[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZ59GZVX15MAB89EF860FB":3,"skill-same:01M6CZ59GZVX15MAB89EF860FB":67},{"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":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M6CZ59GZVX15MAB89EF860FB","search-ncbi-datasets",null,"Search NCBI Datasets for genome assemblies, genes, taxonomy records, and virus genomes using the NCBI Datasets CLI or REST API.","Scientific-Tooling\u002Fstructured-intelligence","Scientific-Tooling","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F267453265?v=4","01M6CZ1SE6GGD4F67EAQ0PVX38","Scientific Tooling","01M6CZ1SJKCFVGH10Z3A152K02",4,"MIT","https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-ncbi-datasets\u002FSKILL.md",[],[19,20,21,22,23,24,25,26],"search","datasets","search ncbi datasets","cli","REST","api","taxonomy","rest api","2026-11-10 10:12:30",false,"---\nname: search-ncbi-datasets\ndescription: Search NCBI Datasets for genome assemblies, genes, taxonomy records, and virus genomes using the NCBI Datasets CLI or REST API.\n---\n\n# Skill: Search NCBI Datasets\n\n## Use When\n\n- A user wants to find and download genome assemblies from the NCBI Datasets portal.\n- A user needs to query genomes by organism name, taxonomy ID, assembly accession (GCF\u002FGCA), or assembly level (complete, chromosome, scaffold, contig).\n- A user wants gene-level data: sequences, annotations, or orthologs by gene symbol, gene ID, or taxon.\n- A user wants virus genome records (NCBI Virus) by species, collection date, host, or geographic region.\n- A user wants summary statistics (assembly count, N50, total length) for a set of assemblies before downloading.\n- A user wants to generate a dehydrated dataset package and rehydrate later, or get direct download links for genome FASTA\u002FGFF\u002FGTF files.\n\n## Inputs\n\n- Required:\n  - one of: organism name or NCBI taxonomy ID, assembly accession (GCF_\u002FGCA_), gene symbol or gene ID, or virus taxon\n- Optional:\n  - data type: `genome`, `gene`, `virus`, `taxonomy` (default: `genome`)\n  - assembly level filter: `complete`, `chromosome`, `scaffold`, `contig`\n  - assembly source filter: `refseq` (GCF) or `genbank` (GCA)\n  - annotation filter: `annotated` (only assemblies with annotation)\n  - reference-only flag: restrict to reference\u002Frepresentative genomes\n  - include flags for genome downloads: `genome`, `rna`, `protein`, `cds`, `gff3`, `gtf`, `seq-report`\n  - limit on number of results\n  - output format: `json` (summary) or direct download (zip package)\n  - output directory\n\n## Workflow\n\n1. Choose the interface:\n   - **NCBI Datasets CLI** (`datasets` + `dataformat`): preferred for batch or scripted use.\n   - **NCBI Datasets REST API**: use when the CLI is not installed.\n     Base URL: `https:\u002F\u002Fapi.ncbi.nlm.nih.gov\u002Fdatasets\u002Fv2\u002F`\n\n2. For genome assembly searches:\n   - CLI: `datasets summary genome taxon \"\u003Corganism>\" --assembly-level complete --reference`\n   - API: `GET https:\u002F\u002Fapi.ncbi.nlm.nih.gov\u002Fdatasets\u002Fv2\u002Fgenome\u002Ftaxon\u002F\u003Ctaxon>\u002Fdataset_report`\n   - Reformat summary with: `dataformat tsv genome --fields accession,organism-name,assembly-level,genome-size,contig-n50,annotation-info-release-date`\n\n3. For gene searches:\n   - CLI: `datasets summary gene symbol \u003CGENE> --taxon \"\u003Corganism>\"`\n   - CLI: `datasets summary gene id \u003Cgene_id>`\n\n4. For virus genome searches:\n   - CLI: `datasets summary virus genome taxon \u003Ctaxon> --host \"\u003Chost>\" --geo-location \"\u003Ccountry>\"`\n   - Filter by collection date range with `--released-after` \u002F `--released-before`.\n\n5. To download data:\n   - `datasets download genome accession \u003CGCF_> --include genome,gff3,gtf --filename \u003Cout>.zip`\n   - For large batches, use `--dehydrated` and then `datasets rehydrate --directory \u003Cdir>`.\n\n6. Parse the JSON summary to extract key fields and report a summary table.\n\n## Output Contract\n\n- Exact CLI command or API URL used\n- Number of matching records\n- Summary table for genome queries: Accession (GCF\u002FGCA), Organism, Assembly Level, Genome Size (Mb), Contig N50, Annotation Date, Submitter\n- Summary table for gene queries: Gene ID, Symbol, Full Name, Taxon, Location, RefSeq mRNA\u002FProtein accessions\n- Download command(s) for selected accessions\n- Saved output files when a directory is provided:\n  - `summary.json` (raw API\u002FCLI output)\n  - `summary.tsv` (reformatted with `dataformat`)\n  - `accessions.txt` (one accession per line)\n\n## Limits\n\n- This skill depends on live access to `https:\u002F\u002Fapi.ncbi.nlm.nih.gov\u002Fdatasets\u002Fv2\u002F` or a local install of the `datasets` CLI.\n- NCBI Datasets API rate limits apply; add `NCBI_API_KEY` environment variable or `--api-key` flag for higher throughput.\n- The `datasets` CLI must be installed separately (available from https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fdatasets\u002Fdocs\u002Fv2\u002Fdownload-and-install\u002F).\n- Genome download packages can be very large; always check genome size and count before issuing a download.\n- Not all assemblies in GenBank have annotation; use `--annotated` when annotation files are required.\n- Virus genome data is stored separately from the main genome database; queries must use `datasets summary virus`.\n- Common failure cases:\n  - specifying a taxon name with incorrect spelling or outdated taxonomy\n  - requesting `--include gff3` for assemblies without annotation (download will still proceed but GFF3 will be absent)\n  - confusing GCF (RefSeq) with GCA (GenBank) accessions when a specific source is required\n  - omitting `dataformat` to reformat JSON output, resulting in hard-to-parse raw JSON\n","# Skill: Search NCBI Datasets\n\n## Use When\n\n- A user wants to find and download genome assemblies from the NCBI Datasets portal.\n- A user needs to query genomes by organism name, taxonomy ID, assembly accession (GCF\u002FGCA), or assembly level (complete, chromosome, scaffold, contig).\n- A user wants gene-level data: sequences, annotations, or orthologs by gene symbol, gene ID, or taxon.\n- A user wants virus genome records (NCBI Virus) by species, collection date, host, or geographic region.\n- A user wants summary statistics (assembly count, N50, total length) for a set of assemblies before downloading.\n- A user wants to generate a dehydrated dataset package and rehydrate later, or get direct download links for genome FASTA\u002FGFF\u002FGTF files.\n\n## Inputs\n\n- Required:\n  - one of: organism name or NCBI taxonomy ID, assembly accession (GCF_\u002FGCA_), gene symbol or gene ID, or virus taxon\n- Optional:\n  - data type: `genome`, `gene`, `virus`, `taxonomy` (default: `genome`)\n  - assembly level filter: `complete`, `chromosome`, `scaffold`, `contig`\n  - assembly source filter: `refseq` (GCF) or `genbank` (GCA)\n  - annotation filter: `annotated` (only assemblies with annotation)\n  - reference-only flag: restrict to reference\u002Frepresentative genomes\n  - include flags for genome downloads: `genome`, `rna`, `protein`, `cds`, `gff3`, `gtf`, `seq-report`\n  - limit on number of results\n  - output format: `json` (summary) or direct download (zip package)\n  - output directory\n\n## Workflow\n\n1. Choose the interface:\n   - **NCBI Datasets CLI** (`datasets` + `dataformat`): preferred for batch or scripted use.\n   - **NCBI Datasets REST API**: use when the CLI is not installed.\n     Base URL: `https:\u002F\u002Fapi.ncbi.nlm.nih.gov\u002Fdatasets\u002Fv2\u002F`\n\n2. For genome assembly searches:\n   - CLI: `datasets summary genome taxon \"\u003Corganism>\" --assembly-level complete --reference`\n   - API: `GET https:\u002F\u002Fapi.ncbi.nlm.nih.gov\u002Fdatasets\u002Fv2\u002Fgenome\u002Ftaxon\u002F\u003Ctaxon>\u002Fdataset_report`\n   - Reformat summary with: `dataformat tsv genome --fields accession,organism-name,assembly-level,genome-size,contig-n50,annotation-info-release-date`\n\n3. For gene searches:\n   - CLI: `datasets summary gene symbol \u003CGENE> --taxon \"\u003Corganism>\"`\n   - CLI: `datasets summary gene id \u003Cgene_id>`\n\n4. For virus genome searches:\n   - CLI: `datasets summary virus genome taxon \u003Ctaxon> --host \"\u003Chost>\" --geo-location \"\u003Ccountry>\"`\n   - Filter by collection date range with `--released-after` \u002F `--released-before`.\n\n5. To download data:\n   - `datasets download genome accession \u003CGCF_> --include genome,gff3,gtf --filename \u003Cout>.zip`\n   - For large batches, use `--dehydrated` and then `datasets rehydrate --directory \u003Cdir>`.\n\n6. Parse the JSON summary to extract key fields and report a summary table.\n\n## Output Contract\n\n- Exact CLI command or API URL used\n- Number of matching records\n- Summary table for genome queries: Accession (GCF\u002FGCA), Organism, Assembly Level, Genome Size (Mb), Contig N50, Annotation Date, Submitter\n- Summary table for gene queries: Gene ID, Symbol, Full Name, Taxon, Location, RefSeq mRNA\u002FProtein accessions\n- Download command(s) for selected accessions\n- Saved output files when a directory is provided:\n  - `summary.json` (raw API\u002FCLI output)\n  - `summary.tsv` (reformatted with `dataformat`)\n  - `accessions.txt` (one accession per line)\n\n## Limits\n\n- This skill depends on live access to `https:\u002F\u002Fapi.ncbi.nlm.nih.gov\u002Fdatasets\u002Fv2\u002F` or a local install of the `datasets` CLI.\n- NCBI Datasets API rate limits apply; add `NCBI_API_KEY` environment variable or `--api-key` flag for higher throughput.\n- The `datasets` CLI must be installed separately (available from https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fdatasets\u002Fdocs\u002Fv2\u002Fdownload-and-install\u002F).\n- Genome download packages can be very large; always check genome size and count before issuing a download.\n- Not all assemblies in GenBank have annotation; use `--annotated` when annotation files are required.\n- Virus genome data is stored separately from the main genome database; queries must use `datasets summary virus`.\n- Common failure cases:\n  - specifying a taxon name with incorrect spelling or outdated taxonomy\n  - requesting `--include gff3` for assemblies without annotation (download will still proceed but GFF3 will be absent)\n  - confusing GCF (RefSeq) with GCA (GenBank) accessions when a specific source is required\n  - omitting `dataformat` to reformat JSON output, resulting in hard-to-parse raw JSON\n",{"name":5,"description":7},"main","5118e7fda890e9aa819cb71e003cd243d3a31970","skills\u002Fsearch-ncbi-datasets",1,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence","https:\u002F\u002Fgithub.com\u002FScientific-Tooling","2026-11-03 00:01:40",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add Scientific-Tooling\u002Fstructured-intelligence --skill search-ncbi-datasets",{"tool":45,"command":46},"bunx","bunx skills add Scientific-Tooling\u002Fstructured-intelligence --skill search-ncbi-datasets",{"tool":48,"command":49},"pnpm","pnpm dlx skills add Scientific-Tooling\u002Fstructured-intelligence --skill search-ncbi-datasets","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-ncbi-datasets\u002FSKILL.md",true,[53,59,63],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"agents\u002Fclaude.yaml","REFERENCE","参考文档",338,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-ncbi-datasets\u002Fagents\u002Fclaude.yaml",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"agents\u002Fopenai.yaml",339,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-ncbi-datasets\u002Fagents\u002Fopenai.yaml",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"config.yaml",329,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fsearch-ncbi-datasets\u002Fconfig.yaml",[68,96,109,122,136,148],{"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":79,"publishedAt":27},"01M6CZ6S2C54G03K71G77H22KE","structured-intelligence-skill-creator","Create or update repository skills that conform to local templates, provider metadata requirements, registry rules, and validation workflows.","https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fstructured-intelligence-skill-creator\u002FSKILL.md",[74],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95],"structured intelligence skill creator","skill creator","intelligence","structured","create","requirements","workflows","provider","update","registry","local","validation","metadata","repository","templates","Rules",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":27},"01M6CZ6M3JFN400406T1NPWNER","stat-survival-analysis","Estimate and compare survival functions using Kaplan-Meier curves and log-rank test, with optional Cox proportional hazards regression.","https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fstat-survival-analysis\u002FSKILL.md",[],[103,104,105,106,107,108],"analysis","stat survival analysis","regression","log","functions","test",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":27},"01M6CZ6G5JPDZASM4DRD9QCTEE","stat-pca","Perform PCA on a numeric data matrix to reduce dimensionality, visualize sample structure, and identify top contributing features.","https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fstat-pca\u002FSKILL.md",[],[116,117,118,119,120,121],"stat pca","sample","visualize","contributing","data","structure",{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":27},"01M6CZ6D9A3N6849BT9VYFSBK5","stat-pairwise-correlation","Compute pairwise correlations and significance tests across all numeric variables, and produce a correlation heatmap.","https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fstat-pairwise-correlation\u002FSKILL.md",[],[129,130,131,132,133,134,135],"stat pairwise correlation","correlation","produce","heatmap","compute","across","tests",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":27},"01M6CZ69DMF1PDKW83RWARQX6D","stat-nonlinear-embedding","Embed high-dimensional data into 2D using t-SNE or UMAP for exploratory visualization of sample or cell relationships.","https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fstat-nonlinear-embedding\u002FSKILL.md",[],[143,144,120,145,117,146,147],"stat nonlinear embedding","visualization","relationships","cell","exploratory visualization",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":27},"01M6CZ65YZGJV40F2FZNH04PBS","stat-logistic-regression","Fit a logistic regression model for binary outcomes, report odds ratios and model performance (AUC-ROC, confusion matrix).","https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fstat-logistic-regression\u002FSKILL.md",[],[105,155,156,157,158,159],"stat logistic regression","report","model","outcomes","performance"]