[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DNJ6BDDXY3J81PSK658EC4":3,"skill-same:01M6DNJ6BDDXY3J81PSK658EC4":221},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":105,"commitSha":106,"skillDirectory":5,"forksCount":14,"repositoryHtmlUrl":107,"repositoryHomepageUrl":6,"ownerHtmlUrl":108,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":109,"install":110,"resources":123},"01M6DNJ6BDDXY3J81PSK658EC4","claw-metagenomics",null,"Shotgun metagenomics profiling — taxonomy, resistome, and functional pathways","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\u002Fclaw-metagenomics\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"claw","claw metagenomics","end","PDF","WHO-critical-ARGs","functional-profiling","antimicrobial-resistance","metagenomics","fq","critical","chart","pandas","scipy","reproducibility","environment","taxonomy","classification","seaborn","biopython","file","2026-11-10 10:12:30",false,"---\nname: claw-metagenomics\nversion: 0.1.0\ndescription: Shotgun metagenomics profiling — taxonomy, resistome, and functional pathways\nauthor: Manuel Corpas\nlicense: MIT\ntags:\n  - metagenomics\n  - antimicrobial-resistance\n  - taxonomy\n  - functional-profiling\n  - environmental\n  - WHO-critical-ARGs\ninputs:\n  - name: r1\n    type: file\n    format: [fastq, fastq.gz, fq, fq.gz]\n    description: Forward reads (paired-end FASTQ R1)\n  - name: r2\n    type: file\n    format: [fastq, fastq.gz, fq, fq.gz]\n    description: Reverse reads (paired-end FASTQ R2)\n  - name: input\n    type: file\n    format: [fastq, fastq.gz, fq, fq.gz]\n    description: Single concatenated or interleaved FASTQ (alternative to R1+R2)\noutputs:\n  - name: taxonomy_report\n    type: file\n    format: tsv\n    description: Bracken-adjusted species-level taxonomy abundance table\n  - name: resistome_profile\n    type: file\n    format: tsv\n    description: RGI\u002FCARD antimicrobial resistance gene hits with WHO priority classification\n  - name: functional_pathways\n    type: file\n    format: tsv\n    description: HUMAnN3 pathway abundance table (MetaCyc\u002FUniRef)\n  - name: figures\n    type: directory\n    format: [png, pdf]\n    description: Publication-quality figures (taxonomy bar chart, resistome heatmap, WHO-critical ARG summary)\n  - name: reproducibility\n    type: directory\n    description: commands.sh, environment.yml, checksums.sha256\nmetadata:\n  openclaw:\n    category: bioinformatics\n    homepage: https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio\n    min_python: \"3.9\"\n    dependencies:\n      - pandas\n      - numpy\n      - matplotlib\n      - seaborn\n      - scipy\n      - biopython\n    system_dependencies:\n      - kraken2\n      - bracken\n      - rgi\n      - humann\n---\n\n# Shotgun Metagenomics Profiler\n\nComprehensive shotgun metagenomics analysis combining taxonomic classification, antimicrobial resistance gene detection, and functional pathway profiling from paired-end FASTQ files.\n\n## What it does\n\n1. Takes paired-end FASTQ files (R1, R2) or a single concatenated FASTQ as input\n2. Runs **Kraken2** taxonomic classification against a standard database (e.g., Standard-8, PlusPF)\n3. Refines abundances with **Bracken** at species level (read re-estimation)\n4. Detects antimicrobial resistance genes with **RGI** against the **CARD** database\n5. Classifies detected ARGs by **WHO critical priority pathogen** association\n6. Optionally runs **HUMAnN3** for functional pathway profiling (MetaCyc + UniRef)\n7. Generates three publication-quality figures:\n   - **Figure 1**: Taxonomy bar chart — top 20 species by relative abundance\n   - **Figure 2**: Resistome heatmap — ARG families by drug class with abundance\n   - **Figure 3**: WHO-critical ARG summary — priority-tier breakdown of detected resistance genes\n8. Produces a full reproducibility bundle (commands.sh, environment.yml, checksums.sha256)\n\n## Why this exists\n\nIf you ask a general AI to \"analyse a metagenome,\" it will:\n- Not know which Kraken2 database to use or how to set confidence thresholds\n- Hallucinate Bracken parameters for read-length and taxonomic level\n- Miss the connection between detected ARGs and WHO priority pathogen lists\n- Skip HUMAnN3 entirely (or misconfigure its database paths)\n- Produce a single bar chart with no resistance context\n- Not provide a reproducibility bundle\n\nThis skill encodes the correct methodological decisions:\n- Kraken2 confidence threshold of 0.2 (reduces false positives in environmental samples)\n- Bracken re-estimation at species level with minimum 10 reads\n- RGI MAIN with \"Perfect\" and \"Strict\" hit criteria only (no \"Loose\" hits)\n- WHO Critical Priority Pathogen list mapped to detected ARG families\n- HUMAnN3 with MetaCyc stratification for pathway-level functional context\n- Thread count auto-detected from available CPUs\n- Full reproducibility bundle for every run\n\n## Validated On\n\nThe skill works with any shotgun metagenome but has been validated on:\n- **Peru sewage metagenomics study** (6 samples, 3 collection sites: Lima, Cusco, Iquitos)\n- Environmental sewage samples with mixed microbial communities\n- Read depths ranging from 2M to 15M paired-end reads per sample\n\n## WHO-Critical ARG Detection\n\nA key feature is the classification of detected resistance genes by WHO priority tier:\n\n| Priority | Pathogen | Resistance |\n|----------|----------|------------|\n| Critical | *Acinetobacter baumannii* | Carbapenem-resistant |\n| Critical | *Pseudomonas aeruginosa* | Carbapenem-resistant |\n| Critical | *Enterobacteriaceae* | Carbapenem-resistant, 3rd-gen cephalosporin-resistant |\n| High | *Enterococcus faecium* | Vancomycin-resistant |\n| High | *Staphylococcus aureus* | Methicillin-resistant, vancomycin-resistant |\n| High | *Helicobacter pylori* | Clarithromycin-resistant |\n| High | *Campylobacter* | Fluoroquinolone-resistant |\n| High | *Salmonella* spp. | Fluoroquinolone-resistant |\n| High | *Neisseria gonorrhoeae* | 3rd-gen cephalosporin-resistant, fluoroquinolone-resistant |\n| Medium | *Streptococcus pneumoniae* | Penicillin-non-susceptible |\n| Medium | *Haemophilus influenzae* | Ampicillin-resistant |\n| Medium | *Shigella* spp. | Fluoroquinolone-resistant |\n\n## Usage\n\n```bash\n# Full pipeline (taxonomy + resistome + functional)\npython metagenomics_profiler.py \\\n    --r1 sample_R1.fastq.gz \\\n    --r2 sample_R2.fastq.gz \\\n    --output metagenomics_report\n\n# Skip HUMAnN3 (faster — taxonomy + resistome only)\npython metagenomics_profiler.py \\\n    --r1 sample_R1.fastq.gz \\\n    --r2 sample_R2.fastq.gz \\\n    --output metagenomics_report \\\n    --skip-functional\n\n# Single concatenated FASTQ\npython metagenomics_profiler.py \\\n    --input combined.fastq.gz \\\n    --output metagenomics_report\n\n# Specify Kraken2 database path\npython metagenomics_profiler.py \\\n    --r1 sample_R1.fastq.gz \\\n    --r2 sample_R2.fastq.gz \\\n    --output metagenomics_report \\\n    --kraken2-db \u002Fpath\u002Fto\u002Fkraken2_db \\\n    --read-length 150\n```\n\n### Demo (works out of the box)\n\n```bash\npython metagenomics_profiler.py --demo --output demo_report\n```\n\nThe demo uses pre-computed results from the Peru sewage metagenomics study (6 samples, 3 sites) and generates all figures and reports instantly without requiring external tools.\n\n## Example Output\n\n```\nMetagenomics Profiler — ClawBio\n================================\nMode: demo (pre-computed Peru sewage data)\nSamples: 6 (3 sites: Lima, Cusco, Iquitos)\n\nTaxonomy (Kraken2 + Bracken):\n  Total classified: 94.2%\n  Top species: Escherichia coli (12.3%), Klebsiella pneumoniae (8.7%),\n               Pseudomonas aeruginosa (5.1%), Acinetobacter baumannii (3.9%)\n\nResistome (RGI\u002FCARD):\n  Total ARG hits: 247 (Perfect: 89, Strict: 158)\n  Drug classes: 14\n  WHO-Critical ARGs detected: 23\n    - Carbapenem resistance: NDM-1, OXA-48, KPC-3\n    - 3rd-gen cephalosporin resistance: CTX-M-15, CTX-M-27\n\nFunctional Pathways (HUMAnN3):\n  Total pathways: 312\n  Top: PWY-7219 (adenosine ribonucleotides de novo biosynthesis)\n\nFigures saved to: demo_report\u002Ffigures\u002F\n  taxonomy_barplot.png (300 dpi)\n  resistome_heatmap.png (300 dpi)\n  who_critical_args.png (300 dpi)\n\nReproducibility:\n  commands.sh | environment.yml | checksums.sha256\n```\n\n## Pipeline Architecture\n\n```\nFASTQ R1 + R2\n     |\n     v\n[Kraken2] --> kraken2_report.txt\n     |\n     v\n[Bracken] --> bracken_species.tsv   --> Figure 1: Taxonomy bar chart\n     |\n     v\n[RGI MAIN] --> rgi_results.txt      --> Figure 2: Resistome heatmap\n     |                                --> Figure 3: WHO-critical ARG summary\n     v\n[HUMAnN3] --> pathabundance.tsv     (optional, --skip-functional to omit)\n     |\n     v\n[Report] --> report.md + figures\u002F + reproducibility\u002F\n```\n\n## Database Requirements\n\n| Tool | Database | Size | Notes |\n|------|----------|------|-------|\n| Kraken2 | Standard-8 or PlusPF | 8-70 GB | Set via `--kraken2-db` or `$KRAKEN2_DB` |\n| Bracken | (built from Kraken2 DB) | included | Read-length specific (default: 150 bp) |\n| RGI | CARD | ~500 MB | Auto-downloaded via `rgi auto_load` |\n| HUMAnN3 | ChocoPhlAn + UniRef90 | ~15 GB | Set via `--humann-db` or `$HUMANN_DB` |\n\n## Citations\n\nIf you use this skill in a publication, please cite:\n\n- Wood, D.E., Lu, J. & Langmead, B. (2019). Improved metagenomic analysis with Kraken 2. Genome Biology, 20, 257.\n- Lu, J. et al. (2017). Bracken: estimating species abundance in metagenomics data. PeerJ Computer Science, 3, e104.\n- Alcock, B.P. et al. (2023). CARD 2023: expanded curation, support for machine learning, and resistome prediction at the Comprehensive Antibiotic Resistance Database. Nucleic Acids Research, 51(D1), D419-D430.\n- Beghini, F. et al. (2021). Integrating taxonomic, functional, and strain-level profiling of diverse microbial communities with bioBakery 3. eLife, 10, e65088.\n- Corpas, M. (2026). ClawBio. https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio\n","# Shotgun Metagenomics Profiler\n\nComprehensive shotgun metagenomics analysis combining taxonomic classification, antimicrobial resistance gene detection, and functional pathway profiling from paired-end FASTQ files.\n\n## What it does\n\n1. Takes paired-end FASTQ files (R1, R2) or a single concatenated FASTQ as input\n2. Runs **Kraken2** taxonomic classification against a standard database (e.g., Standard-8, PlusPF)\n3. Refines abundances with **Bracken** at species level (read re-estimation)\n4. Detects antimicrobial resistance genes with **RGI** against the **CARD** database\n5. Classifies detected ARGs by **WHO critical priority pathogen** association\n6. Optionally runs **HUMAnN3** for functional pathway profiling (MetaCyc + UniRef)\n7. Generates three publication-quality figures:\n   - **Figure 1**: Taxonomy bar chart — top 20 species by relative abundance\n   - **Figure 2**: Resistome heatmap — ARG families by drug class with abundance\n   - **Figure 3**: WHO-critical ARG summary — priority-tier breakdown of detected resistance genes\n8. Produces a full reproducibility bundle (commands.sh, environment.yml, checksums.sha256)\n\n## Why this exists\n\nIf you ask a general AI to \"analyse a metagenome,\" it will:\n- Not know which Kraken2 database to use or how to set confidence thresholds\n- Hallucinate Bracken parameters for read-length and taxonomic level\n- Miss the connection between detected ARGs and WHO priority pathogen lists\n- Skip HUMAnN3 entirely (or misconfigure its database paths)\n- Produce a single bar chart with no resistance context\n- Not provide a reproducibility bundle\n\nThis skill encodes the correct methodological decisions:\n- Kraken2 confidence threshold of 0.2 (reduces false positives in environmental samples)\n- Bracken re-estimation at species level with minimum 10 reads\n- RGI MAIN with \"Perfect\" and \"Strict\" hit criteria only (no \"Loose\" hits)\n- WHO Critical Priority Pathogen list mapped to detected ARG families\n- HUMAnN3 with MetaCyc stratification for pathway-level functional context\n- Thread count auto-detected from available CPUs\n- Full reproducibility bundle for every run\n\n## Validated On\n\nThe skill works with any shotgun metagenome but has been validated on:\n- **Peru sewage metagenomics study** (6 samples, 3 collection sites: Lima, Cusco, Iquitos)\n- Environmental sewage samples with mixed microbial communities\n- Read depths ranging from 2M to 15M paired-end reads per sample\n\n## WHO-Critical ARG Detection\n\nA key feature is the classification of detected resistance genes by WHO priority tier:\n\n| Priority | Pathogen | Resistance |\n|----------|----------|------------|\n| Critical | *Acinetobacter baumannii* | Carbapenem-resistant |\n| Critical | *Pseudomonas aeruginosa* | Carbapenem-resistant |\n| Critical | *Enterobacteriaceae* | Carbapenem-resistant, 3rd-gen cephalosporin-resistant |\n| High | *Enterococcus faecium* | Vancomycin-resistant |\n| High | *Staphylococcus aureus* | Methicillin-resistant, vancomycin-resistant |\n| High | *Helicobacter pylori* | Clarithromycin-resistant |\n| High | *Campylobacter* | Fluoroquinolone-resistant |\n| High | *Salmonella* spp. | Fluoroquinolone-resistant |\n| High | *Neisseria gonorrhoeae* | 3rd-gen cephalosporin-resistant, fluoroquinolone-resistant |\n| Medium | *Streptococcus pneumoniae* | Penicillin-non-susceptible |\n| Medium | *Haemophilus influenzae* | Ampicillin-resistant |\n| Medium | *Shigella* spp. | Fluoroquinolone-resistant |\n\n## Usage\n\n```bash\n# Full pipeline (taxonomy + resistome + functional)\npython metagenomics_profiler.py \\\n    --r1 sample_R1.fastq.gz \\\n    --r2 sample_R2.fastq.gz \\\n    --output metagenomics_report\n\n# Skip HUMAnN3 (faster — taxonomy + resistome only)\npython metagenomics_profiler.py \\\n    --r1 sample_R1.fastq.gz \\\n    --r2 sample_R2.fastq.gz \\\n    --output metagenomics_report \\\n    --skip-functional\n\n# Single concatenated FASTQ\npython metagenomics_profiler.py \\\n    --input combined.fastq.gz \\\n    --output metagenomics_report\n\n# Specify Kraken2 database path\npython metagenomics_profiler.py \\\n    --r1 sample_R1.fastq.gz \\\n    --r2 sample_R2.fastq.gz \\\n    --output metagenomics_report \\\n    --kraken2-db \u002Fpath\u002Fto\u002Fkraken2_db \\\n    --read-length 150\n```\n\n### Demo (works out of the box)\n\n```bash\npython metagenomics_profiler.py --demo --output demo_report\n```\n\nThe demo uses pre-computed results from the Peru sewage metagenomics study (6 samples, 3 sites) and generates all figures and reports instantly without requiring external tools.\n\n## Example Output\n\n```\nMetagenomics Profiler — ClawBio\n================================\nMode: demo (pre-computed Peru sewage data)\nSamples: 6 (3 sites: Lima, Cusco, Iquitos)\n\nTaxonomy (Kraken2 + Bracken):\n  Total classified: 94.2%\n  Top species: Escherichia coli (12.3%), Klebsiella pneumoniae (8.7%),\n               Pseudomonas aeruginosa (5.1%), Acinetobacter baumannii (3.9%)\n\nResistome (RGI\u002FCARD):\n  Total ARG hits: 247 (Perfect: 89, Strict: 158)\n  Drug classes: 14\n  WHO-Critical ARGs detected: 23\n    - Carbapenem resistance: NDM-1, OXA-48, KPC-3\n    - 3rd-gen cephalosporin resistance: CTX-M-15, CTX-M-27\n\nFunctional Pathways (HUMAnN3):\n  Total pathways: 312\n  Top: PWY-7219 (adenosine ribonucleotides de novo biosynthesis)\n\nFigures saved to: demo_report\u002Ffigures\u002F\n  taxonomy_barplot.png (300 dpi)\n  resistome_heatmap.png (300 dpi)\n  who_critical_args.png (300 dpi)\n\nReproducibility:\n  commands.sh | environment.yml | checksums.sha256\n```\n\n## Pipeline Architecture\n\n```\nFASTQ R1 + R2\n     |\n     v\n[Kraken2] --> kraken2_report.txt\n     |\n     v\n[Bracken] --> bracken_species.tsv   --> Figure 1: Taxonomy bar chart\n     |\n     v\n[RGI MAIN] --> rgi_results.txt      --> Figure 2: Resistome heatmap\n     |                                --> Figure 3: WHO-critical ARG summary\n     v\n[HUMAnN3] --> pathabundance.tsv     (optional, --skip-functional to omit)\n     |\n     v\n[Report] --> report.md + figures\u002F + reproducibility\u002F\n```\n\n## Database Requirements\n\n| Tool | Database | Size | Notes |\n|------|----------|------|-------|\n| Kraken2 | Standard-8 or PlusPF | 8-70 GB | Set via `--kraken2-db` or `$KRAKEN2_DB` |\n| Bracken | (built from Kraken2 DB) | included | Read-length specific (default: 150 bp) |\n| RGI | CARD | ~500 MB | Auto-downloaded via `rgi auto_load` |\n| HUMAnN3 | ChocoPhlAn + UniRef90 | ~15 GB | Set via `--humann-db` or `$HUMANN_DB` |\n\n## Citations\n\nIf you use this skill in a publication, please cite:\n\n- Wood, D.E., Lu, J. & Langmead, B. (2019). Improved metagenomic analysis with Kraken 2. Genome Biology, 20, 257.\n- Lu, J. et al. (2017). Bracken: estimating species abundance in metagenomics data. PeerJ Computer Science, 3, e104.\n- Alcock, B.P. et al. (2023). CARD 2023: expanded curation, support for machine learning, and resistome prediction at the Comprehensive Antibiotic Resistance Database. Nucleic Acids Research, 51(D1), D419-D430.\n- Beghini, F. et al. (2021). Integrating taxonomic, functional, and strain-level profiling of diverse microbial communities with bioBakery 3. eLife, 10, e65088.\n- Corpas, M. (2026). ClawBio. https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio\n",{"name":5,"tags":52,"author":54,"inputs":55,"license":15,"outputs":71,"version":91,"metadata":92,"description":7},[34,33,42,32,53,31],"environmental","Manuel Corpas",[56,63,67],{"name":57,"type":46,"format":58,"description":62},"r1",[59,60,35,61],"fastq","fastq.gz","fq.gz","Forward reads (paired-end FASTQ R1)",{"name":64,"type":46,"format":65,"description":66},"r2",[59,60,35,61],"Reverse reads (paired-end FASTQ R2)",{"name":68,"type":46,"format":69,"description":70},"input",[59,60,35,61],"Single concatenated or interleaved FASTQ (alternative to R1+R2)",[72,76,79,82,89],{"name":73,"type":46,"format":74,"description":75},"taxonomy_report","tsv","Bracken-adjusted species-level taxonomy abundance table",{"name":77,"type":46,"format":74,"description":78},"resistome_profile","RGI\u002FCARD antimicrobial resistance gene hits with WHO priority classification",{"name":80,"type":46,"format":74,"description":81},"functional_pathways","HUMAnN3 pathway abundance table (MetaCyc\u002FUniRef)",{"name":83,"type":84,"format":85,"description":88},"figures","directory",[86,87],"png","pdf","Publication-quality figures (taxonomy bar chart, resistome heatmap, WHO-critical ARG summary)",{"name":40,"type":84,"description":90},"commands.sh, environment.yml, checksums.sha256","0.1.0",{"openclaw":93},{"category":94,"homepage":95,"min_python":96,"dependencies":97,"system_dependencies":100},"bioinformatics","https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio","3.9",[38,98,99,44,39,45],"numpy","matplotlib",[101,102,103,104],"kraken2","bracken","rgi","humann","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":111,"prompt":121,"zipAvailable":122},[112,115,118],{"tool":113,"command":114},"npx","npx skills add huamu668\u002Fclawhub-openclaw-medical --skill claw-metagenomics",{"tool":116,"command":117},"bunx","bunx skills add huamu668\u002Fclawhub-openclaw-medical --skill claw-metagenomics",{"tool":119,"command":120},"pnpm","pnpm dlx skills add huamu668\u002Fclawhub-openclaw-medical --skill claw-metagenomics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhuamu668\u002Fclawhub-openclaw-medical\u002Fblob\u002Fmain\u002Fclaw-metagenomics\u002FSKILL.md",true,[124,130,133,139,143,149,153,157,161,165,169,173,177,181,185,189,193,197,201,205,209,213,217],{"path":125,"resourceType":126,"resourceTypeDesc":127,"sizeBytes":128,"sourceHtmlUrl":129},"bin\u002Fccopy","OTHER","其他",161,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fbin\u002Fccopy",{"path":131,"resourceType":126,"resourceTypeDesc":127,"sizeBytes":128,"sourceHtmlUrl":132},"bin\u002Fcursor-copy","https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fbin\u002Fcursor-copy",{"path":134,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":137,"sourceHtmlUrl":138},"install.sh","SCRIPT","脚本",412,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Finstall.sh",{"path":140,"resourceType":126,"resourceTypeDesc":127,"sizeBytes":141,"sourceHtmlUrl":142},"Makefile",143,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002FMakefile",{"path":144,"resourceType":145,"resourceTypeDesc":146,"sizeBytes":147,"sourceHtmlUrl":148},"README.md","REFERENCE","参考文档",651,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002FREADME.md",{"path":150,"resourceType":145,"resourceTypeDesc":146,"sizeBytes":151,"sourceHtmlUrl":152},"references\u002FUSAGE.md",778,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Freferences\u002FUSAGE.md",{"path":154,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":155,"sourceHtmlUrl":156},"run.sh",869,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Frun.sh",{"path":158,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":159,"sourceHtmlUrl":160},"sanity.sh",2414,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fsanity.sh",{"path":162,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":163,"sourceHtmlUrl":164},"scripts\u002Fccopy\u002F__init__.py",617,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fccopy\u002F__init__.py",{"path":166,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":167,"sourceHtmlUrl":168},"scripts\u002Fccopy\u002Fcli.py",4484,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fccopy\u002Fcli.py",{"path":170,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":171,"sourceHtmlUrl":172},"scripts\u002Fccopy\u002Fclipboard.py",1928,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fccopy\u002Fclipboard.py",{"path":174,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":175,"sourceHtmlUrl":176},"scripts\u002Fccopy\u002Fcore.py",1747,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fccopy\u002Fcore.py",{"path":178,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":179,"sourceHtmlUrl":180},"scripts\u002Fccopy\u002Fdiagnostics.py",4282,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fccopy\u002Fdiagnostics.py",{"path":182,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":183,"sourceHtmlUrl":184},"scripts\u002Fccopy\u002Ferrors.py",145,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fccopy\u002Ferrors.py",{"path":186,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":187,"sourceHtmlUrl":188},"scripts\u002Fccopy\u002Fformatters.py",2996,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fccopy\u002Fformatters.py",{"path":190,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":191,"sourceHtmlUrl":192},"scripts\u002Fccopy\u002Fmodels.py",1223,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fccopy\u002Fmodels.py",{"path":194,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":195,"sourceHtmlUrl":196},"scripts\u002Fccopy\u002Fsqlite_backend.py",20447,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fccopy\u002Fsqlite_backend.py",{"path":198,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":199,"sourceHtmlUrl":200},"scripts\u002Fccopy\u002Fsqlite_db.py",3339,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fccopy\u002Fsqlite_db.py",{"path":202,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":203,"sourceHtmlUrl":204},"scripts\u002Fccopy\u002Ftranscript.py",7423,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fccopy\u002Ftranscript.py",{"path":206,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":207,"sourceHtmlUrl":208},"scripts\u002Fccopy\u002Futils.py",3201,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fccopy\u002Futils.py",{"path":210,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":211,"sourceHtmlUrl":212},"scripts\u002Fcursor_copy.py",345,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Fscripts\u002Fcursor_copy.py",{"path":214,"resourceType":126,"resourceTypeDesc":127,"sizeBytes":215,"sourceHtmlUrl":216},"tests\u002Ffixtures\u002Fsample_transcript.jsonl",464,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Ftests\u002Ffixtures\u002Fsample_transcript.jsonl",{"path":218,"resourceType":135,"resourceTypeDesc":136,"sizeBytes":219,"sourceHtmlUrl":220},"tests\u002Ftest_cursor_copy.py",9619,"https:\u002F\u002Fgithub.com\u002Fcateyephotos\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fccopy\u002Ftests\u002Ftest_cursor_copy.py",[222,241,268,287,301,330],{"skillNo":223,"name":224,"nameZh":6,"description":225,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":226,"categories":227,"keywords":228,"publishedAt":47},"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",[],[229,230,231,232,98,233,234,235,236,237,238,239,240],"python","zarr python","storage","scientific computing","arrays","pipelines","parallel","dask","cloud","gcs","s3","integration",{"skillNo":242,"name":243,"nameZh":6,"description":244,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":245,"categories":246,"keywords":248,"publishedAt":47},"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",[247],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[243,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267],"machine learning","in memory","learning","csv","visualization","create","core","ml","big data","memory","visualizations","fit","statistics","do","build","files","use","operations","work",{"skillNo":269,"name":270,"nameZh":6,"description":271,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":272,"categories":273,"keywords":274,"publishedAt":47},"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",[],[275,251,276,277,278,279,280,281,282,283,284,285,286,43],"torch geometric","node","Neural","link","gat","molecular","graphs","deep","networks","graph","neural networks","deep learning",{"skillNo":288,"name":289,"nameZh":6,"description":290,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":291,"categories":292,"keywords":293,"publishedAt":47},"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",[],[289,294,295,296,297,298,299,235,300,231],"data","genomics","sample","queries","ingestion","export","capabilities",{"skillNo":302,"name":303,"nameZh":6,"description":304,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":305,"categories":306,"keywords":315,"publishedAt":47},"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",[307,310],{"categoryNo":308,"categoryName":309,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":311,"categoryName":312,"taxonomyType":313,"taxonomyTypeDesc":314},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[303,316,317,265,318,319,320,321,322,323,324,325,326,327,328,329],"inclusion","yield","modal","Tools","aggregation","design","proteins","solubility","proteinmpnn","ligandmpnn","ligand-aware","inverse-folding","expression","sequence-design",{"skillNo":331,"name":332,"nameZh":6,"description":333,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":334,"licenseFileUrl":6,"sourceHtmlUrl":335,"categories":336,"keywords":337,"publishedAt":47},"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",[],[332,338,339,340,341,342,343,344,345,346,347,319,294,348,349],"RNA","single-cell","infer","cell","transitions","time","compute","velocity","scanpy","analysis","state","inference"]