[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DNX5R56HM2PM7ZMHCM7867":3,"skill-same:01M6DNX5R56HM2PM7ZMHCM7867":98},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":79,"commitSha":80,"skillDirectory":5,"forksCount":14,"repositoryHtmlUrl":81,"repositoryHomepageUrl":6,"ownerHtmlUrl":82,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":83,"install":84,"resources":97},"01M6DNX5R56HM2PM7ZMHCM7867","galaxy-bridge",null,"Galaxy tool discovery, intelligent recommendation, and execution — 8,000+ bioinformatics tools from usegalaxy.org with multi-signal scoring and workflow suggestions","huamu668\u002Fclawhub-openclaw-medical","huamu668","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F202473531?v=4","01M6DK1V7D7VP9PJ06Z1VXVK13","huamu","01M6DK1VBYG1BX5FT154AFZHAS",0,"MIT","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fgalaxy-bridge\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"bridge","galaxy bridge","Galaxy","scoring","linux","NGS","tool-discovery","metagenomics","false","workflow","bioinformatics","signal scoring","workflows","github","python3","tool","discovery","api","execution","pipeline","2026-11-10 10:12:30",false,"---\nname: galaxy-bridge\ndescription: \"Galaxy tool discovery, intelligent recommendation, and execution — 8,000+ bioinformatics tools from usegalaxy.org with multi-signal scoring and workflow suggestions\"\nversion: 0.2.0\nauthor: Manuel Corpas\nlicense: MIT\ntags: [galaxy, bioinformatics, tool-discovery, workflows, NGS, genomics, proteomics, metagenomics]\nmetadata:\n  openclaw:\n    requires:\n      bins:\n        - python3\n      env:\n        - GALAXY_URL\n        - GALAXY_API_KEY\n      config: []\n    always: false\n    emoji: \"?\"\n    homepage: https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio\n    os: [macos, linux]\n    install:\n      - kind: pip\n        package: bioblend\n        bins: []\n    trigger_keywords:\n      - galaxy\n      - usegalaxy\n      - tool shed\n      - bioblend\n      - run on galaxy\n      - galaxy tool\n      - galaxy workflow\n      - NGS pipeline\n---\n\n# Galaxy Bridge\n\n**ClawBio's gateway to the Galaxy ecosystem — 1,770+ production bioinformatics tools, discoverable and executable through natural language.**\n\n## Why This Exists\n\nGalaxy (usegalaxy.org) hosts the world's largest collection of curated bioinformatics tools — 1,770+ on the main server alone, covering everything from FASTQ QC to metagenomics to protein structure prediction. But discovering the right tool requires knowing exact tool IDs, navigating nested ToolShed categories, and understanding parameter schemas.\n\nGalaxy Bridge makes these tools **agent-accessible**: search by natural language, execute via CLI, and chain Galaxy tools with ClawBio's local skills for cross-platform workflows that neither system can do alone.\n\n## Core Capabilities\n\n1. **Intelligent tool recommendation** — describe a task in plain English; multi-signal scoring across 7 dimensions returns the best Galaxy tool with explanations\n2. **Workflow suggestions** — 8 pre-defined pipeline templates (RNA-seq DE, metagenomics, variant calling, WES germline, ChIP-seq, nanopore, genome assembly, variant annotation)\n3. **Input format awareness** — provide your file extension (.fastq, .bam, .vcf) for format-aware recommendations\n4. **Version deduplication** — 8,182 catalog entries collapse to ~2,300 unique tools; latest version preferred, version count as maturity signal\n5. **EDAM ontology resolution** — 108 EDAM topic\u002Foperation IDs resolved to human-readable labels for richer matching\n6. **Natural language search** — keyword-based search across 8,000+ Galaxy tools by name, description, section, and EDAM terms\n7. **Remote execution** — run Galaxy tools on usegalaxy.org via BioBlend API\n8. **Category browsing** — explore 86 ToolShed categories with tool counts\n9. **Tool detail inspection** — view inputs, outputs, and parameter schemas\n10. **Offline demo mode** — FastQC demo with pre-cached results (no API key needed)\n11. **Cross-platform chaining** — Galaxy VEP → ClawBio PharmGx, Galaxy Kraken2 → ClawBio metagenomics\n\n## Input Formats\n\n| Format | Extension | Required Fields | Example |\n|--------|-----------|----------------|---------|\n| FASTQ | `.fq`, `.fastq`, `.fq.gz` | Sequence reads | Illumina paired-end reads |\n| VCF | `.vcf`, `.vcf.gz` | Variant calls | Annotated VCF for VEP |\n| BAM | `.bam` | Aligned reads | BWA-MEM2 output |\n| FASTA | `.fa`, `.fasta` | Sequences | Reference genome |\n| Tabular | `.tsv`, `.csv` | Varies by tool | Gene expression matrix |\n\n## Workflow\n\n1. **Search** — User describes what they need → bridge searches local catalog + Galaxy API\n2. **Select** — Ranked results with descriptions, versions, and categories\n3. **Configure** — Show tool inputs\u002Foutputs schema; user provides files and parameters\n4. **Execute** — Upload input to Galaxy, run tool, poll for completion\n5. **Retrieve** — Download outputs to local directory\n6. **Bundle** — Generate reproducibility package (commands.sh, environment.yml, checksums)\n\n## CLI Reference\n\n```bash\n# Intelligent tool recommendation (new in v0.2.0)\npython galaxy_bridge.py --recommend \"quality control on my sequencing reads\"\npython galaxy_bridge.py --recommend \"classify microbial species\" --format .fastq\npython galaxy_bridge.py --recommend \"call variants\" --format .bam\npython galaxy_bridge.py --recommend \"annotate variants from WES\" --format .vcf\n\n# Workflow \u002F pipeline suggestions (new in v0.2.0)\npython galaxy_bridge.py --workflow \"RNA-seq differential expression\"\npython galaxy_bridge.py --workflow \"metagenomics\"\npython galaxy_bridge.py --workflow \"whole exome sequencing\"\n\n# Search for tools by keyword\npython galaxy_bridge.py --search \"metagenomics profiling\"\npython galaxy_bridge.py --search \"variant annotation\"\npython galaxy_bridge.py --search \"RNA-seq differential expression\"\n\n# Browse Galaxy ToolShed categories\npython galaxy_bridge.py --list-categories\n\n# View tool details (inputs, outputs, parameters)\npython galaxy_bridge.py --tool-details toolshed.g2.bx.psu.edu\u002Frepos\u002Fdevteam\u002Ffastqc\u002Ffastqc\u002F0.74+galaxy1\n\n# Run a tool on Galaxy (requires GALAXY_API_KEY)\npython galaxy_bridge.py --run fastqc --input reads.fq.gz --output \u002Ftmp\u002Fqc_results\n\n# Demo mode (works offline, no API key needed)\npython galaxy_bridge.py --demo\n```\n\n## Recommendation Engine\n\nThe `--recommend` flag uses **multi-signal scoring** across 7 dimensions to rank tools:\n\n| Signal | Max Points | Description |\n|--------|-----------|-------------|\n| Section match | 30 | Tool's Galaxy category matches the detected task |\n| Preferred tool | 20 | Tool is a known best-in-class for the task |\n| Exact name match | 15 | Tool name appears in the query |\n| Keyword match | 15 | Query words found in tool name\u002Fdescription |\n| EDAM ontology | 10 | EDAM topic\u002Foperation IDs match the task |\n| Format compatibility | 10 | Tool accepts the specified input format |\n| Version maturity | 5 | Tools with more versions score higher (log scale) |\n\n**15 task categories** are recognised: Quality Control, Read Mapping, Variant Calling, Variant Annotation, WES\u002FWGS, RNA-seq, Metagenomics, Genome Assembly, Genome Annotation, Phylogenetics, ChIP-seq, Single-cell, Proteomics, Nanopore, BAM Processing.\n\n**8 workflow templates**: WES Germline, WES Annotation, RNA-seq DE, Metagenomics Profiling, Variant Calling, ChIP-seq, Nanopore Assembly, Genome Assembly.\n\n## Demo\n\nRunning `--demo` executes a simulated FastQC analysis using pre-cached results:\n\n```\n$ python galaxy_bridge.py --demo\n\nGalaxy Bridge — Demo Mode (offline)\n====================================\nTool: FastQC v0.74+galaxy1\nInput: demo\u002Fdemo_reads.fq (bundled synthetic FASTQ, 1000 reads)\nOutput: demo\u002Ffastqc_demo_output.html\n\nResult: PASS — Per base sequence quality ✓\n        PASS — Per sequence quality scores ✓\n        WARN — Per base sequence content (normal for Illumina)\n        PASS — Sequence length distribution ✓\n\nReproducibility bundle written to demo\u002Freproducibility\u002F\n```\n\n## Galaxy Tool Categories\n\nThe bridge indexes tools across all 56 Galaxy ToolShed categories, including:\n\n- **Sequence Analysis** (~30 tools): FastQC, Trimmomatic, Cutadapt, fastp\n- **Metagenomics** (~25 tools): Kraken2, MetaPhlAn, HUMAnN, QIIME2\n- **Variant Analysis** (~25 tools): VEP, SnpSift, BCFtools, FreeBayes\n- **RNA** (~20 tools): HISAT2, StringTie, featureCounts, DESeq2\n- **Proteomics** (~15 tools): MaxQuant, SearchGUI, PeptideShaker\n- **Phylogenetics** (~15 tools): IQ-TREE, RAxML, MAFFT, MUSCLE\n- **Genome Annotation** (~15 tools): Prokka, Augustus, MAKER\n- **Assembly** (~15 tools): SPAdes, Flye, Unicycler, MEGAHIT\n- **Single Cell** (~10 tools): Scanpy, CellRanger, Seurat\n- **ChIP-seq\u002FEpigenetics** (~10 tools): MACS2, deepTools, DiffBind\n- **GWAS** (~10 tools): PLINK, REGENIE, BOLT-LMM\n- **Nanopore** (~10 tools): NanoPlot, Medaka, minimap2\n\n## Output Structure\n\n```\noutput_dir\u002F\n├── report.md              # Analysis summary with methods and results\n├── result.json            # Machine-readable: tool ID, version, parameters, output paths\n├── galaxy_outputs\u002F        # Raw outputs downloaded from Galaxy\n│   ├── fastqc_report.html\n│   └── ...\n└── reproducibility\u002F\n    ├── commands.sh        # Galaxy API calls to reproduce\n    ├── environment.yml    # Tool versions and Galaxy server info\n    └── checksums.sha256   # SHA-256 of all inputs and outputs\n```\n\n## Dependencies\n\n**Required:**\n- Python 3.9+\n- bioblend (Galaxy Python SDK)\n\n**Optional (for execution):**\n- `GALAXY_URL` environment variable (default: `https:\u002F\u002Fusegalaxy.org`)\n- `GALAXY_API_KEY` environment variable (register at usegalaxy.org)\n\n## Safety\n\n- **Local-first search**: Tool discovery uses the bundled `galaxy_catalog.json` — no API calls needed\n- **API key optional**: Demo mode and search work without credentials\n- **No data retention**: Uploaded files are deleted from Galaxy after output retrieval\n- **Reproducibility**: Every execution generates a full provenance bundle\n- **Disclaimer**: ClawBio is a research and educational tool. It is not a medical device and does not provide clinical diagnoses. Consult a healthcare professional before making any medical decisions.\n\n## Integration with Bio Orchestrator\n\n**Triggers when**: User mentions \"galaxy\", \"usegalaxy\", \"tool shed\", \"run on galaxy\", \"NGS pipeline\", or references a Galaxy tool ID.\n\n**Chaining partners**:\n- `pharmgx-reporter` — Galaxy VEP annotates variants → PharmGx generates dosage report\n- `claw-metagenomics` — Galaxy Kraken2 → ClawBio metagenomics profiling\n- `equity-scorer` — Galaxy VCF processing → HEIM equity scoring\n- `vcf-annotator` — Galaxy VEP\u002FSnpSift ↔ ClawBio annotation\n\n## Citations\n\n- [Galaxy Project](https:\u002F\u002Fgalaxyproject.org\u002F) — Afgan et al. (2018) Nucleic Acids Research\n- [BioBlend](https:\u002F\u002Fbioblend.readthedocs.io\u002F) — Sloggett et al. (2013) Bioinformatics\n- [usegalaxy.org](https:\u002F\u002Fusegalaxy.org\u002F) — Main Galaxy public server\n- [Galaxy ToolShed](https:\u002F\u002Ftoolshed.g2.bx.psu.edu\u002F) — Community tool repository\n","# Galaxy Bridge\n\n**ClawBio's gateway to the Galaxy ecosystem — 1,770+ production bioinformatics tools, discoverable and executable through natural language.**\n\n## Why This Exists\n\nGalaxy (usegalaxy.org) hosts the world's largest collection of curated bioinformatics tools — 1,770+ on the main server alone, covering everything from FASTQ QC to metagenomics to protein structure prediction. But discovering the right tool requires knowing exact tool IDs, navigating nested ToolShed categories, and understanding parameter schemas.\n\nGalaxy Bridge makes these tools **agent-accessible**: search by natural language, execute via CLI, and chain Galaxy tools with ClawBio's local skills for cross-platform workflows that neither system can do alone.\n\n## Core Capabilities\n\n1. **Intelligent tool recommendation** — describe a task in plain English; multi-signal scoring across 7 dimensions returns the best Galaxy tool with explanations\n2. **Workflow suggestions** — 8 pre-defined pipeline templates (RNA-seq DE, metagenomics, variant calling, WES germline, ChIP-seq, nanopore, genome assembly, variant annotation)\n3. **Input format awareness** — provide your file extension (.fastq, .bam, .vcf) for format-aware recommendations\n4. **Version deduplication** — 8,182 catalog entries collapse to ~2,300 unique tools; latest version preferred, version count as maturity signal\n5. **EDAM ontology resolution** — 108 EDAM topic\u002Foperation IDs resolved to human-readable labels for richer matching\n6. **Natural language search** — keyword-based search across 8,000+ Galaxy tools by name, description, section, and EDAM terms\n7. **Remote execution** — run Galaxy tools on usegalaxy.org via BioBlend API\n8. **Category browsing** — explore 86 ToolShed categories with tool counts\n9. **Tool detail inspection** — view inputs, outputs, and parameter schemas\n10. **Offline demo mode** — FastQC demo with pre-cached results (no API key needed)\n11. **Cross-platform chaining** — Galaxy VEP → ClawBio PharmGx, Galaxy Kraken2 → ClawBio metagenomics\n\n## Input Formats\n\n| Format | Extension | Required Fields | Example |\n|--------|-----------|----------------|---------|\n| FASTQ | `.fq`, `.fastq`, `.fq.gz` | Sequence reads | Illumina paired-end reads |\n| VCF | `.vcf`, `.vcf.gz` | Variant calls | Annotated VCF for VEP |\n| BAM | `.bam` | Aligned reads | BWA-MEM2 output |\n| FASTA | `.fa`, `.fasta` | Sequences | Reference genome |\n| Tabular | `.tsv`, `.csv` | Varies by tool | Gene expression matrix |\n\n## Workflow\n\n1. **Search** — User describes what they need → bridge searches local catalog + Galaxy API\n2. **Select** — Ranked results with descriptions, versions, and categories\n3. **Configure** — Show tool inputs\u002Foutputs schema; user provides files and parameters\n4. **Execute** — Upload input to Galaxy, run tool, poll for completion\n5. **Retrieve** — Download outputs to local directory\n6. **Bundle** — Generate reproducibility package (commands.sh, environment.yml, checksums)\n\n## CLI Reference\n\n```bash\n# Intelligent tool recommendation (new in v0.2.0)\npython galaxy_bridge.py --recommend \"quality control on my sequencing reads\"\npython galaxy_bridge.py --recommend \"classify microbial species\" --format .fastq\npython galaxy_bridge.py --recommend \"call variants\" --format .bam\npython galaxy_bridge.py --recommend \"annotate variants from WES\" --format .vcf\n\n# Workflow \u002F pipeline suggestions (new in v0.2.0)\npython galaxy_bridge.py --workflow \"RNA-seq differential expression\"\npython galaxy_bridge.py --workflow \"metagenomics\"\npython galaxy_bridge.py --workflow \"whole exome sequencing\"\n\n# Search for tools by keyword\npython galaxy_bridge.py --search \"metagenomics profiling\"\npython galaxy_bridge.py --search \"variant annotation\"\npython galaxy_bridge.py --search \"RNA-seq differential expression\"\n\n# Browse Galaxy ToolShed categories\npython galaxy_bridge.py --list-categories\n\n# View tool details (inputs, outputs, parameters)\npython galaxy_bridge.py --tool-details toolshed.g2.bx.psu.edu\u002Frepos\u002Fdevteam\u002Ffastqc\u002Ffastqc\u002F0.74+galaxy1\n\n# Run a tool on Galaxy (requires GALAXY_API_KEY)\npython galaxy_bridge.py --run fastqc --input reads.fq.gz --output \u002Ftmp\u002Fqc_results\n\n# Demo mode (works offline, no API key needed)\npython galaxy_bridge.py --demo\n```\n\n## Recommendation Engine\n\nThe `--recommend` flag uses **multi-signal scoring** across 7 dimensions to rank tools:\n\n| Signal | Max Points | Description |\n|--------|-----------|-------------|\n| Section match | 30 | Tool's Galaxy category matches the detected task |\n| Preferred tool | 20 | Tool is a known best-in-class for the task |\n| Exact name match | 15 | Tool name appears in the query |\n| Keyword match | 15 | Query words found in tool name\u002Fdescription |\n| EDAM ontology | 10 | EDAM topic\u002Foperation IDs match the task |\n| Format compatibility | 10 | Tool accepts the specified input format |\n| Version maturity | 5 | Tools with more versions score higher (log scale) |\n\n**15 task categories** are recognised: Quality Control, Read Mapping, Variant Calling, Variant Annotation, WES\u002FWGS, RNA-seq, Metagenomics, Genome Assembly, Genome Annotation, Phylogenetics, ChIP-seq, Single-cell, Proteomics, Nanopore, BAM Processing.\n\n**8 workflow templates**: WES Germline, WES Annotation, RNA-seq DE, Metagenomics Profiling, Variant Calling, ChIP-seq, Nanopore Assembly, Genome Assembly.\n\n## Demo\n\nRunning `--demo` executes a simulated FastQC analysis using pre-cached results:\n\n```\n$ python galaxy_bridge.py --demo\n\nGalaxy Bridge — Demo Mode (offline)\n====================================\nTool: FastQC v0.74+galaxy1\nInput: demo\u002Fdemo_reads.fq (bundled synthetic FASTQ, 1000 reads)\nOutput: demo\u002Ffastqc_demo_output.html\n\nResult: PASS — Per base sequence quality ✓\n        PASS — Per sequence quality scores ✓\n        WARN — Per base sequence content (normal for Illumina)\n        PASS — Sequence length distribution ✓\n\nReproducibility bundle written to demo\u002Freproducibility\u002F\n```\n\n## Galaxy Tool Categories\n\nThe bridge indexes tools across all 56 Galaxy ToolShed categories, including:\n\n- **Sequence Analysis** (~30 tools): FastQC, Trimmomatic, Cutadapt, fastp\n- **Metagenomics** (~25 tools): Kraken2, MetaPhlAn, HUMAnN, QIIME2\n- **Variant Analysis** (~25 tools): VEP, SnpSift, BCFtools, FreeBayes\n- **RNA** (~20 tools): HISAT2, StringTie, featureCounts, DESeq2\n- **Proteomics** (~15 tools): MaxQuant, SearchGUI, PeptideShaker\n- **Phylogenetics** (~15 tools): IQ-TREE, RAxML, MAFFT, MUSCLE\n- **Genome Annotation** (~15 tools): Prokka, Augustus, MAKER\n- **Assembly** (~15 tools): SPAdes, Flye, Unicycler, MEGAHIT\n- **Single Cell** (~10 tools): Scanpy, CellRanger, Seurat\n- **ChIP-seq\u002FEpigenetics** (~10 tools): MACS2, deepTools, DiffBind\n- **GWAS** (~10 tools): PLINK, REGENIE, BOLT-LMM\n- **Nanopore** (~10 tools): NanoPlot, Medaka, minimap2\n\n## Output Structure\n\n```\noutput_dir\u002F\n├── report.md              # Analysis summary with methods and results\n├── result.json            # Machine-readable: tool ID, version, parameters, output paths\n├── galaxy_outputs\u002F        # Raw outputs downloaded from Galaxy\n│   ├── fastqc_report.html\n│   └── ...\n└── reproducibility\u002F\n    ├── commands.sh        # Galaxy API calls to reproduce\n    ├── environment.yml    # Tool versions and Galaxy server info\n    └── checksums.sha256   # SHA-256 of all inputs and outputs\n```\n\n## Dependencies\n\n**Required:**\n- Python 3.9+\n- bioblend (Galaxy Python SDK)\n\n**Optional (for execution):**\n- `GALAXY_URL` environment variable (default: `https:\u002F\u002Fusegalaxy.org`)\n- `GALAXY_API_KEY` environment variable (register at usegalaxy.org)\n\n## Safety\n\n- **Local-first search**: Tool discovery uses the bundled `galaxy_catalog.json` — no API calls needed\n- **API key optional**: Demo mode and search work without credentials\n- **No data retention**: Uploaded files are deleted from Galaxy after output retrieval\n- **Reproducibility**: Every execution generates a full provenance bundle\n- **Disclaimer**: ClawBio is a research and educational tool. It is not a medical device and does not provide clinical diagnoses. Consult a healthcare professional before making any medical decisions.\n\n## Integration with Bio Orchestrator\n\n**Triggers when**: User mentions \"galaxy\", \"usegalaxy\", \"tool shed\", \"run on galaxy\", \"NGS pipeline\", or references a Galaxy tool ID.\n\n**Chaining partners**:\n- `pharmgx-reporter` — Galaxy VEP annotates variants → PharmGx generates dosage report\n- `claw-metagenomics` — Galaxy Kraken2 → ClawBio metagenomics profiling\n- `equity-scorer` — Galaxy VCF processing → HEIM equity scoring\n- `vcf-annotator` — Galaxy VEP\u002FSnpSift ↔ ClawBio annotation\n\n## Citations\n\n- [Galaxy Project](https:\u002F\u002Fgalaxyproject.org\u002F) — Afgan et al. (2018) Nucleic Acids Research\n- [BioBlend](https:\u002F\u002Fbioblend.readthedocs.io\u002F) — Sloggett et al. (2013) Bioinformatics\n- [usegalaxy.org](https:\u002F\u002Fusegalaxy.org\u002F) — Main Galaxy public server\n- [Galaxy ToolShed](https:\u002F\u002Ftoolshed.g2.bx.psu.edu\u002F) — Community tool repository\n",{"name":5,"tags":49,"author":53,"license":15,"version":54,"metadata":55,"description":7},[50,34,30,36,29,51,52,31],"galaxy","genomics","proteomics","Manuel Corpas","0.2.0",{"openclaw":56},{"os":57,"emoji":59,"always":45,"install":60,"homepage":65,"requires":66,"trigger_keywords":72},[58,28],"macos","?",[61],{"bins":62,"kind":63,"package":64},[],"pip","bioblend","https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio",{"env":67,"bins":70,"config":71},[68,69],"GALAXY_URL","GALAXY_API_KEY",[38],[],[50,73,74,64,75,76,77,78],"usegalaxy","tool shed","run on galaxy","galaxy tool","galaxy workflow","NGS pipeline","main","d3998984163a67a891ee8397e35adf79b14e872d","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical","https:\u002F\u002Fgithub.com\u002Fhuamu668","2026-03-12 11:49:42",{"source":8,"skillName":5,"commands":85,"prompt":95,"zipAvailable":96},[86,89,92],{"tool":87,"command":88},"npx","npx skills add huamu668\u002Fclawhub-openclaw-medical --skill galaxy-bridge",{"tool":90,"command":91},"bunx","bunx skills add huamu668\u002Fclawhub-openclaw-medical --skill galaxy-bridge",{"tool":93,"command":94},"pnpm","pnpm dlx skills add huamu668\u002Fclawhub-openclaw-medical --skill galaxy-bridge","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fgalaxy-bridge\u002FSKILL.md",true,[],[99,119,148,168,181,210],{"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":44},"01M6DR3JGAEX5G5FR7TK3D8NS8","zarr-python","Chunked N-D arrays for cloud storage. Compressed arrays, parallel I\u002FO, S3\u002FGCS integration, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fzarr-python\u002FSKILL.md",[],[106,107,108,109,110,111,112,113,114,115,116,117,118],"python","zarr python","storage","scientific computing","numpy","arrays","pipelines","parallel","dask","cloud","gcs","s3","integration",{"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":128,"publishedAt":44},"01M6DR101MEDE5XT2ZZ5VBEAA5","vaex","Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV\u002FHDF5\u002FArrow\u002FParquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fvaex\u002FSKILL.md",[125],{"categoryNo":126,"categoryName":127,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[121,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147],"machine learning","in memory","learning","csv","visualization","create","core","ml","big data","memory","visualizations","fit","statistics","do","build","files","use","operations","work",{"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":44},"01M6DQVMB0GBKF2W44FKXVD1P7","torch-geometric","Graph Neural Networks (PyG). Node\u002Fgraph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Ftorch-geometric\u002FSKILL.md",[],[155,131,156,157,158,159,160,161,162,163,164,165,166,167],"torch geometric","node","Neural","link","gat","molecular","graphs","deep","networks","graph","neural networks","deep learning","classification",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":174,"publishedAt":44},"01M6DQH2GZPZKEQ140GRCJ9746","tiledbvcf","Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF\u002FBCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for population genomics.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Ftiledbvcf\u002FSKILL.md",[],[170,175,51,176,177,178,179,113,180,108],"data","sample","queries","ingestion","export","capabilities",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":195,"publishedAt":44},"01M6DQD9G958EM6NHJ994D0SK1","solublempnn","Solubility-optimized protein sequence design using SolubleMPNN. Use this skill when: (1) Designing for E. coli expression, (2) Optimizing solubility of designed proteins, (3) Reducing aggregation propensity, (4) Need high-yield expression, (5) Avoiding inclusion body formation.\nFor standard design, use proteinmpnn. For ligand-aware design, use ligandmpnn.","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fsolublempnn\u002FSKILL.md",[187,190],{"categoryNo":188,"categoryName":189,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":191,"categoryName":192,"taxonomyType":193,"taxonomyTypeDesc":194},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[183,196,197,145,198,199,200,201,202,203,204,205,206,207,208,209],"inclusion","yield","modal","Tools","aggregation","design","proteins","solubility","proteinmpnn","ligandmpnn","ligand-aware","inverse-folding","expression","sequence-design",{"skillNo":211,"name":212,"nameZh":6,"description":213,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":214,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":217,"publishedAt":44},"01M6DQ8W91A93MGGCEEW949HBC","scvelo","RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced\u002Fspliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy\u002FscVI-tools for trajectory inference.","BSD-3-Clause","https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fscvelo\u002FSKILL.md",[],[212,218,219,220,221,222,223,224,225,226,227,199,175,228,229],"RNA","single-cell","infer","cell","transitions","time","compute","velocity","scanpy","analysis","state","inference"]