[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZ69DMF1PDKW83RWARQX6D":3,"skill-same:01M6CZ69DMF1PDKW83RWARQX6D":66},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":34,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M6CZ69DMF1PDKW83RWARQX6D","stat-nonlinear-embedding",null,"Embed high-dimensional data into 2D using t-SNE or UMAP for exploratory visualization of sample or cell relationships.","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\u002Fstat-nonlinear-embedding\u002FSKILL.md",[],[19,20,21,22,23,24,25],"stat nonlinear embedding","visualization","data","relationships","sample","cell","exploratory visualization","2026-11-10 10:12:30",false,"---\nname: stat-nonlinear-embedding\ndescription: Embed high-dimensional data into 2D using t-SNE or UMAP for exploratory visualization of sample or cell relationships.\n---\n\n# Skill: Nonlinear Dimensionality Reduction\n\n## Use When\n\n- User wants to visualize cell populations or sample clusters in 2D after scRNA-seq, flow cytometry, or omics analysis\n- User wants a t-SNE or UMAP plot colored by cell type, cluster, or metadata\n- User needs a nonlinear embedding that preserves local neighborhood structure\n- Use `stat-pca` for linear embedding first, then this skill for refined visualization\n\n## Inputs\n\n- Required:\n  - Data matrix (CSV or TSV): rows = samples\u002Fcells, columns = features; OR a precomputed PCA coordinate table\n- Optional:\n  - Embedding method: `umap` (default) or `tsne`\n  - Input type: `raw` (default) or `pca` (precomputed PC coordinates)\n  - For t-SNE: perplexity (default: `30`), max iterations (default: `1000`), learning rate (default: `200`)\n  - For UMAP: n_neighbors (default: `15`), min_dist (default: `0.1`), metric (default: `euclidean`)\n  - Metadata table (CSV or TSV) for coloring the plot\n  - Color-by column from metadata\n  - Random seed (default: `42`)\n  - Output directory (default: `.\u002Fembedding_output`)\n\n## Workflow\n\n1. Read data matrix or precomputed PCA coordinates.\n2. If raw data: run PCA first (top 50 PCs) and use PCs as input to embedding (standard practice for large omics datasets).\n3. Fit t-SNE or UMAP using specified parameters and random seed.\n4. Extract 2D embedding coordinates for each sample\u002Fcell.\n5. If metadata provided: join embedding coordinates with metadata; generate scatter plot colored by specified column.\n6. If no metadata: generate plain scatter plot.\n7. Report: number of samples embedded, method and parameters used, runtime.\n8. Write embedding coordinates (TSV) and scatter plot (PDF) to output directory.\n9. Save the executable analysis script (`analysis_code.py` or `analysis_code.R`) and software version manifest (`session_info.txt`) used to produce results.\n\n## Output Contract\n\n- Embedding coordinates (TSV): sample_id, dim1, dim2\n- Scatter plot (PDF): 2D embedding colored by metadata or uniform color\n- Parameters used (printed to stdout): method, all hyperparameters, random seed\n- Reproducibility artifacts: `analysis_code.py` or `analysis_code.R`, plus `session_info.txt`\n\n## Limits\n\n- t-SNE and UMAP are non-deterministic (set seed for reproducibility); results vary with hyperparameters.\n- t-SNE distances between clusters are not interpretable — use only for local structure visualization.\n- UMAP better preserves global structure than t-SNE and is generally faster.\n- Both methods are sensitive to the scale of input data; ensure PCA pre-processing for high-dimensional input.\n- Common failure: memory error for very large inputs (> 100k cells) — subsample or use approximate UMAP.\n","# Skill: Nonlinear Dimensionality Reduction\n\n## Use When\n\n- User wants to visualize cell populations or sample clusters in 2D after scRNA-seq, flow cytometry, or omics analysis\n- User wants a t-SNE or UMAP plot colored by cell type, cluster, or metadata\n- User needs a nonlinear embedding that preserves local neighborhood structure\n- Use `stat-pca` for linear embedding first, then this skill for refined visualization\n\n## Inputs\n\n- Required:\n  - Data matrix (CSV or TSV): rows = samples\u002Fcells, columns = features; OR a precomputed PCA coordinate table\n- Optional:\n  - Embedding method: `umap` (default) or `tsne`\n  - Input type: `raw` (default) or `pca` (precomputed PC coordinates)\n  - For t-SNE: perplexity (default: `30`), max iterations (default: `1000`), learning rate (default: `200`)\n  - For UMAP: n_neighbors (default: `15`), min_dist (default: `0.1`), metric (default: `euclidean`)\n  - Metadata table (CSV or TSV) for coloring the plot\n  - Color-by column from metadata\n  - Random seed (default: `42`)\n  - Output directory (default: `.\u002Fembedding_output`)\n\n## Workflow\n\n1. Read data matrix or precomputed PCA coordinates.\n2. If raw data: run PCA first (top 50 PCs) and use PCs as input to embedding (standard practice for large omics datasets).\n3. Fit t-SNE or UMAP using specified parameters and random seed.\n4. Extract 2D embedding coordinates for each sample\u002Fcell.\n5. If metadata provided: join embedding coordinates with metadata; generate scatter plot colored by specified column.\n6. If no metadata: generate plain scatter plot.\n7. Report: number of samples embedded, method and parameters used, runtime.\n8. Write embedding coordinates (TSV) and scatter plot (PDF) to output directory.\n9. Save the executable analysis script (`analysis_code.py` or `analysis_code.R`) and software version manifest (`session_info.txt`) used to produce results.\n\n## Output Contract\n\n- Embedding coordinates (TSV): sample_id, dim1, dim2\n- Scatter plot (PDF): 2D embedding colored by metadata or uniform color\n- Parameters used (printed to stdout): method, all hyperparameters, random seed\n- Reproducibility artifacts: `analysis_code.py` or `analysis_code.R`, plus `session_info.txt`\n\n## Limits\n\n- t-SNE and UMAP are non-deterministic (set seed for reproducibility); results vary with hyperparameters.\n- t-SNE distances between clusters are not interpretable — use only for local structure visualization.\n- UMAP better preserves global structure than t-SNE and is generally faster.\n- Both methods are sensitive to the scale of input data; ensure PCA pre-processing for high-dimensional input.\n- Common failure: memory error for very large inputs (> 100k cells) — subsample or use approximate UMAP.\n",{"name":5,"description":7},"main","5118e7fda890e9aa819cb71e003cd243d3a31970","skills\u002Fstat-nonlinear-embedding",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":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add Scientific-Tooling\u002Fstructured-intelligence --skill stat-nonlinear-embedding",{"tool":44,"command":45},"bunx","bunx skills add Scientific-Tooling\u002Fstructured-intelligence --skill stat-nonlinear-embedding",{"tool":47,"command":48},"pnpm","pnpm dlx skills add Scientific-Tooling\u002Fstructured-intelligence --skill stat-nonlinear-embedding","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fstat-nonlinear-embedding\u002FSKILL.md",true,[52,58,62],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"agents\u002Fclaude.yaml","REFERENCE","参考文档",344,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fstat-nonlinear-embedding\u002Fagents\u002Fclaude.yaml",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"agents\u002Fopenai.yaml",345,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fstat-nonlinear-embedding\u002Fagents\u002Fopenai.yaml",{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"config.yaml",311,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fstat-nonlinear-embedding\u002Fconfig.yaml",[67,95,108,119,133,145],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":78,"publishedAt":26},"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",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94],"structured intelligence skill creator","structured","intelligence","skill creator","validation","workflows","requirements","create","update","registry","metadata","repository","templates","Rules","provider","local",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":26},"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",[],[102,103,104,105,106,107],"stat survival analysis","analysis","log","functions","test","regression",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":26},"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",[],[115,116,117,21,118,23],"stat pca","visualize","contributing","structure",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":26},"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",[],[126,127,128,129,130,131,132],"stat pairwise correlation","correlation","produce","heatmap","compute","across","tests",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":26},"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",[],[140,107,141,142,143,144],"stat logistic regression","performance","outcomes","model","report",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":26},"01M6CZ63JR8A7YR02312EY9AQ4","stat-learn-bayesian-network","Learn the structure and conditional probabilities of a Bayesian network from observational data for causal discovery or dependency modeling.","https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fstat-learn-bayesian-network\u002FSKILL.md",[],[152,153,154,118,155,21,156,157],"network","learn","stat learn bayesian network","dependency","discovery","modeling"]