[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-ngs-bcl-to-fastq":3,"mdc--lhr8vp-key":36,"related-repo-openai-ngs-bcl-to-fastq":631,"related-org-openai-ngs-bcl-to-fastq":754},{"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-bcl-to-fastq","convert Illumina BCL to FASTQ","Validate Illumina BCL run folders and sample sheets, plan demultiplexing, review index\u002FUMI\u002Flane choices, run BCL-to-FASTQ conversion, and interpret demux metrics while surfacing license\u002Fdownload boundaries.",{"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},"Bioinformatics","bioinformatics","tag",{"name":17,"slug":18,"type":15},"RNA-seq","rna-seq",{"name":20,"slug":21,"type":15},"Laboratory","laboratory",{"name":23,"slug":24,"type":15},"Genomics","genomics",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-bcl-to-fastq","---\nname: ngs-bcl-to-fastq\ndescription: Validate Illumina BCL run folders and sample sheets, plan demultiplexing, review index\u002FUMI\u002Flane choices, run BCL-to-FASTQ conversion, and interpret demux metrics while surfacing license\u002Fdownload boundaries.\n---\n\n# BCL To FASTQ\n\nUse this skill when the input is an Illumina BCL run folder or the user asks to demultiplex a sequencing run. This is a deep demultiplexing and run-validation skill, not only a command wrapper.\n\n## Essential Inputs\n\nConfirm:\n\n- run folder path with `RunInfo.xml`\n- sample sheet path and format\n- output directory\n- instrument\u002Frun metadata from `RunInfo.xml` and `RunParameters.xml`\n- lane handling: split by lane or combine lanes\n- index mismatch tolerance\n- index read structure and dual-index orientation\n- UMI layout, if any\n- whether adapter trimming\u002Fmasking should happen during conversion\n- whether undetermined reads and demultiplexing metrics should be reviewed before downstream analysis\n\n## Public Tool Boundary\n\nPrefer `bcl-convert` if it is already installed. It is free for local use but proprietary and RPM-distributed by Illumina, so do not auto-download without explicit user approval.\n\nLegacy `bcl2fastq` may exist in older environments. Use it only when BCL Convert is unavailable or the run requires legacy compatibility.\n\n## Preflight\n\n```bash\npython plugins\u002Fngs-analysis\u002Fscripts\u002Fngs_preflight.py --pipeline bcl_to_fastq --emit-install-plan\n```\n\nAlso check run-folder structure:\n\n```bash\ntest -f \u002Fpath\u002Fto\u002Frun\u002FRunInfo.xml\ntest -f \u002Fpath\u002Fto\u002FSampleSheet.csv\nfind \u002Fpath\u002Fto\u002Frun -maxdepth 4 -type d -name BaseCalls\n```\n\n## Local Execution Package\n\nUse the plugin-owned runner when the user provides a local run folder and sample sheet:\n\n```bash\npython plugins\u002Fngs-analysis\u002Fscripts\u002Frun_bcl_to_fastq.py \\\n  --run-folder \u002Fpath\u002Fto\u002Frun \\\n  --sample-sheet \u002Fpath\u002Fto\u002FSampleSheet.csv \\\n  --output-directory \u002Fpath\u002Fto\u002Ffastq_out\n```\n\nAdd `--execute` only when conversion is requested. The runner validates `RunInfo.xml`, optional `RunParameters.xml`, the BaseCalls directory, sample-sheet rows, duplicate lane\u002Findex combinations, and index length compatibility. With `--execute`, it uses installed `bcl-convert`, then legacy `bcl2fastq` if available; if neither exists, it records the blocker instead of downloading proprietary software.\n\n## Validation Checklist\n\nBefore conversion, validate:\n\n- `RunInfo.xml` exists and its read structure matches the expected sequencing design.\n- `SampleSheet.csv` exists, is the intended version, and has no duplicate sample\u002Findex combinations within each lane.\n- Index sequence lengths match the index reads and any trimming\u002Fmasking requested by the sample sheet.\n- Dual-index orientation is explicit for the instrument and library prep; do not infer i5 orientation from filenames.\n- UMI bases are assigned to the intended read or index read and carried through to FASTQ headers or output metadata as needed.\n- Lane-splitting, sample-name normalization, and output directory behavior are agreed before running.\n- Disk space is sufficient for output FASTQs, reports, and temporary files.\n\n## Kickoff Pattern\n\nFirst produce a preflight plan with paths and sample sheet validation. Then run conversion only after the user confirms:\n\n```bash\nbcl-convert \\\n  --bcl-input-directory \u002Fpath\u002Fto\u002Frun \\\n  --output-directory \u002Fpath\u002Fto\u002Ffastq_out \\\n  --sample-sheet \u002Fpath\u002Fto\u002FSampleSheet.csv\n```\n\n## Metrics Review\n\nAfter conversion, inspect and report:\n\n- total clusters, clusters passing filter, and yield by lane\n- percent assigned by sample and percent undetermined by lane\n- top undetermined index sequences when available\n- per-sample FASTQ counts and read-pair consistency\n- unexpected index hopping, barcode collision, or sample-sheet mismatch signals\n\nRecord software version, command, sample sheet checksum, run-folder path, output path, and conversion metrics. Do not start downstream analysis until severe demultiplexing anomalies are surfaced.\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,56,63,68,143,149,162,175,181,225,230,318,324,329,401,449,455,460,509,515,520,581,587,592,620,625],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"bcl-to-fastq",[47],{"type":48,"value":49},"text","BCL To FASTQ",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54],{"type":48,"value":55},"Use this skill when the input is an Illumina BCL run folder or the user asks to demultiplex a sequencing run. This is a deep demultiplexing and run-validation skill, not only a command wrapper.",{"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",{},[72,85,90,95,113,118,123,128,133,138],{"type":42,"tag":73,"props":74,"children":75},"li",{},[76,78],{"type":48,"value":77},"run folder path with ",{"type":42,"tag":79,"props":80,"children":82},"code",{"className":81},[],[83],{"type":48,"value":84},"RunInfo.xml",{"type":42,"tag":73,"props":86,"children":87},{},[88],{"type":48,"value":89},"sample sheet path and format",{"type":42,"tag":73,"props":91,"children":92},{},[93],{"type":48,"value":94},"output directory",{"type":42,"tag":73,"props":96,"children":97},{},[98,100,105,107],{"type":48,"value":99},"instrument\u002Frun metadata from ",{"type":42,"tag":79,"props":101,"children":103},{"className":102},[],[104],{"type":48,"value":84},{"type":48,"value":106}," and ",{"type":42,"tag":79,"props":108,"children":110},{"className":109},[],[111],{"type":48,"value":112},"RunParameters.xml",{"type":42,"tag":73,"props":114,"children":115},{},[116],{"type":48,"value":117},"lane handling: split by lane or combine lanes",{"type":42,"tag":73,"props":119,"children":120},{},[121],{"type":48,"value":122},"index mismatch tolerance",{"type":42,"tag":73,"props":124,"children":125},{},[126],{"type":48,"value":127},"index read structure and dual-index orientation",{"type":42,"tag":73,"props":129,"children":130},{},[131],{"type":48,"value":132},"UMI layout, if any",{"type":42,"tag":73,"props":134,"children":135},{},[136],{"type":48,"value":137},"whether adapter trimming\u002Fmasking should happen during conversion",{"type":42,"tag":73,"props":139,"children":140},{},[141],{"type":48,"value":142},"whether undetermined reads and demultiplexing metrics should be reviewed before downstream analysis",{"type":42,"tag":57,"props":144,"children":146},{"id":145},"public-tool-boundary",[147],{"type":48,"value":148},"Public Tool Boundary",{"type":42,"tag":51,"props":150,"children":151},{},[152,154,160],{"type":48,"value":153},"Prefer ",{"type":42,"tag":79,"props":155,"children":157},{"className":156},[],[158],{"type":48,"value":159},"bcl-convert",{"type":48,"value":161}," if it is already installed. It is free for local use but proprietary and RPM-distributed by Illumina, so do not auto-download without explicit user approval.",{"type":42,"tag":51,"props":163,"children":164},{},[165,167,173],{"type":48,"value":166},"Legacy ",{"type":42,"tag":79,"props":168,"children":170},{"className":169},[],[171],{"type":48,"value":172},"bcl2fastq",{"type":48,"value":174}," may exist in older environments. Use it only when BCL Convert is unavailable or the run requires legacy compatibility.",{"type":42,"tag":57,"props":176,"children":178},{"id":177},"preflight",[179],{"type":48,"value":180},"Preflight",{"type":42,"tag":182,"props":183,"children":188},"pre",{"className":184,"code":185,"language":186,"meta":187,"style":187},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","python plugins\u002Fngs-analysis\u002Fscripts\u002Fngs_preflight.py --pipeline bcl_to_fastq --emit-install-plan\n","bash","",[189],{"type":42,"tag":79,"props":190,"children":191},{"__ignoreMap":187},[192],{"type":42,"tag":193,"props":194,"children":197},"span",{"class":195,"line":196},"line",1,[198,204,210,215,220],{"type":42,"tag":193,"props":199,"children":201},{"style":200},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[202],{"type":48,"value":203},"python",{"type":42,"tag":193,"props":205,"children":207},{"style":206},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[208],{"type":48,"value":209}," plugins\u002Fngs-analysis\u002Fscripts\u002Fngs_preflight.py",{"type":42,"tag":193,"props":211,"children":212},{"style":206},[213],{"type":48,"value":214}," --pipeline",{"type":42,"tag":193,"props":216,"children":217},{"style":206},[218],{"type":48,"value":219}," bcl_to_fastq",{"type":42,"tag":193,"props":221,"children":222},{"style":206},[223],{"type":48,"value":224}," --emit-install-plan\n",{"type":42,"tag":51,"props":226,"children":227},{},[228],{"type":48,"value":229},"Also check run-folder structure:",{"type":42,"tag":182,"props":231,"children":233},{"className":184,"code":232,"language":186,"meta":187,"style":187},"test -f \u002Fpath\u002Fto\u002Frun\u002FRunInfo.xml\ntest -f \u002Fpath\u002Fto\u002FSampleSheet.csv\nfind \u002Fpath\u002Fto\u002Frun -maxdepth 4 -type d -name BaseCalls\n",[234],{"type":42,"tag":79,"props":235,"children":236},{"__ignoreMap":187},[237,256,273],{"type":42,"tag":193,"props":238,"children":239},{"class":195,"line":196},[240,246,251],{"type":42,"tag":193,"props":241,"children":243},{"style":242},"--shiki-light:#6182B8;--shiki-default:#82AAFF;--shiki-dark:#82AAFF",[244],{"type":48,"value":245},"test",{"type":42,"tag":193,"props":247,"children":248},{"style":206},[249],{"type":48,"value":250}," -f",{"type":42,"tag":193,"props":252,"children":253},{"style":206},[254],{"type":48,"value":255}," \u002Fpath\u002Fto\u002Frun\u002FRunInfo.xml\n",{"type":42,"tag":193,"props":257,"children":259},{"class":195,"line":258},2,[260,264,268],{"type":42,"tag":193,"props":261,"children":262},{"style":242},[263],{"type":48,"value":245},{"type":42,"tag":193,"props":265,"children":266},{"style":206},[267],{"type":48,"value":250},{"type":42,"tag":193,"props":269,"children":270},{"style":206},[271],{"type":48,"value":272}," \u002Fpath\u002Fto\u002FSampleSheet.csv\n",{"type":42,"tag":193,"props":274,"children":276},{"class":195,"line":275},3,[277,282,287,292,298,303,308,313],{"type":42,"tag":193,"props":278,"children":279},{"style":200},[280],{"type":48,"value":281},"find",{"type":42,"tag":193,"props":283,"children":284},{"style":206},[285],{"type":48,"value":286}," \u002Fpath\u002Fto\u002Frun",{"type":42,"tag":193,"props":288,"children":289},{"style":206},[290],{"type":48,"value":291}," -maxdepth",{"type":42,"tag":193,"props":293,"children":295},{"style":294},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[296],{"type":48,"value":297}," 4",{"type":42,"tag":193,"props":299,"children":300},{"style":206},[301],{"type":48,"value":302}," -type",{"type":42,"tag":193,"props":304,"children":305},{"style":206},[306],{"type":48,"value":307}," d",{"type":42,"tag":193,"props":309,"children":310},{"style":206},[311],{"type":48,"value":312}," -name",{"type":42,"tag":193,"props":314,"children":315},{"style":206},[316],{"type":48,"value":317}," BaseCalls\n",{"type":42,"tag":57,"props":319,"children":321},{"id":320},"local-execution-package",[322],{"type":48,"value":323},"Local Execution Package",{"type":42,"tag":51,"props":325,"children":326},{},[327],{"type":48,"value":328},"Use the plugin-owned runner when the user provides a local run folder and sample sheet:",{"type":42,"tag":182,"props":330,"children":332},{"className":184,"code":331,"language":186,"meta":187,"style":187},"python plugins\u002Fngs-analysis\u002Fscripts\u002Frun_bcl_to_fastq.py \\\n  --run-folder \u002Fpath\u002Fto\u002Frun \\\n  --sample-sheet \u002Fpath\u002Fto\u002FSampleSheet.csv \\\n  --output-directory \u002Fpath\u002Fto\u002Ffastq_out\n",[333],{"type":42,"tag":79,"props":334,"children":335},{"__ignoreMap":187},[336,354,370,387],{"type":42,"tag":193,"props":337,"children":338},{"class":195,"line":196},[339,343,348],{"type":42,"tag":193,"props":340,"children":341},{"style":200},[342],{"type":48,"value":203},{"type":42,"tag":193,"props":344,"children":345},{"style":206},[346],{"type":48,"value":347}," plugins\u002Fngs-analysis\u002Fscripts\u002Frun_bcl_to_fastq.py",{"type":42,"tag":193,"props":349,"children":351},{"style":350},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[352],{"type":48,"value":353}," \\\n",{"type":42,"tag":193,"props":355,"children":356},{"class":195,"line":258},[357,362,366],{"type":42,"tag":193,"props":358,"children":359},{"style":206},[360],{"type":48,"value":361},"  --run-folder",{"type":42,"tag":193,"props":363,"children":364},{"style":206},[365],{"type":48,"value":286},{"type":42,"tag":193,"props":367,"children":368},{"style":350},[369],{"type":48,"value":353},{"type":42,"tag":193,"props":371,"children":372},{"class":195,"line":275},[373,378,383],{"type":42,"tag":193,"props":374,"children":375},{"style":206},[376],{"type":48,"value":377},"  --sample-sheet",{"type":42,"tag":193,"props":379,"children":380},{"style":206},[381],{"type":48,"value":382}," \u002Fpath\u002Fto\u002FSampleSheet.csv",{"type":42,"tag":193,"props":384,"children":385},{"style":350},[386],{"type":48,"value":353},{"type":42,"tag":193,"props":388,"children":390},{"class":195,"line":389},4,[391,396],{"type":42,"tag":193,"props":392,"children":393},{"style":206},[394],{"type":48,"value":395},"  --output-directory",{"type":42,"tag":193,"props":397,"children":398},{"style":206},[399],{"type":48,"value":400}," \u002Fpath\u002Fto\u002Ffastq_out\n",{"type":42,"tag":51,"props":402,"children":403},{},[404,406,412,414,419,421,426,428,433,435,440,442,447],{"type":48,"value":405},"Add ",{"type":42,"tag":79,"props":407,"children":409},{"className":408},[],[410],{"type":48,"value":411},"--execute",{"type":48,"value":413}," only when conversion is requested. The runner validates ",{"type":42,"tag":79,"props":415,"children":417},{"className":416},[],[418],{"type":48,"value":84},{"type":48,"value":420},", optional ",{"type":42,"tag":79,"props":422,"children":424},{"className":423},[],[425],{"type":48,"value":112},{"type":48,"value":427},", the BaseCalls directory, sample-sheet rows, duplicate lane\u002Findex combinations, and index length compatibility. With ",{"type":42,"tag":79,"props":429,"children":431},{"className":430},[],[432],{"type":48,"value":411},{"type":48,"value":434},", it uses installed ",{"type":42,"tag":79,"props":436,"children":438},{"className":437},[],[439],{"type":48,"value":159},{"type":48,"value":441},", then legacy ",{"type":42,"tag":79,"props":443,"children":445},{"className":444},[],[446],{"type":48,"value":172},{"type":48,"value":448}," if available; if neither exists, it records the blocker instead of downloading proprietary software.",{"type":42,"tag":57,"props":450,"children":452},{"id":451},"validation-checklist",[453],{"type":48,"value":454},"Validation Checklist",{"type":42,"tag":51,"props":456,"children":457},{},[458],{"type":48,"value":459},"Before conversion, validate:",{"type":42,"tag":69,"props":461,"children":462},{},[463,473,484,489,494,499,504],{"type":42,"tag":73,"props":464,"children":465},{},[466,471],{"type":42,"tag":79,"props":467,"children":469},{"className":468},[],[470],{"type":48,"value":84},{"type":48,"value":472}," exists and its read structure matches the expected sequencing design.",{"type":42,"tag":73,"props":474,"children":475},{},[476,482],{"type":42,"tag":79,"props":477,"children":479},{"className":478},[],[480],{"type":48,"value":481},"SampleSheet.csv",{"type":48,"value":483}," exists, is the intended version, and has no duplicate sample\u002Findex combinations within each lane.",{"type":42,"tag":73,"props":485,"children":486},{},[487],{"type":48,"value":488},"Index sequence lengths match the index reads and any trimming\u002Fmasking requested by the sample sheet.",{"type":42,"tag":73,"props":490,"children":491},{},[492],{"type":48,"value":493},"Dual-index orientation is explicit for the instrument and library prep; do not infer i5 orientation from filenames.",{"type":42,"tag":73,"props":495,"children":496},{},[497],{"type":48,"value":498},"UMI bases are assigned to the intended read or index read and carried through to FASTQ headers or output metadata as needed.",{"type":42,"tag":73,"props":500,"children":501},{},[502],{"type":48,"value":503},"Lane-splitting, sample-name normalization, and output directory behavior are agreed before running.",{"type":42,"tag":73,"props":505,"children":506},{},[507],{"type":48,"value":508},"Disk space is sufficient for output FASTQs, reports, and temporary files.",{"type":42,"tag":57,"props":510,"children":512},{"id":511},"kickoff-pattern",[513],{"type":48,"value":514},"Kickoff Pattern",{"type":42,"tag":51,"props":516,"children":517},{},[518],{"type":48,"value":519},"First produce a preflight plan with paths and sample sheet validation. Then run conversion only after the user confirms:",{"type":42,"tag":182,"props":521,"children":523},{"className":184,"code":522,"language":186,"meta":187,"style":187},"bcl-convert \\\n  --bcl-input-directory \u002Fpath\u002Fto\u002Frun \\\n  --output-directory \u002Fpath\u002Fto\u002Ffastq_out \\\n  --sample-sheet \u002Fpath\u002Fto\u002FSampleSheet.csv\n",[524],{"type":42,"tag":79,"props":525,"children":526},{"__ignoreMap":187},[527,538,554,570],{"type":42,"tag":193,"props":528,"children":529},{"class":195,"line":196},[530,534],{"type":42,"tag":193,"props":531,"children":532},{"style":200},[533],{"type":48,"value":159},{"type":42,"tag":193,"props":535,"children":536},{"style":350},[537],{"type":48,"value":353},{"type":42,"tag":193,"props":539,"children":540},{"class":195,"line":258},[541,546,550],{"type":42,"tag":193,"props":542,"children":543},{"style":206},[544],{"type":48,"value":545},"  --bcl-input-directory",{"type":42,"tag":193,"props":547,"children":548},{"style":206},[549],{"type":48,"value":286},{"type":42,"tag":193,"props":551,"children":552},{"style":350},[553],{"type":48,"value":353},{"type":42,"tag":193,"props":555,"children":556},{"class":195,"line":275},[557,561,566],{"type":42,"tag":193,"props":558,"children":559},{"style":206},[560],{"type":48,"value":395},{"type":42,"tag":193,"props":562,"children":563},{"style":206},[564],{"type":48,"value":565}," \u002Fpath\u002Fto\u002Ffastq_out",{"type":42,"tag":193,"props":567,"children":568},{"style":350},[569],{"type":48,"value":353},{"type":42,"tag":193,"props":571,"children":572},{"class":195,"line":389},[573,577],{"type":42,"tag":193,"props":574,"children":575},{"style":206},[576],{"type":48,"value":377},{"type":42,"tag":193,"props":578,"children":579},{"style":206},[580],{"type":48,"value":272},{"type":42,"tag":57,"props":582,"children":584},{"id":583},"metrics-review",[585],{"type":48,"value":586},"Metrics Review",{"type":42,"tag":51,"props":588,"children":589},{},[590],{"type":48,"value":591},"After conversion, inspect and report:",{"type":42,"tag":69,"props":593,"children":594},{},[595,600,605,610,615],{"type":42,"tag":73,"props":596,"children":597},{},[598],{"type":48,"value":599},"total clusters, clusters passing filter, and yield by lane",{"type":42,"tag":73,"props":601,"children":602},{},[603],{"type":48,"value":604},"percent assigned by sample and percent undetermined by lane",{"type":42,"tag":73,"props":606,"children":607},{},[608],{"type":48,"value":609},"top undetermined index sequences when available",{"type":42,"tag":73,"props":611,"children":612},{},[613],{"type":48,"value":614},"per-sample FASTQ counts and read-pair consistency",{"type":42,"tag":73,"props":616,"children":617},{},[618],{"type":48,"value":619},"unexpected index hopping, barcode collision, or sample-sheet mismatch signals",{"type":42,"tag":51,"props":621,"children":622},{},[623],{"type":48,"value":624},"Record software version, command, sample sheet checksum, run-folder path, output path, and conversion metrics. Do not start downstream analysis until severe demultiplexing anomalies are surfaced.",{"type":42,"tag":626,"props":627,"children":628},"style",{},[629],{"type":48,"value":630},"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":632,"total":753},[633,651,667,679,699,721,741],{"slug":634,"name":634,"fn":635,"description":636,"org":637,"tags":638,"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},[639,642,645,648],{"name":640,"slug":641,"type":15},"Accessibility","accessibility",{"name":643,"slug":644,"type":15},"Charts","charts",{"name":646,"slug":647,"type":15},"Data Visualization","data-visualization",{"name":649,"slug":650,"type":15},"Design","design",{"slug":652,"name":652,"fn":653,"description":654,"org":655,"tags":656,"stars":25,"repoUrl":26,"updatedAt":666},"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},[657,660,663],{"name":658,"slug":659,"type":15},"Agents","agents",{"name":661,"slug":662,"type":15},"Browser Automation","browser-automation",{"name":664,"slug":665,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":668,"name":668,"fn":669,"description":670,"org":671,"tags":672,"stars":25,"repoUrl":26,"updatedAt":678},"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},[673,674,677],{"name":661,"slug":662,"type":15},{"name":675,"slug":676,"type":15},"Local Development","local-development",{"name":664,"slug":665,"type":15},"2026-04-06T18:41:17.526867",{"slug":680,"name":680,"fn":681,"description":682,"org":683,"tags":684,"stars":25,"repoUrl":26,"updatedAt":698},"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},[685,686,689,692,695],{"name":658,"slug":659,"type":15},{"name":687,"slug":688,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":690,"slug":691,"type":15},"SDK","sdk",{"name":693,"slug":694,"type":15},"Serverless","serverless",{"name":696,"slug":697,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":700,"name":700,"fn":701,"description":702,"org":703,"tags":704,"stars":25,"repoUrl":26,"updatedAt":720},"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},[705,708,711,714,717],{"name":706,"slug":707,"type":15},"Frontend","frontend",{"name":709,"slug":710,"type":15},"React","react",{"name":712,"slug":713,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":715,"slug":716,"type":15},"UI Components","ui-components",{"name":718,"slug":719,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":722,"name":722,"fn":723,"description":724,"org":725,"tags":726,"stars":25,"repoUrl":26,"updatedAt":740},"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},[727,730,733,736,739],{"name":728,"slug":729,"type":15},"AI Infrastructure","ai-infrastructure",{"name":731,"slug":732,"type":15},"Cost Optimization","cost-optimization",{"name":734,"slug":735,"type":15},"LLM","llm",{"name":737,"slug":738,"type":15},"Performance","performance",{"name":718,"slug":719,"type":15},"2026-04-06T18:40:44.377464",{"slug":742,"name":742,"fn":743,"description":744,"org":745,"tags":746,"stars":25,"repoUrl":26,"updatedAt":752},"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},[747,748,751],{"name":731,"slug":732,"type":15},{"name":749,"slug":750,"type":15},"Database","database",{"name":734,"slug":735,"type":15},"2026-04-06T18:41:08.513425",600,{"items":755,"total":952},[756,777,800,817,833,850,869,881,895,909,921,936],{"slug":757,"name":757,"fn":758,"description":759,"org":760,"tags":761,"stars":774,"repoUrl":775,"updatedAt":776},"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},[762,765,768,771],{"name":763,"slug":764,"type":15},"Documents","documents",{"name":766,"slug":767,"type":15},"Healthcare","healthcare",{"name":769,"slug":770,"type":15},"Insurance","insurance",{"name":772,"slug":773,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":778,"name":778,"fn":779,"description":780,"org":781,"tags":782,"stars":797,"repoUrl":798,"updatedAt":799},"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},[783,786,788,791,794],{"name":784,"slug":785,"type":15},".NET","dotnet",{"name":787,"slug":778,"type":15},"ASP.NET Core",{"name":789,"slug":790,"type":15},"Blazor","blazor",{"name":792,"slug":793,"type":15},"C#","csharp",{"name":795,"slug":796,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":801,"name":801,"fn":802,"description":803,"org":804,"tags":805,"stars":797,"repoUrl":798,"updatedAt":816},"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},[806,809,812,815],{"name":807,"slug":808,"type":15},"Apps SDK","apps-sdk",{"name":810,"slug":811,"type":15},"ChatGPT","chatgpt",{"name":813,"slug":814,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":818,"name":818,"fn":819,"description":820,"org":821,"tags":822,"stars":797,"repoUrl":798,"updatedAt":832},"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},[823,826,829],{"name":824,"slug":825,"type":15},"API Development","api-development",{"name":827,"slug":828,"type":15},"CLI","cli",{"name":830,"slug":831,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":834,"name":834,"fn":835,"description":836,"org":837,"tags":838,"stars":797,"repoUrl":798,"updatedAt":849},"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},[839,842,845,846],{"name":840,"slug":841,"type":15},"Cloudflare","cloudflare",{"name":843,"slug":844,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":687,"slug":688,"type":15},{"name":847,"slug":848,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":851,"name":851,"fn":852,"description":853,"org":854,"tags":855,"stars":797,"repoUrl":798,"updatedAt":868},"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},[856,859,862,865],{"name":857,"slug":858,"type":15},"Productivity","productivity",{"name":860,"slug":861,"type":15},"Project Management","project-management",{"name":863,"slug":864,"type":15},"Strategy","strategy",{"name":866,"slug":867,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":870,"name":870,"fn":871,"description":872,"org":873,"tags":874,"stars":797,"repoUrl":798,"updatedAt":880},"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},[875,876,878,879],{"name":649,"slug":650,"type":15},{"name":877,"slug":870,"type":15},"Figma",{"name":706,"slug":707,"type":15},{"name":813,"slug":814,"type":15},"2026-04-12T05:06:47.939943",{"slug":882,"name":882,"fn":883,"description":884,"org":885,"tags":886,"stars":797,"repoUrl":798,"updatedAt":894},"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},[887,888,891,892,893],{"name":649,"slug":650,"type":15},{"name":889,"slug":890,"type":15},"Design System","design-system",{"name":877,"slug":870,"type":15},{"name":706,"slug":707,"type":15},{"name":715,"slug":716,"type":15},"2026-05-10T05:59:52.971881",{"slug":896,"name":896,"fn":897,"description":898,"org":899,"tags":900,"stars":797,"repoUrl":798,"updatedAt":908},"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},[901,902,903,906,907],{"name":649,"slug":650,"type":15},{"name":889,"slug":890,"type":15},{"name":904,"slug":905,"type":15},"Documentation","documentation",{"name":877,"slug":870,"type":15},{"name":706,"slug":707,"type":15},"2026-05-16T06:07:47.821474",{"slug":910,"name":910,"fn":911,"description":912,"org":913,"tags":914,"stars":797,"repoUrl":798,"updatedAt":920},"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},[915,916,917,918,919],{"name":649,"slug":650,"type":15},{"name":877,"slug":870,"type":15},{"name":706,"slug":707,"type":15},{"name":715,"slug":716,"type":15},{"name":795,"slug":796,"type":15},"2026-05-16T06:07:40.583615",{"slug":922,"name":922,"fn":923,"description":924,"org":925,"tags":926,"stars":797,"repoUrl":798,"updatedAt":935},"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},[927,930,931,934],{"name":928,"slug":929,"type":15},"Animation","animation",{"name":830,"slug":831,"type":15},{"name":932,"slug":933,"type":15},"Creative","creative",{"name":649,"slug":650,"type":15},"2026-05-02T05:31:48.48485",{"slug":937,"name":937,"fn":938,"description":939,"org":940,"tags":941,"stars":797,"repoUrl":798,"updatedAt":951},"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},[942,943,944,947,950],{"name":932,"slug":933,"type":15},{"name":649,"slug":650,"type":15},{"name":945,"slug":946,"type":15},"Image Generation","image-generation",{"name":948,"slug":949,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]