[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-ngs-amplicon-microbiome":3,"mdc-sozgy9-key":36,"related-repo-openai-ngs-amplicon-microbiome":837,"related-org-openai-ngs-amplicon-microbiome":960},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":25,"repoUrl":26,"updatedAt":27,"license":28,"forks":29,"topics":30,"repo":31,"sourceUrl":34,"mdContent":35},"ngs-amplicon-microbiome","run amplicon microbiome analysis workflows","Kick off public 16S, 18S, ITS, COI, or other marker-gene amplicon microbiome workflows using nf-core\u002Fampliseq, QIIME2, DADA2, and Cutadapt.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19,22],{"name":13,"slug":14,"type":15},"Nextflow","nextflow","tag",{"name":17,"slug":18,"type":15},"Data Analysis","data-analysis",{"name":20,"slug":21,"type":15},"Life Sciences","life-sciences",{"name":23,"slug":24,"type":15},"Bioinformatics","bioinformatics",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-06-30T19:00:57.102",null,465,[],{"repoUrl":26,"stars":25,"forks":29,"topics":32,"description":33},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fngs-analysis\u002Fskills\u002Fngs-amplicon-microbiome","---\nname: ngs-amplicon-microbiome\ndescription: Kick off public 16S, 18S, ITS, COI, or other marker-gene amplicon microbiome workflows using nf-core\u002Fampliseq, QIIME2, DADA2, and Cutadapt.\n---\n\n# Amplicon Microbiome\n\nUse this skill for marker-gene microbiome analysis from amplicon FASTQs.\n\n## Essential Inputs\n\nConfirm:\n\n- marker region: 16S, 18S, ITS, COI, or custom\n- primer sequences and orientation\n- paired-end or single-end reads\n- whether reads should be merged\n- taxonomy database and version\n- sample metadata\n- endpoint: ASV table, taxonomy, diversity, differential abundance, or plots\n\n## Public Defaults\n\nPrefer `nf-core\u002Fampliseq` for reproducible end-to-end runs. Use QIIME2 or DADA2 directly when the user wants notebook-level control or an existing lab protocol requires it.\n\n## Preflight\n\n```bash\npython plugins\u002Fngs-analysis\u002Fscripts\u002Fngs_preflight.py --pipeline amplicon_microbiome --emit-install-plan\n```\n\n## Local Execution Package\n\nFor FASTQ intake\u002FQC before primer, ASV, and taxonomy decisions, use:\n\n```bash\npython plugins\u002Fngs-analysis\u002Fscripts\u002Frun_fastq_assay_package.py \\\n  --lane amplicon_microbiome \\\n  --sample-sheet amplicon_samples.tsv \\\n  --execute\n```\n\nThis validates read paths and structure, runs seqkit stats and FastQC\u002FMultiQC when available, and writes `amplicon_analysis_status.json`. The runner now also emits `methods\u002Famplicon_methods.json` plus a concrete backend handoff bundle under `workflow\u002F` so primer, denoiser, truncation, normalization, and taxonomy choices are machine-readable even before a full backend is run.\n\nIf the user asks for a full amplicon analysis rather than QC\u002Freadiness, do not treat FASTQs alone as sufficient. Require primer sequences, primer orientation, taxonomy database plus version, and sample metadata before presenting the run as analysis-ready. Without that context, run the local execution package and describe the result as a read-QC\u002Freadiness bundle only.\n\nFor backend ASV\u002Ftaxonomy\u002Fdiversity execution when primers, metadata, and taxonomy resources are available, use:\n\n```bash\npython plugins\u002Fngs-analysis\u002Fscripts\u002Frun_amplicon_microbiome.py \\\n  --sample-sheet amplicon_samples.tsv \\\n  --backend qiime2 \\\n  --primer-forward GTGYCAGCMGCCGCGGTAA \\\n  --primer-reverse GGACTACNVGGGTWTCTAAT \\\n  --taxonomy-classifier silva-138-classifier.qza \\\n  --metadata sample_metadata.tsv \\\n  --execute\n```\n\nUse `--backend dada2` for a direct R\u002FBioconductor ASV path. The plugin includes `workflows\u002Famplicon_microbiome\u002Frun_dada2_backend.R`; the runner checks for `Rscript` and the `dada2` R package before execution, then writes normalized ASV, representative-sequence, read-retention, and optional taxonomy tables under `tables\u002F`.\n\nFor nf-core execution, use `plugins\u002Fngs-analysis\u002Fscripts\u002Frun_nfcore_pipeline.py --pipeline ampliseq`.\n\nThe direct backend runner also emits `resources\u002Fresource_plan.json`, `resource_manifest.tsv`, `resource_env.sh`, and `resource_readiness.md`. The resource check is advisory by default when a QIIME classifier is supplied directly; add `--bundle-root silva_138_amplicon=\u003Cpath>`, `--include-optional-resources`, and `--require-resource-plan` when missing registered taxonomy databases should block readiness.\n\nThe backend runner writes native normalized tables when QIIME2\u002FDADA2\u002Fnf-core outputs are present:\n\n- `tables\u002Fasv_table.tsv`\n- `tables\u002Frepresentative_sequences.fasta` for direct DADA2 runs\n- `tables\u002Ftaxonomy.tsv`\n- `tables\u002Fread_retention.tsv`\n- `tables\u002Famplicon_backend_summary.json`\n- `tables\u002Falpha_diversity.tsv`, `tables\u002Fbray_curtis_distance.tsv`, and `tables\u002Ftop_taxa_or_features.tsv` when a normalized ASV\u002Ffeature table is available\n\nQIIME2 BIOM-only feature-table exports are recorded as requiring conversion, with a `biom convert` command in the backend summary. Do not claim diversity or taxonomy interpretation unless these normalized tables or equivalent supplied inputs exist.\n\n## Kickoff Pattern\n\nnf-core preflight run:\n\n```bash\nnextflow run nf-core\u002Fampliseq \\\n  -profile test,docker \\\n  --outdir results\u002Fampliseq_test\n```\n\nBefore a real run, verify primer trimming and truncation choices from read-quality profiles.\n\n## Visualization Outputs\n\nThe local FASTQ package always writes `visualizations\u002Findex.html` and `visualizations\u002Fvisualization_manifest.json`. With only FASTQs, this is a read-QC\u002Freadiness bundle. If an ASV\u002Ffeature table is available, pass it to the runner with `--asv-table` to generate alpha diversity, Bray-Curtis PCoA, and rarefaction artifacts. If a feature taxonomy table is available, pass `--taxonomy-table` to generate taxa barplots. When downstream tables are labeled synthetic or contain sample columns that are not present in the real sample sheet, the runner marks the run review-only and blocks beta-diversity\u002FPCoA unless `--allow-synthetic-diversity` is set explicitly.\n\nThe run also emits `qc_verdict.json` and, for amplicon runs, `qc_interpretation.json` with machine-readable reason codes, a readiness verdict, and follow-on command templates for generating ASV\u002Ftaxonomy tables and re-rendering plugin-native plots. Backend runs additionally write `tables\u002Famplicon_backend_summary.json` so exported ASV, taxonomy, read-retention, and BIOM-conversion status are auditable. When a normalized ASV\u002Ffeature table is available, the backend runner also writes `tables\u002Famplicon_diversity_summary.json`, `visualizations\u002Famplicon_backend_dashboard.html`, and SVG plots for sample depth, Shannon diversity, and top taxa\u002Ffeatures. If the ASV table is absent, these outputs remain explicitly unavailable rather than inferred from FASTQ QC.\n\n## Guardrails\n\n- Do not choose truncation lengths before looking at quality distributions.\n- Do not mix taxonomy database versions without recording them.\n- Preserve negative controls and extraction blanks in metadata.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,56,63,68,108,114,128,134,178,184,189,258,287,292,297,431,476,488,546,551,626,639,645,650,708,713,719,764,807,813,831],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"amplicon-microbiome",[47],{"type":48,"value":49},"text","Amplicon Microbiome",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54],{"type":48,"value":55},"Use this skill for marker-gene microbiome analysis from amplicon FASTQs.",{"type":42,"tag":57,"props":58,"children":60},"h2",{"id":59},"essential-inputs",[61],{"type":48,"value":62},"Essential Inputs",{"type":42,"tag":51,"props":64,"children":65},{},[66],{"type":48,"value":67},"Confirm:",{"type":42,"tag":69,"props":70,"children":71},"ul",{},[72,78,83,88,93,98,103],{"type":42,"tag":73,"props":74,"children":75},"li",{},[76],{"type":48,"value":77},"marker region: 16S, 18S, ITS, COI, or custom",{"type":42,"tag":73,"props":79,"children":80},{},[81],{"type":48,"value":82},"primer sequences and orientation",{"type":42,"tag":73,"props":84,"children":85},{},[86],{"type":48,"value":87},"paired-end or single-end reads",{"type":42,"tag":73,"props":89,"children":90},{},[91],{"type":48,"value":92},"whether reads should be merged",{"type":42,"tag":73,"props":94,"children":95},{},[96],{"type":48,"value":97},"taxonomy database and version",{"type":42,"tag":73,"props":99,"children":100},{},[101],{"type":48,"value":102},"sample metadata",{"type":42,"tag":73,"props":104,"children":105},{},[106],{"type":48,"value":107},"endpoint: ASV table, taxonomy, diversity, differential abundance, or plots",{"type":42,"tag":57,"props":109,"children":111},{"id":110},"public-defaults",[112],{"type":48,"value":113},"Public Defaults",{"type":42,"tag":51,"props":115,"children":116},{},[117,119,126],{"type":48,"value":118},"Prefer ",{"type":42,"tag":120,"props":121,"children":123},"code",{"className":122},[],[124],{"type":48,"value":125},"nf-core\u002Fampliseq",{"type":48,"value":127}," for reproducible end-to-end runs. Use QIIME2 or DADA2 directly when the user wants notebook-level control or an existing lab protocol requires it.",{"type":42,"tag":57,"props":129,"children":131},{"id":130},"preflight",[132],{"type":48,"value":133},"Preflight",{"type":42,"tag":135,"props":136,"children":141},"pre",{"className":137,"code":138,"language":139,"meta":140,"style":140},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","python plugins\u002Fngs-analysis\u002Fscripts\u002Fngs_preflight.py --pipeline amplicon_microbiome --emit-install-plan\n","bash","",[142],{"type":42,"tag":120,"props":143,"children":144},{"__ignoreMap":140},[145],{"type":42,"tag":146,"props":147,"children":150},"span",{"class":148,"line":149},"line",1,[151,157,163,168,173],{"type":42,"tag":146,"props":152,"children":154},{"style":153},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[155],{"type":48,"value":156},"python",{"type":42,"tag":146,"props":158,"children":160},{"style":159},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[161],{"type":48,"value":162}," plugins\u002Fngs-analysis\u002Fscripts\u002Fngs_preflight.py",{"type":42,"tag":146,"props":164,"children":165},{"style":159},[166],{"type":48,"value":167}," --pipeline",{"type":42,"tag":146,"props":169,"children":170},{"style":159},[171],{"type":48,"value":172}," amplicon_microbiome",{"type":42,"tag":146,"props":174,"children":175},{"style":159},[176],{"type":48,"value":177}," --emit-install-plan\n",{"type":42,"tag":57,"props":179,"children":181},{"id":180},"local-execution-package",[182],{"type":48,"value":183},"Local Execution Package",{"type":42,"tag":51,"props":185,"children":186},{},[187],{"type":48,"value":188},"For FASTQ intake\u002FQC before primer, ASV, and taxonomy decisions, use:",{"type":42,"tag":135,"props":190,"children":192},{"className":137,"code":191,"language":139,"meta":140,"style":140},"python plugins\u002Fngs-analysis\u002Fscripts\u002Frun_fastq_assay_package.py \\\n  --lane amplicon_microbiome \\\n  --sample-sheet amplicon_samples.tsv \\\n  --execute\n",[193],{"type":42,"tag":120,"props":194,"children":195},{"__ignoreMap":140},[196,214,231,249],{"type":42,"tag":146,"props":197,"children":198},{"class":148,"line":149},[199,203,208],{"type":42,"tag":146,"props":200,"children":201},{"style":153},[202],{"type":48,"value":156},{"type":42,"tag":146,"props":204,"children":205},{"style":159},[206],{"type":48,"value":207}," plugins\u002Fngs-analysis\u002Fscripts\u002Frun_fastq_assay_package.py",{"type":42,"tag":146,"props":209,"children":211},{"style":210},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[212],{"type":48,"value":213}," \\\n",{"type":42,"tag":146,"props":215,"children":217},{"class":148,"line":216},2,[218,223,227],{"type":42,"tag":146,"props":219,"children":220},{"style":159},[221],{"type":48,"value":222},"  --lane",{"type":42,"tag":146,"props":224,"children":225},{"style":159},[226],{"type":48,"value":172},{"type":42,"tag":146,"props":228,"children":229},{"style":210},[230],{"type":48,"value":213},{"type":42,"tag":146,"props":232,"children":234},{"class":148,"line":233},3,[235,240,245],{"type":42,"tag":146,"props":236,"children":237},{"style":159},[238],{"type":48,"value":239},"  --sample-sheet",{"type":42,"tag":146,"props":241,"children":242},{"style":159},[243],{"type":48,"value":244}," amplicon_samples.tsv",{"type":42,"tag":146,"props":246,"children":247},{"style":210},[248],{"type":48,"value":213},{"type":42,"tag":146,"props":250,"children":252},{"class":148,"line":251},4,[253],{"type":42,"tag":146,"props":254,"children":255},{"style":159},[256],{"type":48,"value":257},"  --execute\n",{"type":42,"tag":51,"props":259,"children":260},{},[261,263,269,271,277,279,285],{"type":48,"value":262},"This validates read paths and structure, runs seqkit stats and FastQC\u002FMultiQC when available, and writes ",{"type":42,"tag":120,"props":264,"children":266},{"className":265},[],[267],{"type":48,"value":268},"amplicon_analysis_status.json",{"type":48,"value":270},". The runner now also emits ",{"type":42,"tag":120,"props":272,"children":274},{"className":273},[],[275],{"type":48,"value":276},"methods\u002Famplicon_methods.json",{"type":48,"value":278}," plus a concrete backend handoff bundle under ",{"type":42,"tag":120,"props":280,"children":282},{"className":281},[],[283],{"type":48,"value":284},"workflow\u002F",{"type":48,"value":286}," so primer, denoiser, truncation, normalization, and taxonomy choices are machine-readable even before a full backend is run.",{"type":42,"tag":51,"props":288,"children":289},{},[290],{"type":48,"value":291},"If the user asks for a full amplicon analysis rather than QC\u002Freadiness, do not treat FASTQs alone as sufficient. Require primer sequences, primer orientation, taxonomy database plus version, and sample metadata before presenting the run as analysis-ready. Without that context, run the local execution package and describe the result as a read-QC\u002Freadiness bundle only.",{"type":42,"tag":51,"props":293,"children":294},{},[295],{"type":48,"value":296},"For backend ASV\u002Ftaxonomy\u002Fdiversity execution when primers, metadata, and taxonomy resources are available, use:",{"type":42,"tag":135,"props":298,"children":300},{"className":137,"code":299,"language":139,"meta":140,"style":140},"python plugins\u002Fngs-analysis\u002Fscripts\u002Frun_amplicon_microbiome.py \\\n  --sample-sheet amplicon_samples.tsv \\\n  --backend qiime2 \\\n  --primer-forward GTGYCAGCMGCCGCGGTAA \\\n  --primer-reverse GGACTACNVGGGTWTCTAAT \\\n  --taxonomy-classifier silva-138-classifier.qza \\\n  --metadata sample_metadata.tsv \\\n  --execute\n",[301],{"type":42,"tag":120,"props":302,"children":303},{"__ignoreMap":140},[304,320,335,352,369,387,405,423],{"type":42,"tag":146,"props":305,"children":306},{"class":148,"line":149},[307,311,316],{"type":42,"tag":146,"props":308,"children":309},{"style":153},[310],{"type":48,"value":156},{"type":42,"tag":146,"props":312,"children":313},{"style":159},[314],{"type":48,"value":315}," plugins\u002Fngs-analysis\u002Fscripts\u002Frun_amplicon_microbiome.py",{"type":42,"tag":146,"props":317,"children":318},{"style":210},[319],{"type":48,"value":213},{"type":42,"tag":146,"props":321,"children":322},{"class":148,"line":216},[323,327,331],{"type":42,"tag":146,"props":324,"children":325},{"style":159},[326],{"type":48,"value":239},{"type":42,"tag":146,"props":328,"children":329},{"style":159},[330],{"type":48,"value":244},{"type":42,"tag":146,"props":332,"children":333},{"style":210},[334],{"type":48,"value":213},{"type":42,"tag":146,"props":336,"children":337},{"class":148,"line":233},[338,343,348],{"type":42,"tag":146,"props":339,"children":340},{"style":159},[341],{"type":48,"value":342},"  --backend",{"type":42,"tag":146,"props":344,"children":345},{"style":159},[346],{"type":48,"value":347}," qiime2",{"type":42,"tag":146,"props":349,"children":350},{"style":210},[351],{"type":48,"value":213},{"type":42,"tag":146,"props":353,"children":354},{"class":148,"line":251},[355,360,365],{"type":42,"tag":146,"props":356,"children":357},{"style":159},[358],{"type":48,"value":359},"  --primer-forward",{"type":42,"tag":146,"props":361,"children":362},{"style":159},[363],{"type":48,"value":364}," GTGYCAGCMGCCGCGGTAA",{"type":42,"tag":146,"props":366,"children":367},{"style":210},[368],{"type":48,"value":213},{"type":42,"tag":146,"props":370,"children":372},{"class":148,"line":371},5,[373,378,383],{"type":42,"tag":146,"props":374,"children":375},{"style":159},[376],{"type":48,"value":377},"  --primer-reverse",{"type":42,"tag":146,"props":379,"children":380},{"style":159},[381],{"type":48,"value":382}," GGACTACNVGGGTWTCTAAT",{"type":42,"tag":146,"props":384,"children":385},{"style":210},[386],{"type":48,"value":213},{"type":42,"tag":146,"props":388,"children":390},{"class":148,"line":389},6,[391,396,401],{"type":42,"tag":146,"props":392,"children":393},{"style":159},[394],{"type":48,"value":395},"  --taxonomy-classifier",{"type":42,"tag":146,"props":397,"children":398},{"style":159},[399],{"type":48,"value":400}," silva-138-classifier.qza",{"type":42,"tag":146,"props":402,"children":403},{"style":210},[404],{"type":48,"value":213},{"type":42,"tag":146,"props":406,"children":408},{"class":148,"line":407},7,[409,414,419],{"type":42,"tag":146,"props":410,"children":411},{"style":159},[412],{"type":48,"value":413},"  --metadata",{"type":42,"tag":146,"props":415,"children":416},{"style":159},[417],{"type":48,"value":418}," sample_metadata.tsv",{"type":42,"tag":146,"props":420,"children":421},{"style":210},[422],{"type":48,"value":213},{"type":42,"tag":146,"props":424,"children":426},{"class":148,"line":425},8,[427],{"type":42,"tag":146,"props":428,"children":429},{"style":159},[430],{"type":48,"value":257},{"type":42,"tag":51,"props":432,"children":433},{},[434,436,442,444,450,452,458,460,466,468,474],{"type":48,"value":435},"Use ",{"type":42,"tag":120,"props":437,"children":439},{"className":438},[],[440],{"type":48,"value":441},"--backend dada2",{"type":48,"value":443}," for a direct R\u002FBioconductor ASV path. The plugin includes ",{"type":42,"tag":120,"props":445,"children":447},{"className":446},[],[448],{"type":48,"value":449},"workflows\u002Famplicon_microbiome\u002Frun_dada2_backend.R",{"type":48,"value":451},"; the runner checks for ",{"type":42,"tag":120,"props":453,"children":455},{"className":454},[],[456],{"type":48,"value":457},"Rscript",{"type":48,"value":459}," and the ",{"type":42,"tag":120,"props":461,"children":463},{"className":462},[],[464],{"type":48,"value":465},"dada2",{"type":48,"value":467}," R package before execution, then writes normalized ASV, representative-sequence, read-retention, and optional taxonomy tables under ",{"type":42,"tag":120,"props":469,"children":471},{"className":470},[],[472],{"type":48,"value":473},"tables\u002F",{"type":48,"value":475},".",{"type":42,"tag":51,"props":477,"children":478},{},[479,481,487],{"type":48,"value":480},"For nf-core execution, use ",{"type":42,"tag":120,"props":482,"children":484},{"className":483},[],[485],{"type":48,"value":486},"plugins\u002Fngs-analysis\u002Fscripts\u002Frun_nfcore_pipeline.py --pipeline ampliseq",{"type":48,"value":475},{"type":42,"tag":51,"props":489,"children":490},{},[491,493,499,501,507,508,514,516,522,524,530,531,537,538,544],{"type":48,"value":492},"The direct backend runner also emits ",{"type":42,"tag":120,"props":494,"children":496},{"className":495},[],[497],{"type":48,"value":498},"resources\u002Fresource_plan.json",{"type":48,"value":500},", ",{"type":42,"tag":120,"props":502,"children":504},{"className":503},[],[505],{"type":48,"value":506},"resource_manifest.tsv",{"type":48,"value":500},{"type":42,"tag":120,"props":509,"children":511},{"className":510},[],[512],{"type":48,"value":513},"resource_env.sh",{"type":48,"value":515},", and ",{"type":42,"tag":120,"props":517,"children":519},{"className":518},[],[520],{"type":48,"value":521},"resource_readiness.md",{"type":48,"value":523},". The resource check is advisory by default when a QIIME classifier is supplied directly; add ",{"type":42,"tag":120,"props":525,"children":527},{"className":526},[],[528],{"type":48,"value":529},"--bundle-root silva_138_amplicon=\u003Cpath>",{"type":48,"value":500},{"type":42,"tag":120,"props":532,"children":534},{"className":533},[],[535],{"type":48,"value":536},"--include-optional-resources",{"type":48,"value":515},{"type":42,"tag":120,"props":539,"children":541},{"className":540},[],[542],{"type":48,"value":543},"--require-resource-plan",{"type":48,"value":545}," when missing registered taxonomy databases should block readiness.",{"type":42,"tag":51,"props":547,"children":548},{},[549],{"type":48,"value":550},"The backend runner writes native normalized tables when QIIME2\u002FDADA2\u002Fnf-core outputs are present:",{"type":42,"tag":69,"props":552,"children":553},{},[554,563,574,583,592,601],{"type":42,"tag":73,"props":555,"children":556},{},[557],{"type":42,"tag":120,"props":558,"children":560},{"className":559},[],[561],{"type":48,"value":562},"tables\u002Fasv_table.tsv",{"type":42,"tag":73,"props":564,"children":565},{},[566,572],{"type":42,"tag":120,"props":567,"children":569},{"className":568},[],[570],{"type":48,"value":571},"tables\u002Frepresentative_sequences.fasta",{"type":48,"value":573}," for direct DADA2 runs",{"type":42,"tag":73,"props":575,"children":576},{},[577],{"type":42,"tag":120,"props":578,"children":580},{"className":579},[],[581],{"type":48,"value":582},"tables\u002Ftaxonomy.tsv",{"type":42,"tag":73,"props":584,"children":585},{},[586],{"type":42,"tag":120,"props":587,"children":589},{"className":588},[],[590],{"type":48,"value":591},"tables\u002Fread_retention.tsv",{"type":42,"tag":73,"props":593,"children":594},{},[595],{"type":42,"tag":120,"props":596,"children":598},{"className":597},[],[599],{"type":48,"value":600},"tables\u002Famplicon_backend_summary.json",{"type":42,"tag":73,"props":602,"children":603},{},[604,610,611,617,618,624],{"type":42,"tag":120,"props":605,"children":607},{"className":606},[],[608],{"type":48,"value":609},"tables\u002Falpha_diversity.tsv",{"type":48,"value":500},{"type":42,"tag":120,"props":612,"children":614},{"className":613},[],[615],{"type":48,"value":616},"tables\u002Fbray_curtis_distance.tsv",{"type":48,"value":515},{"type":42,"tag":120,"props":619,"children":621},{"className":620},[],[622],{"type":48,"value":623},"tables\u002Ftop_taxa_or_features.tsv",{"type":48,"value":625}," when a normalized ASV\u002Ffeature table is available",{"type":42,"tag":51,"props":627,"children":628},{},[629,631,637],{"type":48,"value":630},"QIIME2 BIOM-only feature-table exports are recorded as requiring conversion, with a ",{"type":42,"tag":120,"props":632,"children":634},{"className":633},[],[635],{"type":48,"value":636},"biom convert",{"type":48,"value":638}," command in the backend summary. Do not claim diversity or taxonomy interpretation unless these normalized tables or equivalent supplied inputs exist.",{"type":42,"tag":57,"props":640,"children":642},{"id":641},"kickoff-pattern",[643],{"type":48,"value":644},"Kickoff Pattern",{"type":42,"tag":51,"props":646,"children":647},{},[648],{"type":48,"value":649},"nf-core preflight run:",{"type":42,"tag":135,"props":651,"children":653},{"className":137,"code":652,"language":139,"meta":140,"style":140},"nextflow run nf-core\u002Fampliseq \\\n  -profile test,docker \\\n  --outdir results\u002Fampliseq_test\n",[654],{"type":42,"tag":120,"props":655,"children":656},{"__ignoreMap":140},[657,678,695],{"type":42,"tag":146,"props":658,"children":659},{"class":148,"line":149},[660,664,669,674],{"type":42,"tag":146,"props":661,"children":662},{"style":153},[663],{"type":48,"value":14},{"type":42,"tag":146,"props":665,"children":666},{"style":159},[667],{"type":48,"value":668}," run",{"type":42,"tag":146,"props":670,"children":671},{"style":159},[672],{"type":48,"value":673}," nf-core\u002Fampliseq",{"type":42,"tag":146,"props":675,"children":676},{"style":210},[677],{"type":48,"value":213},{"type":42,"tag":146,"props":679,"children":680},{"class":148,"line":216},[681,686,691],{"type":42,"tag":146,"props":682,"children":683},{"style":159},[684],{"type":48,"value":685},"  -profile",{"type":42,"tag":146,"props":687,"children":688},{"style":159},[689],{"type":48,"value":690}," test,docker",{"type":42,"tag":146,"props":692,"children":693},{"style":210},[694],{"type":48,"value":213},{"type":42,"tag":146,"props":696,"children":697},{"class":148,"line":233},[698,703],{"type":42,"tag":146,"props":699,"children":700},{"style":159},[701],{"type":48,"value":702},"  --outdir",{"type":42,"tag":146,"props":704,"children":705},{"style":159},[706],{"type":48,"value":707}," results\u002Fampliseq_test\n",{"type":42,"tag":51,"props":709,"children":710},{},[711],{"type":48,"value":712},"Before a real run, verify primer trimming and truncation choices from read-quality profiles.",{"type":42,"tag":57,"props":714,"children":716},{"id":715},"visualization-outputs",[717],{"type":48,"value":718},"Visualization Outputs",{"type":42,"tag":51,"props":720,"children":721},{},[722,724,730,732,738,740,746,748,754,756,762],{"type":48,"value":723},"The local FASTQ package always writes ",{"type":42,"tag":120,"props":725,"children":727},{"className":726},[],[728],{"type":48,"value":729},"visualizations\u002Findex.html",{"type":48,"value":731}," and ",{"type":42,"tag":120,"props":733,"children":735},{"className":734},[],[736],{"type":48,"value":737},"visualizations\u002Fvisualization_manifest.json",{"type":48,"value":739},". With only FASTQs, this is a read-QC\u002Freadiness bundle. If an ASV\u002Ffeature table is available, pass it to the runner with ",{"type":42,"tag":120,"props":741,"children":743},{"className":742},[],[744],{"type":48,"value":745},"--asv-table",{"type":48,"value":747}," to generate alpha diversity, Bray-Curtis PCoA, and rarefaction artifacts. If a feature taxonomy table is available, pass ",{"type":42,"tag":120,"props":749,"children":751},{"className":750},[],[752],{"type":48,"value":753},"--taxonomy-table",{"type":48,"value":755}," to generate taxa barplots. When downstream tables are labeled synthetic or contain sample columns that are not present in the real sample sheet, the runner marks the run review-only and blocks beta-diversity\u002FPCoA unless ",{"type":42,"tag":120,"props":757,"children":759},{"className":758},[],[760],{"type":48,"value":761},"--allow-synthetic-diversity",{"type":48,"value":763}," is set explicitly.",{"type":42,"tag":51,"props":765,"children":766},{},[767,769,775,777,783,785,790,792,798,799,805],{"type":48,"value":768},"The run also emits ",{"type":42,"tag":120,"props":770,"children":772},{"className":771},[],[773],{"type":48,"value":774},"qc_verdict.json",{"type":48,"value":776}," and, for amplicon runs, ",{"type":42,"tag":120,"props":778,"children":780},{"className":779},[],[781],{"type":48,"value":782},"qc_interpretation.json",{"type":48,"value":784}," with machine-readable reason codes, a readiness verdict, and follow-on command templates for generating ASV\u002Ftaxonomy tables and re-rendering plugin-native plots. Backend runs additionally write ",{"type":42,"tag":120,"props":786,"children":788},{"className":787},[],[789],{"type":48,"value":600},{"type":48,"value":791}," so exported ASV, taxonomy, read-retention, and BIOM-conversion status are auditable. When a normalized ASV\u002Ffeature table is available, the backend runner also writes ",{"type":42,"tag":120,"props":793,"children":795},{"className":794},[],[796],{"type":48,"value":797},"tables\u002Famplicon_diversity_summary.json",{"type":48,"value":500},{"type":42,"tag":120,"props":800,"children":802},{"className":801},[],[803],{"type":48,"value":804},"visualizations\u002Famplicon_backend_dashboard.html",{"type":48,"value":806},", and SVG plots for sample depth, Shannon diversity, and top taxa\u002Ffeatures. If the ASV table is absent, these outputs remain explicitly unavailable rather than inferred from FASTQ QC.",{"type":42,"tag":57,"props":808,"children":810},{"id":809},"guardrails",[811],{"type":48,"value":812},"Guardrails",{"type":42,"tag":69,"props":814,"children":815},{},[816,821,826],{"type":42,"tag":73,"props":817,"children":818},{},[819],{"type":48,"value":820},"Do not choose truncation lengths before looking at quality distributions.",{"type":42,"tag":73,"props":822,"children":823},{},[824],{"type":48,"value":825},"Do not mix taxonomy database versions without recording them.",{"type":42,"tag":73,"props":827,"children":828},{},[829],{"type":48,"value":830},"Preserve negative controls and extraction blanks in metadata.",{"type":42,"tag":832,"props":833,"children":834},"style",{},[835],{"type":48,"value":836},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":838,"total":959},[839,857,873,885,905,927,947],{"slug":840,"name":840,"fn":841,"description":842,"org":843,"tags":844,"stars":25,"repoUrl":26,"updatedAt":27},"accessibility-and-inclusive-visualization","make data visualizations accessible","Make data visualizations accessible and inclusive. Use when the user needs chart or diagram accessibility guidance, text alternatives for complex visuals, color and contrast review, keyboard support, reduced-motion behavior for animation or parallax, or an accessibility QA workflow for exported figures, UML-like diagrams, and dashboards.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[845,848,851,854],{"name":846,"slug":847,"type":15},"Accessibility","accessibility",{"name":849,"slug":850,"type":15},"Charts","charts",{"name":852,"slug":853,"type":15},"Data Visualization","data-visualization",{"name":855,"slug":856,"type":15},"Design","design",{"slug":858,"name":858,"fn":859,"description":860,"org":861,"tags":862,"stars":25,"repoUrl":26,"updatedAt":872},"agent-browser","automate browser interactions for agents","Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[863,866,869],{"name":864,"slug":865,"type":15},"Agents","agents",{"name":867,"slug":868,"type":15},"Browser Automation","browser-automation",{"name":870,"slug":871,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":874,"name":874,"fn":875,"description":876,"org":877,"tags":878,"stars":25,"repoUrl":26,"updatedAt":884},"agent-browser-verify","verify dev server output with automated browser","Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass\u002Ffail before continuing.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[879,880,883],{"name":867,"slug":868,"type":15},{"name":881,"slug":882,"type":15},"Local Development","local-development",{"name":870,"slug":871,"type":15},"2026-04-06T18:41:17.526867",{"slug":886,"name":886,"fn":887,"description":888,"org":889,"tags":890,"stars":25,"repoUrl":26,"updatedAt":904},"agents-sdk","build AI agents on Cloudflare Workers","Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[891,892,895,898,901],{"name":864,"slug":865,"type":15},{"name":893,"slug":894,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":896,"slug":897,"type":15},"SDK","sdk",{"name":899,"slug":900,"type":15},"Serverless","serverless",{"name":902,"slug":903,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":906,"name":906,"fn":907,"description":908,"org":909,"tags":910,"stars":25,"repoUrl":26,"updatedAt":926},"ai-elements","build chat UIs with AI Elements","AI Elements component library guidance — pre-built React components for AI interfaces built on shadcn\u002Fui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[911,914,917,920,923],{"name":912,"slug":913,"type":15},"Frontend","frontend",{"name":915,"slug":916,"type":15},"React","react",{"name":918,"slug":919,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":921,"slug":922,"type":15},"UI Components","ui-components",{"name":924,"slug":925,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":928,"name":928,"fn":929,"description":930,"org":931,"tags":932,"stars":25,"repoUrl":26,"updatedAt":946},"ai-gateway","configure Vercel AI Gateway","Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[933,936,939,942,945],{"name":934,"slug":935,"type":15},"AI Infrastructure","ai-infrastructure",{"name":937,"slug":938,"type":15},"Cost Optimization","cost-optimization",{"name":940,"slug":941,"type":15},"LLM","llm",{"name":943,"slug":944,"type":15},"Performance","performance",{"name":924,"slug":925,"type":15},"2026-04-06T18:40:44.377464",{"slug":948,"name":948,"fn":949,"description":950,"org":951,"tags":952,"stars":25,"repoUrl":26,"updatedAt":958},"ai-generation-persistence","implement persistence patterns for AI generations","AI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[953,954,957],{"name":937,"slug":938,"type":15},{"name":955,"slug":956,"type":15},"Database","database",{"name":940,"slug":941,"type":15},"2026-04-06T18:41:08.513425",600,{"items":961,"total":1158},[962,983,1006,1023,1039,1056,1075,1087,1101,1115,1127,1142],{"slug":963,"name":963,"fn":964,"description":965,"org":966,"tags":967,"stars":980,"repoUrl":981,"updatedAt":982},"prior-auth-packet-builder","build healthcare prior authorization packets","Build a concise prior authorization packet from local case files and payer policy docs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[968,971,974,977],{"name":969,"slug":970,"type":15},"Documents","documents",{"name":972,"slug":973,"type":15},"Healthcare","healthcare",{"name":975,"slug":976,"type":15},"Insurance","insurance",{"name":978,"slug":979,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":984,"name":984,"fn":985,"description":986,"org":987,"tags":988,"stars":1003,"repoUrl":1004,"updatedAt":1005},"aspnet-core","build ASP.NET Core web applications","Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[989,992,994,997,1000],{"name":990,"slug":991,"type":15},".NET","dotnet",{"name":993,"slug":984,"type":15},"ASP.NET Core",{"name":995,"slug":996,"type":15},"Blazor","blazor",{"name":998,"slug":999,"type":15},"C#","csharp",{"name":1001,"slug":1002,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1007,"name":1007,"fn":1008,"description":1009,"org":1010,"tags":1011,"stars":1003,"repoUrl":1004,"updatedAt":1022},"chatgpt-apps","build ChatGPT Apps SDK applications","Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1012,1015,1018,1021],{"name":1013,"slug":1014,"type":15},"Apps SDK","apps-sdk",{"name":1016,"slug":1017,"type":15},"ChatGPT","chatgpt",{"name":1019,"slug":1020,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1024,"name":1024,"fn":1025,"description":1026,"org":1027,"tags":1028,"stars":1003,"repoUrl":1004,"updatedAt":1038},"cli-creator","build CLIs from API docs","Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read\u002Fwrite commands, return stable JSON, manage auth, and pair with a companion skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1029,1032,1035],{"name":1030,"slug":1031,"type":15},"API Development","api-development",{"name":1033,"slug":1034,"type":15},"CLI","cli",{"name":1036,"slug":1037,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1040,"name":1040,"fn":1041,"description":1042,"org":1043,"tags":1044,"stars":1003,"repoUrl":1004,"updatedAt":1055},"cloudflare-deploy","deploy projects to Cloudflare","Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1045,1048,1051,1052],{"name":1046,"slug":1047,"type":15},"Cloudflare","cloudflare",{"name":1049,"slug":1050,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":893,"slug":894,"type":15},{"name":1053,"slug":1054,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1057,"name":1057,"fn":1058,"description":1059,"org":1060,"tags":1061,"stars":1003,"repoUrl":1004,"updatedAt":1074},"define-goal","define and set measurable project goals","Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1062,1065,1068,1071],{"name":1063,"slug":1064,"type":15},"Productivity","productivity",{"name":1066,"slug":1067,"type":15},"Project Management","project-management",{"name":1069,"slug":1070,"type":15},"Strategy","strategy",{"name":1072,"slug":1073,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1076,"name":1076,"fn":1077,"description":1078,"org":1079,"tags":1080,"stars":1003,"repoUrl":1004,"updatedAt":1086},"figma","translate Figma designs into code","Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1081,1082,1084,1085],{"name":855,"slug":856,"type":15},{"name":1083,"slug":1076,"type":15},"Figma",{"name":912,"slug":913,"type":15},{"name":1019,"slug":1020,"type":15},"2026-04-12T05:06:47.939943",{"slug":1088,"name":1088,"fn":1089,"description":1090,"org":1091,"tags":1092,"stars":1003,"repoUrl":1004,"updatedAt":1100},"figma-code-connect-components","connect Figma designs to code components","Connects Figma design components to code components using Code Connect mapping tools. Use when user says \"code connect\", \"connect this component to code\", \"map this component\", \"link component to code\", \"create code connect mapping\", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1093,1094,1097,1098,1099],{"name":855,"slug":856,"type":15},{"name":1095,"slug":1096,"type":15},"Design System","design-system",{"name":1083,"slug":1076,"type":15},{"name":912,"slug":913,"type":15},{"name":921,"slug":922,"type":15},"2026-05-10T05:59:52.971881",{"slug":1102,"name":1102,"fn":1103,"description":1104,"org":1105,"tags":1106,"stars":1003,"repoUrl":1004,"updatedAt":1114},"figma-create-design-system-rules","generate design system rules from Figma","Generates custom design system rules for the user's codebase. Use when user says \"create design system rules\", \"generate rules for my project\", \"set up design rules\", \"customize design system guidelines\", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1107,1108,1109,1112,1113],{"name":855,"slug":856,"type":15},{"name":1095,"slug":1096,"type":15},{"name":1110,"slug":1111,"type":15},"Documentation","documentation",{"name":1083,"slug":1076,"type":15},{"name":912,"slug":913,"type":15},"2026-05-16T06:07:47.821474",{"slug":1116,"name":1116,"fn":1117,"description":1118,"org":1119,"tags":1120,"stars":1003,"repoUrl":1004,"updatedAt":1126},"figma-implement-design","translate Figma designs into application code","Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions \"implement design\", \"generate code\", \"implement component\", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1121,1122,1123,1124,1125],{"name":855,"slug":856,"type":15},{"name":1083,"slug":1076,"type":15},{"name":912,"slug":913,"type":15},{"name":921,"slug":922,"type":15},{"name":1001,"slug":1002,"type":15},"2026-05-16T06:07:40.583615",{"slug":1128,"name":1128,"fn":1129,"description":1130,"org":1131,"tags":1132,"stars":1003,"repoUrl":1004,"updatedAt":1141},"hatch-pet","create animated pets for Codex","Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1133,1136,1137,1140],{"name":1134,"slug":1135,"type":15},"Animation","animation",{"name":1036,"slug":1037,"type":15},{"name":1138,"slug":1139,"type":15},"Creative","creative",{"name":855,"slug":856,"type":15},"2026-05-02T05:31:48.48485",{"slug":1143,"name":1143,"fn":1144,"description":1145,"org":1146,"tags":1147,"stars":1003,"repoUrl":1004,"updatedAt":1157},"imagegen","generate and edit raster images","Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG\u002Fvector\u002Fcode-native assets, extending an established icon or logo system, or building the visual directly in HTML\u002FCSS\u002Fcanvas.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1148,1149,1150,1153,1156],{"name":1138,"slug":1139,"type":15},{"name":855,"slug":856,"type":15},{"name":1151,"slug":1152,"type":15},"Image Generation","image-generation",{"name":1154,"slug":1155,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]