[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZ216KA0JAWDYHCD3PVWM5":3,"skill-same:01M6CZ216KA0JAWDYHCD3PVWM5":133},{"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},"01M6CZ216KA0JAWDYHCD3PVWM5","bioinformatics-env-setup",null,"Guide users through installing and verifying bioinformatics software for NGS, RNA-seq, scRNA-seq, and metagenomics pipelines using conda, pip, or manual installation.","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\u002Fbioinformatics-env-setup\u002FSKILL.md",[],[19,20,21,22,23,24,25],"setup","bioinformatics","bioinformatics env setup","guide","pipelines","installation","RNA","2026-11-10 10:12:30",false,"---\nname: bioinformatics-env-setup\ndescription: Guide users through installing and verifying bioinformatics software for NGS, RNA-seq, scRNA-seq, and metagenomics pipelines using conda, pip, or manual installation.\n---\n\n# Skill: Bioinformatics Environment Setup\n\n## Use When\n\n- User is starting a new analysis and wants to install the required bioinformatics tools.\n- A pipeline step fails because a tool is missing or the wrong version is installed.\n- User asks how to install a specific bioinformatics tool (e.g., STAR, Cell Ranger, Scanpy, Seurat).\n- User wants a ready-to-use conda environment for a specific pipeline.\n- User is setting up a new compute environment (HPC, cloud VM, local workstation).\n\n## Inputs\n\n- Required:\n  - Target pipeline(s): one or more of `ngs-shared`, `wgs`, `rnaseq`, `scrnaseq`, `metagenomics`, or `all`\n- Optional:\n  - Installation method: `conda` (default), `docker`, or `manual`\n  - Operating system: `linux` (default), `macos`\n  - Environment name prefix (default: `bioinfo`)\n  - Conda channel priority: `strict` (default, reproducible) or `flexible`\n  - Whether to verify existing installations before installing (default: true)\n\n## Workflow\n\n1. **Detect the environment**: Check whether `conda`\u002F`mamba` is available (`which conda`), whether Docker is available (`docker --version`), and whether an HPC module system is present (`module avail`). Report findings to the user and recommend the best installation path.\n\n2. **Check existing installations**: For each tool in the requested pipeline group(s), run `which \u003Ctool> && \u003Ctool> --version 2>&1 | head -1` to detect installed versions. Report a summary table: tool name, found\u002Fmissing, installed version, required minimum version.\n\n3. **Select the installation asset**: Choose the appropriate conda environment YAML from `assets\u002Fenvs\u002F`:\n   - `ngs-shared.yaml` — FastQC, MultiQC, fastp, Trimmomatic, samtools\n   - `wgs.yaml` — BWA-MEM2, GATK, Picard, bcftools, VEP, SnpEff\n   - `rnaseq.yaml` — STAR, HISAT2, featureCounts (subread), salmon, kallisto, DESeq2 (R), edgeR (R)\n   - `scrnaseq-python.yaml` — STARsolo (STAR), Scanpy, scVI-tools, scVelo, Scrublet, CellBender, harmonypy\n   - `scrnaseq-r.yaml` — Seurat v5, SingleR, scDblFinder, SoupX, Monocle3, DoubletFinder\n   - `metagenomics.yaml` — Bowtie2, MetaPhlAn4, HUMAnN3, Kraken2, Bracken, metaSPAdes, MEGAHIT, Prokka\n\n4. **Create the conda environment**:\n   ```bash\n   mamba env create -f assets\u002Fenvs\u002F\u003Cpipeline>.yaml\n   # or, if mamba is unavailable:\n   conda env create -f assets\u002Fenvs\u002F\u003Cpipeline>.yaml\n   ```\n   Prefer `mamba` over `conda` for significantly faster dependency resolution.\n\n5. **Handle tools that cannot be installed via conda** — prompt the user with manual steps:\n   - **Cell Ranger**: Download from the 10x Genomics website (requires registration). Add to PATH: `export PATH=\u002Fpath\u002Fto\u002Fcellranger:$PATH`.\n   - **CellBender**: Install via pip inside the conda environment: `pip install cellbender`. Requires CUDA for GPU acceleration.\n   - **DoubletFinder**: Install from GitHub inside R: `remotes::install_github(\"chris-mcginnis-ucsf\u002FDoubletFinder\")`.\n   - **Monocle3**: Install from Bioconductor: `BiocManager::install(\"monocle3\")`. Alternatively: `remotes::install_github(\"cole-trapnell-lab\u002Fmonocle3\")`.\n   - **velocyto** (for RNA velocity loom generation): `pip install velocyto`. Requires `samtools` and a reference GTF.\n\n6. **Verify all installations**: After installation, re-run the version check for each tool. For R packages, run `Rscript -e 'packageVersion(\"\u003Cpkg>\")'`. Report a final verification table: tool, expected version, installed version, status (PASS\u002FFAIL).\n\n7. **Report any failures** with the specific error message and the most likely fix (e.g., missing system library, incompatible CUDA version, wrong conda channel).\n\n## Output Contract\n\n- Environment detection summary (printed to console)\n- Pre-installation version check table (TSV or formatted table): tool, status, version\n- Installation commands executed (echo each command before running)\n- Post-installation verification table (TSV or formatted table): tool, expected_min_version, installed_version, pass\u002Ffail\n- List of any tools that require manual installation steps, with exact instructions\n\n## Limits\n\n- Cell Ranger requires registration and manual download from 10x Genomics; it cannot be distributed via conda or pip.\n- CellBender GPU acceleration requires CUDA ≥ 11.0 and a compatible NVIDIA GPU; CPU-only mode is available but slow (hours per sample).\n- Monocle3 has complex Bioconductor dependencies that frequently cause installation conflicts; allocate extra time and follow the official installation guide.\n- Conda environments can be large (2–5 GB each); ensure sufficient disk space before creating them.\n- On HPC clusters, use `module load` for pre-installed tools before attempting conda installation; conda may conflict with system modules.\n- macOS (Apple Silicon) requires `CONDA_SUBDIR=osx-64` for some bioinformatics tools that lack native ARM builds.\n- Common failure cases:\n  - `conda solve` timing out on complex environments; switch to `mamba` for faster resolution.\n  - GATK or Picard failing due to wrong Java version; ensure Java 17+ is available (`java --version`).\n  - R package installation failing due to missing system libraries (e.g., `libgdal`, `libcurl`); install the system library first with `apt-get` or `yum`.\n  - STARsolo requiring a STAR version ≥ 2.7.9a for Velocyto output; check STAR version with `STAR --version`.\n","# Skill: Bioinformatics Environment Setup\n\n## Use When\n\n- User is starting a new analysis and wants to install the required bioinformatics tools.\n- A pipeline step fails because a tool is missing or the wrong version is installed.\n- User asks how to install a specific bioinformatics tool (e.g., STAR, Cell Ranger, Scanpy, Seurat).\n- User wants a ready-to-use conda environment for a specific pipeline.\n- User is setting up a new compute environment (HPC, cloud VM, local workstation).\n\n## Inputs\n\n- Required:\n  - Target pipeline(s): one or more of `ngs-shared`, `wgs`, `rnaseq`, `scrnaseq`, `metagenomics`, or `all`\n- Optional:\n  - Installation method: `conda` (default), `docker`, or `manual`\n  - Operating system: `linux` (default), `macos`\n  - Environment name prefix (default: `bioinfo`)\n  - Conda channel priority: `strict` (default, reproducible) or `flexible`\n  - Whether to verify existing installations before installing (default: true)\n\n## Workflow\n\n1. **Detect the environment**: Check whether `conda`\u002F`mamba` is available (`which conda`), whether Docker is available (`docker --version`), and whether an HPC module system is present (`module avail`). Report findings to the user and recommend the best installation path.\n\n2. **Check existing installations**: For each tool in the requested pipeline group(s), run `which \u003Ctool> && \u003Ctool> --version 2>&1 | head -1` to detect installed versions. Report a summary table: tool name, found\u002Fmissing, installed version, required minimum version.\n\n3. **Select the installation asset**: Choose the appropriate conda environment YAML from `assets\u002Fenvs\u002F`:\n   - `ngs-shared.yaml` — FastQC, MultiQC, fastp, Trimmomatic, samtools\n   - `wgs.yaml` — BWA-MEM2, GATK, Picard, bcftools, VEP, SnpEff\n   - `rnaseq.yaml` — STAR, HISAT2, featureCounts (subread), salmon, kallisto, DESeq2 (R), edgeR (R)\n   - `scrnaseq-python.yaml` — STARsolo (STAR), Scanpy, scVI-tools, scVelo, Scrublet, CellBender, harmonypy\n   - `scrnaseq-r.yaml` — Seurat v5, SingleR, scDblFinder, SoupX, Monocle3, DoubletFinder\n   - `metagenomics.yaml` — Bowtie2, MetaPhlAn4, HUMAnN3, Kraken2, Bracken, metaSPAdes, MEGAHIT, Prokka\n\n4. **Create the conda environment**:\n   ```bash\n   mamba env create -f assets\u002Fenvs\u002F\u003Cpipeline>.yaml\n   # or, if mamba is unavailable:\n   conda env create -f assets\u002Fenvs\u002F\u003Cpipeline>.yaml\n   ```\n   Prefer `mamba` over `conda` for significantly faster dependency resolution.\n\n5. **Handle tools that cannot be installed via conda** — prompt the user with manual steps:\n   - **Cell Ranger**: Download from the 10x Genomics website (requires registration). Add to PATH: `export PATH=\u002Fpath\u002Fto\u002Fcellranger:$PATH`.\n   - **CellBender**: Install via pip inside the conda environment: `pip install cellbender`. Requires CUDA for GPU acceleration.\n   - **DoubletFinder**: Install from GitHub inside R: `remotes::install_github(\"chris-mcginnis-ucsf\u002FDoubletFinder\")`.\n   - **Monocle3**: Install from Bioconductor: `BiocManager::install(\"monocle3\")`. Alternatively: `remotes::install_github(\"cole-trapnell-lab\u002Fmonocle3\")`.\n   - **velocyto** (for RNA velocity loom generation): `pip install velocyto`. Requires `samtools` and a reference GTF.\n\n6. **Verify all installations**: After installation, re-run the version check for each tool. For R packages, run `Rscript -e 'packageVersion(\"\u003Cpkg>\")'`. Report a final verification table: tool, expected version, installed version, status (PASS\u002FFAIL).\n\n7. **Report any failures** with the specific error message and the most likely fix (e.g., missing system library, incompatible CUDA version, wrong conda channel).\n\n## Output Contract\n\n- Environment detection summary (printed to console)\n- Pre-installation version check table (TSV or formatted table): tool, status, version\n- Installation commands executed (echo each command before running)\n- Post-installation verification table (TSV or formatted table): tool, expected_min_version, installed_version, pass\u002Ffail\n- List of any tools that require manual installation steps, with exact instructions\n\n## Limits\n\n- Cell Ranger requires registration and manual download from 10x Genomics; it cannot be distributed via conda or pip.\n- CellBender GPU acceleration requires CUDA ≥ 11.0 and a compatible NVIDIA GPU; CPU-only mode is available but slow (hours per sample).\n- Monocle3 has complex Bioconductor dependencies that frequently cause installation conflicts; allocate extra time and follow the official installation guide.\n- Conda environments can be large (2–5 GB each); ensure sufficient disk space before creating them.\n- On HPC clusters, use `module load` for pre-installed tools before attempting conda installation; conda may conflict with system modules.\n- macOS (Apple Silicon) requires `CONDA_SUBDIR=osx-64` for some bioinformatics tools that lack native ARM builds.\n- Common failure cases:\n  - `conda solve` timing out on complex environments; switch to `mamba` for faster resolution.\n  - GATK or Picard failing due to wrong Java version; ensure Java 17+ is available (`java --version`).\n  - R package installation failing due to missing system libraries (e.g., `libgdal`, `libcurl`); install the system library first with `apt-get` or `yum`.\n  - STARsolo requiring a STAR version ≥ 2.7.9a for Velocyto output; check STAR version with `STAR --version`.\n",{"name":5,"description":7},"main","5118e7fda890e9aa819cb71e003cd243d3a31970","skills\u002Fbioinformatics-env-setup",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 bioinformatics-env-setup",{"tool":44,"command":45},"bunx","bunx skills add Scientific-Tooling\u002Fstructured-intelligence --skill bioinformatics-env-setup",{"tool":47,"command":48},"pnpm","pnpm dlx skills add Scientific-Tooling\u002Fstructured-intelligence --skill bioinformatics-env-setup","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fbioinformatics-env-setup\u002FSKILL.md",true,[52,58,62,67,71,75,79,83,87,91,95,101,105,109,113,117,121,125,129],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"agents\u002Fclaude.yaml","REFERENCE","参考文档",346,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fbioinformatics-env-setup\u002Fagents\u002Fclaude.yaml",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"agents\u002Fopenai.yaml",347,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fbioinformatics-env-setup\u002Fagents\u002Fopenai.yaml",{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":56,"sourceHtmlUrl":66},"assets\u002Fenvs\u002Fmetagenomics.yaml","ASSET","资产文件","https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fbioinformatics-env-setup\u002Fassets\u002Fenvs\u002Fmetagenomics.yaml",{"path":68,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":69,"sourceHtmlUrl":70},"assets\u002Fenvs\u002Fngs-shared.yaml",219,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fbioinformatics-env-setup\u002Fassets\u002Fenvs\u002Fngs-shared.yaml",{"path":72,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":73,"sourceHtmlUrl":74},"assets\u002Fenvs\u002Frnaseq.yaml",447,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fbioinformatics-env-setup\u002Fassets\u002Fenvs\u002Frnaseq.yaml",{"path":76,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":77,"sourceHtmlUrl":78},"assets\u002Fenvs\u002Fscrnaseq-python.yaml",631,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fbioinformatics-env-setup\u002Fassets\u002Fenvs\u002Fscrnaseq-python.yaml",{"path":80,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":81,"sourceHtmlUrl":82},"assets\u002Fenvs\u002Fscrnaseq-r.yaml",849,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fbioinformatics-env-setup\u002Fassets\u002Fenvs\u002Fscrnaseq-r.yaml",{"path":84,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":85,"sourceHtmlUrl":86},"assets\u002Fenvs\u002Fwgs.yaml",273,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fbioinformatics-env-setup\u002Fassets\u002Fenvs\u002Fwgs.yaml",{"path":88,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":89,"sourceHtmlUrl":90},"config.yaml",357,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fbioinformatics-env-setup\u002Fconfig.yaml",{"path":92,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fartifact-contracts.md",9030,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FVideo-Generation\u002F口播成片\u002Freferences\u002Fartifact-contracts.md",{"path":96,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":99,"sourceHtmlUrl":100},"scripts\u002Fanimation_style.cjs","SCRIPT","脚本",1785,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FVideo-Generation\u002F口播成片\u002Fscripts\u002Fanimation_style.cjs",{"path":102,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":103,"sourceHtmlUrl":104},"scripts\u002Fexport_final_video.cjs",7294,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FVideo-Generation\u002F口播成片\u002Fscripts\u002Fexport_final_video.cjs",{"path":106,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":107,"sourceHtmlUrl":108},"scripts\u002Fserve_range_preview.cjs",3665,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FVideo-Generation\u002F口播成片\u002Fscripts\u002Fserve_range_preview.cjs",{"path":110,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":111,"sourceHtmlUrl":112},"scripts\u002Fuser_config.cjs",2363,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FVideo-Generation\u002F口播成片\u002Fscripts\u002Fuser_config.cjs",{"path":114,"resourceType":97,"resourceTypeDesc":98,"sizeBytes":115,"sourceHtmlUrl":116},"scripts\u002Fwrite_render_mode.cjs",3998,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FVideo-Generation\u002F口播成片\u002Fscripts\u002Fwrite_render_mode.cjs",{"path":118,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":119,"sourceHtmlUrl":120},"templates\u002Fstoryboard-audit.html",12916,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FVideo-Generation\u002F口播成片\u002Ftemplates\u002Fstoryboard-audit.html",{"path":122,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":123,"sourceHtmlUrl":124},"templates\u002Ftimeline-preview.html",40958,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FVideo-Generation\u002F口播成片\u002Ftemplates\u002Ftimeline-preview.html",{"path":126,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":127,"sourceHtmlUrl":128},"动画\u002Fstyles.json",343,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FVideo-Generation\u002F口播成片\u002F动画\u002Fstyles.json",{"path":130,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":131,"sourceHtmlUrl":132},"用户配置\u002Fdefault.json",58,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FVideo-Generation\u002F口播成片\u002F用户配置\u002Fdefault.json",[134,162,175,188,202,214],{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":145,"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",[140],{"categoryNo":141,"categoryName":142,"taxonomyType":143,"taxonomyTypeDesc":144},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161],"structured intelligence skill creator","skill creator","intelligence","structured","create","requirements","workflows","provider","update","registry","local","validation","metadata","repository","templates","Rules",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"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",[],[169,170,171,172,173,174],"analysis","stat survival analysis","regression","log","functions","test",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":181,"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",[],[182,183,184,185,186,187],"stat pca","sample","visualize","contributing","data","structure",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":194,"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",[],[195,196,197,198,199,200,201],"stat pairwise correlation","correlation","produce","heatmap","compute","across","tests",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":208,"publishedAt":26},"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",[],[209,210,186,211,183,212,213],"stat nonlinear embedding","visualization","relationships","cell","exploratory visualization",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":220,"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",[],[171,221,222,223,224,225],"stat logistic regression","report","model","outcomes","performance"]