets-near-target as it allows a genomic range overlap search.\n\nThis fetches credible sets associated with the target and filters them in Python\nbased on the variant's genomic position.\n\n## Advanced GraphQL Queries\n\nIf you need to query endpoints or fields not exposed by the built-in\nsubcommands, use the `custom-query` subcommand.\n\n**Before writing a custom query:** Read the reference documentation to\nunderstand the API schema, types, and see example queries. See\n[references\u002FOpenTargets_GraphQL_Guide.md](references\u002FOpenTargets_GraphQL_Guide)\nfor full schema details, endpoints, and examples.\n\n**Example: Finding drugs for a disease**\n\n```bash\nuv run scripts\u002Fquery_opentargets.py custom-query \\\n  query drugsForDisease($id: String!) {\n    disease(efoId: $id) {\n      name\n      drugAndClinicalCandidates {\n        count\n        rows {\n          maxClinicalStage\n          drug {\n            id\n            name\n          }\n        }\n      }\n    }\n  }' \\\n--variables '{\"id\": \"EFO_1001006\"}'\n--output '\u002Ftmp\u002Fopentargets_result.json'\n```\n\n## Confidence Star Ratings\n\nThe Open Targets Platform assigns a **confidence level** to each credible set\nbased on the fine-mapping method and quality checks. These correspond to star\nratings displayed in the platform UI:\n\n| Stars          | Confidence String (API value)                             |\n| -------------- | --------------------------------------------------------- |\n| ★★★★ (4 stars) | `SuSiE fine-mapped credible set with in-sample LD`        |\n| ★★★ (3 stars)  | `SuSiE fine-mapped credible set with out-of-sample LD`    |\n| ★★ (2 stars)   | `PICS fine-mapped credible set extracted from summary     |\n:                : statistics`                                               :\n| ★ (1 star)     | `PICS fine-mapped credible set based on reported top hit` |\n| None           | `Unknown confidence`                                      |\n\nWhen users ask about \"N-star confidence\", match their request to the\ncorresponding string in the `confidence` field of the API response.\n\n## Tips and Common Mistakes\n\n-   **ID Formats**:\n    -   Disease IDs must be in EFO format (e.g. `EFO_0000685`).\n    -   Target IDs must be Ensembl IDs (e.g. `ENSG00000169083`), not HGNC\n        symbols. If you only have a gene symbol, you may need to map it first\n        using a custom GraphQL `search` query.\n    -   Variant IDs are formatted as `chromosome_position_ref_alt` (e.g.,\n        `1_154426264_C_T`). A `chr` prefix (e.g. `chr1_154426264_C_T`) is\n        automatically stripped by the tool.\n    -   Study IDs can be GWAS Catalog IDs (e.g. `GCST90204201`) or\n        project-specific IDs (e.g. `FINNGEN_R12_RX_CROHN_2NDLINE`).\n-   **Truncation**: The tool truncates arrays longer than `--limit` to protect\n    the context window. If you see `\"_truncated\"`, you can run the query again\n    with a higher limit if you specifically need more data, but be cautious with\n    large limit values. Always use the `--output` flag to save the result to a\n    file and avoid terminal output truncation.\n-   **Pagination and incomplete results**: The `--page-size` option (default:\n    200) controls how many items are fetched from the API. **Always check the\n    `count` field in the response and compare it to the number of `rows`\n    actually returned.** If `count` > number of rows, you have incomplete data —\n    either increase `--page-size` to fetch more, or inform the user that only a\n    partial result set was returned. This is especially important for `get-l2g`\n    without `--study-id`, which can return hundreds of credible sets.\n","# Open Targets Database Skill\n\n## Overview\n\nThis skill provides access to the Open Targets Platform GraphQL API. It\naggregates multi-modal evidence from genetics (GWAS\u002FeQTL), pathways, animal\nmodels, and clinical trials to rank target-disease associations and identify\ndruggable genes.\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\u002Fopentargets_database_LICENSE.txt does\n    not already exist in the workspace root directory then (1) prominently\n    notify the user to check the terms at\n    https:\u002F\u002Fplatform-docs.opentargets.org\u002Flicence, then (2) create the file\n    recording the notification text and timestamp.\n\n## Core Rules\n\n-   **Use the Wrapper**: ALWAYS execute the provided helper scripts to query the\n    database rather than accessing the database directly. The scripts\n    automatically enforce fair use and implement retry logic.\n-   **Output Flag**: The `--output` flag is always required as output can be\n    very large. Use `jq` or write your own code to process this JSON file.\n-   **Notification**: If this skill is used, ensure this is mentioned in the\n    output.\n\n## Quick Reference\n\nAlways use the provided Python script `scripts\u002Fquery_opentargets.py` to quickly\nquery the database. It handles API communication, retries, formatting, and\nautomatically truncates overly large responses. NEVER write your own curl or\nsimilar requests.\n\n**Usage:**\n\n```bash\nuv run scripts\u002Fquery_opentargets.py --output \u002Ftmp\u002Fopentargets_results.json [OPTIONS] COMMAND [ARGS]...\n```\n\n**Common Options:**\n\n-   `--output PATH`: **Required**. Path to write the JSON output file.\n-   `--limit N`: Limit the number of items returned in arrays (default is 50).\n    Use a smaller number like 10 when doing preliminary exploration.\n-   `--page-size N`: Set the API pagination size (default is 200). Increase if\n    you need more results (e.g., a study with many credible sets).\n\n**Available Commands:**\n\n-   **`get-gwas-studies`** *`efo_id`*: Fetches all GWAS studies associated with\n    a specific disease ontology EFO ID (e.g. `EFO_0000685`).\n-   **`get-study-credible-sets`** *`study_id`*: Fetches all credible sets for a\n    given study ID (e.g. `FINNGEN_R12_RX_CROHN_2NDLINE`). Returns confidence,\n    finemapping method, variant, and p-value info.\n-   **`get-qtl-credible-sets`** *`variant_id`*: Retrieves QTL credible sets for\n    a specific variant ID (e.g. `19_44908822_C_T`).\n-   **`get-l2g`** *`variant_id [--study-id ID]`*: Returns Locus-to-Gene (L2G)\n    predictions\u002Fscores for a locus to identify the most likely causal gene. Only\n    `variant_id` is required; use `--study-id` to filter to a specific study.\n    Accepts `chr` prefix (e.g. `chr1_113834946_A_G`).\n-   **`get-target-druggability`** *`ensembl_id`*: Provides tractability data\n    (small molecule, antibody, etc.) and clinical trial safety info for a\n    gene\u002Ftarget.\n-   **`get-associated-targets`** *`efo_id`*: Find all target genes associated\n    with a specific disease EFO ID.\n-   **`get-associated-diseases`** *`ensembl_id`*: Find all diseases associated\n    with a specific target Ensembl ID.\n-   **`search-disease`** *`query_string`*: Search for a disease by name to find\n    its EFO ID and other metadata.\n-   **`get-credible-sets-near-target`** *`ensembl_id [--window N]`*: Fetches\n    credible sets for a target and filters them to those within a genomic window\n    around the target. Useful for finding variants \"nearby\" a gene.\n-   **`custom-query`** *`query [--variables '{}']`*: Run a raw GraphQL query for\n    any other Open Targets data.\n\n## L2G Query Usage\n\nThe `get-l2g` command has two modes:\n\n*   **Variant only** (`get-l2g \u003Cvariant_id>`): Returns L2G predictions from\n    **all credible sets across all studies** where that variant is the lead\n    variant. This can return a large number of results (e.g., hundreds). Use\n    this when the user wants a broad view of which gene is most likely causal at\n    a locus, or when no specific study is mentioned.\n*   **Variant + study** (`get-l2g \u003Cvariant_id> --study-id \u003Cstudy_id>`): Returns\n    L2G predictions only for credible sets from that specific study. Use this\n    when the user asks about a specific GWAS study or when you need to narrow\n    down the results.\n\n> **Incomplete results warning:** The variant-only mode can return hundreds of\n> credible sets. The default `--page-size` is 200, so if the API reports a\n> `count` higher than the number of `rows` returned, **you are seeing incomplete\n> results**. Always compare `count` to the actual number of rows. If they\n> differ, either increase `--page-size` or inform the user that only a subset\n> was retrieved.\n\n## Querying by Region\n\nTo find studies with variants \"nearby\" a gene, use\n`get-credible-sets-near-target`, which improves upon the base API by performing\na flexible search based on genomic position: `uv run\nscripts\u002Fquery_opentargets.py --output \u002Ftmp\u002Fresults.json\nget-credible-sets-near-target ENSG00000156515 --window 500000`\n\nNote that the Open Targets GraphQL schema includes a `regions` parameter for\n`credibleSets`, however it performs an exact match against pre-computed region\nstrings (e.g., `chr10:68769984-69903496`) and there is some missing data. Use\nget-credible-sets-near-target as it allows a genomic range overlap search.\n\nThis fetches credible sets associated with the target and filters them in Python\nbased on the variant's genomic position.\n\n## Advanced GraphQL Queries\n\nIf you need to query endpoints or fields not exposed by the built-in\nsubcommands, use the `custom-query` subcommand.\n\n**Before writing a custom query:** Read the reference documentation to\nunderstand the API schema, types, and see example queries. See\n[references\u002FOpenTargets_GraphQL_Guide.md](references\u002FOpenTargets_GraphQL_Guide)\nfor full schema details, endpoints, and examples.\n\n**Example: Finding drugs for a disease**\n\n```bash\nuv run scripts\u002Fquery_opentargets.py custom-query \\\n  query drugsForDisease($id: String!) {\n    disease(efoId: $id) {\n      name\n      drugAndClinicalCandidates {\n        count\n        rows {\n          maxClinicalStage\n          drug {\n            id\n            name\n          }\n        }\n      }\n    }\n  }' \\\n--variables '{\"id\": \"EFO_1001006\"}'\n--output '\u002Ftmp\u002Fopentargets_result.json'\n```\n\n## Confidence Star Ratings\n\nThe Open Targets Platform assigns a **confidence level** to each credible set\nbased on the fine-mapping method and quality checks. These correspond to star\nratings displayed in the platform UI:\n\n| Stars          | Confidence String (API value)                             |\n| -------------- | --------------------------------------------------------- |\n| ★★★★ (4 stars) | `SuSiE fine-mapped credible set with in-sample LD`        |\n| ★★★ (3 stars)  | `SuSiE fine-mapped credible set with out-of-sample LD`    |\n| ★★ (2 stars)   | `PICS fine-mapped credible set extracted from summary     |\n:                : statistics`                                               :\n| ★ (1 star)     | `PICS fine-mapped credible set based on reported top hit` |\n| None           | `Unknown confidence`                                      |\n\nWhen users ask about \"N-star confidence\", match their request to the\ncorresponding string in the `confidence` field of the API response.\n\n## Tips and Common Mistakes\n\n-   **ID Formats**:\n    -   Disease IDs must be in EFO format (e.g. `EFO_0000685`).\n    -   Target IDs must be Ensembl IDs (e.g. `ENSG00000169083`), not HGNC\n        symbols. If you only have a gene symbol, you may need to map it first\n        using a custom GraphQL `search` query.\n    -   Variant IDs are formatted as `chromosome_position_ref_alt` (e.g.,\n        `1_154426264_C_T`). A `chr` prefix (e.g. `chr1_154426264_C_T`) is\n        automatically stripped by the tool.\n    -   Study IDs can be GWAS Catalog IDs (e.g. `GCST90204201`) or\n        project-specific IDs (e.g. `FINNGEN_R12_RX_CROHN_2NDLINE`).\n-   **Truncation**: The tool truncates arrays longer than `--limit` to protect\n    the context window. If you see `\"_truncated\"`, you can run the query again\n    with a higher limit if you specifically need more data, but be cautious with\n    large limit values. Always use the `--output` flag to save the result to a\n    file and avoid terminal output truncation.\n-   **Pagination and incomplete results**: The `--page-size` option (default:\n    200) controls how many items are fetched from the API. **Always check the\n    `count` field in the response and compare it to the number of `rows`\n    actually returned.** If `count` > number of rows, you have incomplete data —\n    either increase `--page-size` to fetch more, or inform the user that only a\n    partial result set was returned. This is especially important for `get-l2g`\n    without `--study-id`, which can return hundreds of credible sets.\n",{"name":5,"description":7},"main","e71245365df78e06cd166602744bf2491f79910e","research-skills-hub\u002Fscience-skills\u002Fopentargets_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 opentargets-database",{"tool":39,"command":40},"bunx","bunx skills add pengqianhan\u002FAI-Human-Research-OS --skill opentargets-database",{"tool":42,"command":43},"pnpm","pnpm dlx skills add pengqianhan\u002FAI-Human-Research-OS --skill opentargets-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\u002Fopentargets_database\u002FSKILL.md",true,[47,53,57],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcitation.bib","REFERENCE","参考文档",2489,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fopentargets_database\u002Freferences\u002Fcitation.bib",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002FOpenTargets_GraphQL_Guide.md",7452,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fopentargets_database\u002Freferences\u002FOpenTargets_GraphQL_Guide.md",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Fquery_opentargets.py","SCRIPT","脚本",16214,"https:\u002F\u002Fgithub.com\u002Fpengqianhan\u002FAI-Human-Research-OS\u002Fblob\u002Fmain\u002Fresearch-skills-hub\u002Fscience-skills\u002Fopentargets_database\u002Fscripts\u002Fquery_opentargets.py",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"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":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"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":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"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":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},"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":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},"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",[],[]]