[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZ398Q7RJS0779PD12506J":3,"skill-same:01M6CZ398Q7RJS0779PD12506J":92},{"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":24,"linkOnly":25,"markdownContent":26,"markdownBody":27,"frontMatter":28,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M6CZ398Q7RJS0779PD12506J","metagenome-taxonomic-profiling",null,"Profile microbial community composition from shotgun metagenomic reads using Kraken2\u002FBracken or MetaPhlAn 4.","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\u002Fmetagenome-taxonomic-profiling\u002FSKILL.md",[],[19,20,21,22,23],"profiling","metagenome taxonomic profiling","Composition","profile","community","2026-11-10 10:12:30",false,"---\nname: metagenome-taxonomic-profiling\ndescription: Profile microbial community composition from shotgun metagenomic reads using Kraken2\u002FBracken or MetaPhlAn 4.\n---\n\n# Skill: metagenome-taxonomic-profiling\n\n## Use When\n\n- The user wants to determine which organisms are present in a metagenomic sample.\n- The user needs taxonomic abundance estimates at species, genus, or phylum level.\n- The user wants to compare Kraken2 vs MetaPhlAn profiling approaches.\n- The user needs Bracken re-estimation for more accurate species-level abundance from Kraken2 output.\n\n## Inputs\n\n- Required:\n  - Host-depleted FASTQ file(s) (`.fastq`, `.fq`, `.fastq.gz`, `.fq.gz`).\n- Optional:\n  - `--profiler STR` — Profiler to use: `kraken2` or `metaphlan` (default: `kraken2`).\n  - `--db PATH` — Kraken2 or MetaPhlAn database path.\n  - `--bracken-db PATH` — Bracken database path (for Bracken re-estimation).\n  - `--bracken-len N` — Read length for Bracken (e.g., 100, 150, 250).\n  - `--level CHAR` — Taxonomic level for Bracken: `S` (species), `G` (genus), `P` (phylum), etc. (default: `S`).\n  - `--threads N` — Number of threads (default: 4).\n  - `--outdir DIR` — Output directory (default: `taxonomic_profiling_results`).\n  - `--confidence FLOAT` — Kraken2 confidence threshold (default: `0.0`).\n\n## Workflow\n\n1. If Kraken2: run `kraken2` with `--report` to generate a Kraken-style taxonomic report.\n2. If Bracken: run `bracken` on the Kraken2 report for abundance re-estimation at the specified taxonomic level.\n3. If MetaPhlAn: run `metaphlan` with `--input_type fastq` to produce a merged abundance table.\n4. Parse reports: extract top N taxa, relative abundances, and compute diversity metrics (Shannon, Simpson).\n5. Report: classification rate, top taxa, total species detected, alpha diversity estimates.\n\n## Output Contract\n\n- **Kraken2 report** — Standard Kraken2 taxonomic report (`\u003Coutdir>\u002F\u003Csample>_kraken2_report.txt`).\n- **Bracken abundance table** — Re-estimated abundances at the specified level (`\u003Coutdir>\u002F\u003Csample>_bracken.txt`), if Bracken is used.\n- **MetaPhlAn profile** — Relative abundance table (`\u003Coutdir>\u002F\u003Csample>_metaphlan_profile.txt`), if MetaPhlAn is used.\n- **Classification rate** — Percentage of reads assigned to a taxon.\n- **Top taxa summary** — Top 20 taxa by relative abundance.\n- **Diversity metrics** — Shannon and Simpson alpha diversity indices.\n\n## Limits\n\n- Kraken2 standard database is approximately 70 GB and requires sufficient RAM to load into memory.\n- MetaPhlAn 4 uses marker genes; it has a smaller database and higher species-level precision but may miss novel taxa without markers.\n- Bracken requires a pre-built Bracken database matching the Kraken2 database and the read length used in sequencing.\n- Kraken2 and MetaPhlAn must be installed and available on `$PATH`.\n- Classification rates vary significantly by database completeness and sample type.\n- For low-biomass samples, consider using a higher Kraken2 confidence threshold to reduce false positives.\n- Common failure cases:\n  - Kraken2 database too large to fit in available RAM, causing out-of-memory crash.\n  - Bracken database read length not matching actual sequencing read length.\n  - MetaPhlAn marker database version incompatible with the installed MetaPhlAn version.\n","# Skill: metagenome-taxonomic-profiling\n\n## Use When\n\n- The user wants to determine which organisms are present in a metagenomic sample.\n- The user needs taxonomic abundance estimates at species, genus, or phylum level.\n- The user wants to compare Kraken2 vs MetaPhlAn profiling approaches.\n- The user needs Bracken re-estimation for more accurate species-level abundance from Kraken2 output.\n\n## Inputs\n\n- Required:\n  - Host-depleted FASTQ file(s) (`.fastq`, `.fq`, `.fastq.gz`, `.fq.gz`).\n- Optional:\n  - `--profiler STR` — Profiler to use: `kraken2` or `metaphlan` (default: `kraken2`).\n  - `--db PATH` — Kraken2 or MetaPhlAn database path.\n  - `--bracken-db PATH` — Bracken database path (for Bracken re-estimation).\n  - `--bracken-len N` — Read length for Bracken (e.g., 100, 150, 250).\n  - `--level CHAR` — Taxonomic level for Bracken: `S` (species), `G` (genus), `P` (phylum), etc. (default: `S`).\n  - `--threads N` — Number of threads (default: 4).\n  - `--outdir DIR` — Output directory (default: `taxonomic_profiling_results`).\n  - `--confidence FLOAT` — Kraken2 confidence threshold (default: `0.0`).\n\n## Workflow\n\n1. If Kraken2: run `kraken2` with `--report` to generate a Kraken-style taxonomic report.\n2. If Bracken: run `bracken` on the Kraken2 report for abundance re-estimation at the specified taxonomic level.\n3. If MetaPhlAn: run `metaphlan` with `--input_type fastq` to produce a merged abundance table.\n4. Parse reports: extract top N taxa, relative abundances, and compute diversity metrics (Shannon, Simpson).\n5. Report: classification rate, top taxa, total species detected, alpha diversity estimates.\n\n## Output Contract\n\n- **Kraken2 report** — Standard Kraken2 taxonomic report (`\u003Coutdir>\u002F\u003Csample>_kraken2_report.txt`).\n- **Bracken abundance table** — Re-estimated abundances at the specified level (`\u003Coutdir>\u002F\u003Csample>_bracken.txt`), if Bracken is used.\n- **MetaPhlAn profile** — Relative abundance table (`\u003Coutdir>\u002F\u003Csample>_metaphlan_profile.txt`), if MetaPhlAn is used.\n- **Classification rate** — Percentage of reads assigned to a taxon.\n- **Top taxa summary** — Top 20 taxa by relative abundance.\n- **Diversity metrics** — Shannon and Simpson alpha diversity indices.\n\n## Limits\n\n- Kraken2 standard database is approximately 70 GB and requires sufficient RAM to load into memory.\n- MetaPhlAn 4 uses marker genes; it has a smaller database and higher species-level precision but may miss novel taxa without markers.\n- Bracken requires a pre-built Bracken database matching the Kraken2 database and the read length used in sequencing.\n- Kraken2 and MetaPhlAn must be installed and available on `$PATH`.\n- Classification rates vary significantly by database completeness and sample type.\n- For low-biomass samples, consider using a higher Kraken2 confidence threshold to reduce false positives.\n- Common failure cases:\n  - Kraken2 database too large to fit in available RAM, causing out-of-memory crash.\n  - Bracken database read length not matching actual sequencing read length.\n  - MetaPhlAn marker database version incompatible with the installed MetaPhlAn version.\n",{"name":5,"description":7},"main","5118e7fda890e9aa819cb71e003cd243d3a31970","skills\u002Fmetagenome-taxonomic-profiling",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":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Scientific-Tooling\u002Fstructured-intelligence --skill metagenome-taxonomic-profiling",{"tool":42,"command":43},"bunx","bunx skills add Scientific-Tooling\u002Fstructured-intelligence --skill metagenome-taxonomic-profiling",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Scientific-Tooling\u002Fstructured-intelligence --skill metagenome-taxonomic-profiling","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fmetagenome-taxonomic-profiling\u002FSKILL.md",true,[50,56,60,64,70,74,78,82,88],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"agents\u002Fclaude.yaml","REFERENCE","参考文档",330,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fmetagenome-taxonomic-profiling\u002Fagents\u002Fclaude.yaml",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"agents\u002Fopenai.yaml",331,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fmetagenome-taxonomic-profiling\u002Fagents\u002Fopenai.yaml",{"path":61,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":62,"sourceHtmlUrl":63},"agents\u002FREADME.md",322,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fmetagenome-taxonomic-profiling\u002Fagents\u002FREADME.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"assets\u002F.gitkeep","ASSET","资产文件",0,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fmetagenome-taxonomic-profiling\u002Fassets\u002F.gitkeep",{"path":71,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":72,"sourceHtmlUrl":73},"config.yaml",303,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fmetagenome-taxonomic-profiling\u002Fconfig.yaml",{"path":75,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fkraken2-bracken-metaphlan.md",3433,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fmetagenome-taxonomic-profiling\u002Freferences\u002Fkraken2-bracken-metaphlan.md",{"path":79,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002FREADME.md",68,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fmetagenome-taxonomic-profiling\u002Freferences\u002FREADME.md",{"path":83,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002Fbatch_run.sh","SCRIPT","脚本",4718,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fmetagenome-taxonomic-profiling\u002Fscripts\u002Fbatch_run.sh",{"path":89,"resourceType":84,"resourceTypeDesc":85,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Frun.sh",6181,"https:\u002F\u002Fgithub.com\u002FScientific-Tooling\u002Fstructured-intelligence\u002Fblob\u002Fmain\u002Fskills\u002Fmetagenome-taxonomic-profiling\u002Fscripts\u002Frun.sh",[93,121,134,147,161,173],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":104,"publishedAt":24},"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",[99],{"categoryNo":100,"categoryName":101,"taxonomyType":102,"taxonomyTypeDesc":103},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120],"structured intelligence skill creator","skill creator","intelligence","structured","create","requirements","workflows","provider","update","registry","local","validation","metadata","repository","templates","Rules",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":24},"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",[],[128,129,130,131,132,133],"analysis","stat survival analysis","regression","log","functions","test",{"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":140,"publishedAt":24},"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",[],[141,142,143,144,145,146],"stat pca","sample","visualize","contributing","data","structure",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":24},"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",[],[154,155,156,157,158,159,160],"stat pairwise correlation","correlation","produce","heatmap","compute","across","tests",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":24},"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",[],[168,169,145,170,142,171,172],"stat nonlinear embedding","visualization","relationships","cell","exploratory visualization",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":24},"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",[],[130,180,181,182,183,184],"stat logistic regression","report","model","outcomes","performance"]