[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-ngs-chip-cutrun-peaks-qc":3,"mdc-jt4id2-key":36,"related-org-openai-ngs-chip-cutrun-peaks-qc":636,"related-repo-openai-ngs-chip-cutrun-peaks-qc":843},{"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-chip-cutrun-peaks-qc","run ChIP-seq and CUT&RUN analysis workflows","Run or plan ChIP-seq, CUT&RUN, or CUT&Tag QC, control handling, spike-in, peak calling, broad-vs-narrow target selection, replicate, bigWig, and differential binding workflows.",{"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},"Data Analysis","data-analysis","tag",{"name":17,"slug":18,"type":15},"Life Sciences","life-sciences",{"name":20,"slug":21,"type":15},"Bioinformatics","bioinformatics",{"name":23,"slug":24,"type":15},"RNA-seq","rna-seq",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-chip-cutrun-peaks-qc","---\nname: ngs-chip-cutrun-peaks-qc\ndescription: Run or plan ChIP-seq, CUT&RUN, or CUT&Tag QC, control handling, spike-in, peak calling, broad-vs-narrow target selection, replicate, bigWig, and differential binding workflows.\n---\n\n# ChIP\u002FCUT&RUN Peaks QC\n\nUse this skill for antibody-targeted enrichment workflows: ChIP-seq, CUT&RUN, or CUT&Tag. Use `ngs-atacseq-peaks-qc` for ATAC-seq.\n\n## Essential Inputs\n\nConfirm:\n\n- assay: ChIP-seq, CUT&RUN, or CUT&Tag\n- target class: transcription factor, histone mark, chromatin regulator, or custom target\n- FASTQ\u002FBAM inputs and paired-end status\n- input DNA, IgG, no-antibody, or spike-in controls\n- organism, genome build, blacklist, and spike-in genome if used\n- biological replicates, conditions, batches, and sample metadata\n- desired endpoint: QC, peaks, bigWigs, consensus peaks, or differential binding\n\n## Route\n\nUse `nf-core\u002Fchipseq` for ChIP-seq and `nf-core\u002Fcutandrun` for CUT&RUN\u002FCUT&Tag when they fit the assay. Use direct MACS2 only for prepared BAMs with known control and duplicate policy.\n\nPreflight command:\n\n```bash\npython plugins\u002Fngs-analysis\u002Fscripts\u002Fngs_preflight.py --pipeline chip_cutrun_peaks_qc --emit-install-plan\n```\n\nFor compact FASTQ intake\u002FQC, use the shared epigenomics execution package:\n\n```bash\npython plugins\u002Fngs-analysis\u002Fscripts\u002Frun_fastq_assay_package.py \\\n  --lane epigenomics_peaks \\\n  --sample-sheet chip_or_cutrun_samples.csv \\\n  --execute\n```\n\nIt records FASTQ-level QC and peak-calling readiness.\n\nFor local-light alignment, control-aware MACS2 peak calling, FRiP, bigWig tracks, consensus peaks, and motif-handoff artifacts, use the dedicated ChIP\u002FCUT&RUN runner:\n\n```bash\npython plugins\u002Fngs-analysis\u002Fscripts\u002Frun_chip_cutrun_peaks_qc.py \\\n  --sample-sheet chip_or_cutrun_samples.csv \\\n  --assay chipseq \\\n  --target-class tf \\\n  --peak-mode narrow \\\n  --bowtie2-index \u002Frefs\u002FGRCh38\u002Fbowtie2\u002Fgenome \\\n  --genome-size hs \\\n  --blacklist-bed \u002Frefs\u002FGRCh38\u002Fblacklists\u002Fencode_blacklist.bed \\\n  --execute\n```\n\nThis runner emits `qc\u002Fchip_cutrun_qc_summary.{tsv,json}`, `qc\u002Fchip_cutrun_qc_dashboard.html`, native SVG FRiP\u002Fpeak and insert-size plots, browser-track handoff files under `tracks\u002F`, and `motifs\u002Fmotif_summary.tsv`. Add `--run-motifs --motif-genome \u003Cgenome>` when HOMER motif enrichment should be executed instead of only planned.\n\nIt also emits `resources\u002Fresource_plan.json`, `resource_manifest.tsv`, `resource_env.sh`, and `resource_readiness.md`. The resource check is advisory by default for local-light runs; add `--genome-build`, `--bundle-root \u003Cbundle>=\u003Cpath>`, and `--require-resource-plan` when missing registered reference bundles should block readiness.\n\nFor nf-core execution, use `plugins\u002Fngs-analysis\u002Fscripts\u002Frun_nfcore_pipeline.py --pipeline chipseq` or `--pipeline cutandrun`.\n\n## Decision Points\n\n- Choose narrow versus broad peak mode from target biology, not from convenience.\n- Preserve control pairing and spike-in metadata through sample sheets.\n- For histone marks, expect broad or domain-like signal for many marks; for TFs, expect sharper peaks and stronger replicate checks.\n- Review alignment rate, duplicate rate, fragment size, FRiP\u002Fpeak signal, blacklist overlap, and replicate concordance.\n- Keep consensus peak generation and differential binding design separate from raw peak calling.\n\n## Outputs\n\nProduce:\n\n- assay\u002Ftarget\u002Fcontrol manifest\n- command\u002Fprofile and sample sheet\n- QC summary with replicate\u002Fcontrol status\n- peaks, bigWigs, browser-track manifests, browser-track preview HTML, native QC dashboard\u002FSVG plots, consensus peaks, and count matrix when requested\n- motif summary files when a motif backend is requested\n- differential binding design and caveats for missing controls, weak enrichment, or poor replicate concordance\n",{"data":37,"body":38},{"name":4,"description":6},{"type":39,"children":40},"root",[41,50,65,72,77,117,123,144,149,193,198,268,273,278,430,475,531,552,558,586,592,597,630],{"type":42,"tag":43,"props":44,"children":46},"element","h1",{"id":45},"chipcutrun-peaks-qc",[47],{"type":48,"value":49},"text","ChIP\u002FCUT&RUN Peaks QC",{"type":42,"tag":51,"props":52,"children":53},"p",{},[54,56,63],{"type":48,"value":55},"Use this skill for antibody-targeted enrichment workflows: ChIP-seq, CUT&RUN, or CUT&Tag. Use ",{"type":42,"tag":57,"props":58,"children":60},"code",{"className":59},[],[61],{"type":48,"value":62},"ngs-atacseq-peaks-qc",{"type":48,"value":64}," for ATAC-seq.",{"type":42,"tag":66,"props":67,"children":69},"h2",{"id":68},"essential-inputs",[70],{"type":48,"value":71},"Essential Inputs",{"type":42,"tag":51,"props":73,"children":74},{},[75],{"type":48,"value":76},"Confirm:",{"type":42,"tag":78,"props":79,"children":80},"ul",{},[81,87,92,97,102,107,112],{"type":42,"tag":82,"props":83,"children":84},"li",{},[85],{"type":48,"value":86},"assay: ChIP-seq, CUT&RUN, or CUT&Tag",{"type":42,"tag":82,"props":88,"children":89},{},[90],{"type":48,"value":91},"target class: transcription factor, histone mark, chromatin regulator, or custom target",{"type":42,"tag":82,"props":93,"children":94},{},[95],{"type":48,"value":96},"FASTQ\u002FBAM inputs and paired-end status",{"type":42,"tag":82,"props":98,"children":99},{},[100],{"type":48,"value":101},"input DNA, IgG, no-antibody, or spike-in controls",{"type":42,"tag":82,"props":103,"children":104},{},[105],{"type":48,"value":106},"organism, genome build, blacklist, and spike-in genome if used",{"type":42,"tag":82,"props":108,"children":109},{},[110],{"type":48,"value":111},"biological replicates, conditions, batches, and sample metadata",{"type":42,"tag":82,"props":113,"children":114},{},[115],{"type":48,"value":116},"desired endpoint: QC, peaks, bigWigs, consensus peaks, or differential binding",{"type":42,"tag":66,"props":118,"children":120},{"id":119},"route",[121],{"type":48,"value":122},"Route",{"type":42,"tag":51,"props":124,"children":125},{},[126,128,134,136,142],{"type":48,"value":127},"Use ",{"type":42,"tag":57,"props":129,"children":131},{"className":130},[],[132],{"type":48,"value":133},"nf-core\u002Fchipseq",{"type":48,"value":135}," for ChIP-seq and ",{"type":42,"tag":57,"props":137,"children":139},{"className":138},[],[140],{"type":48,"value":141},"nf-core\u002Fcutandrun",{"type":48,"value":143}," for CUT&RUN\u002FCUT&Tag when they fit the assay. Use direct MACS2 only for prepared BAMs with known control and duplicate policy.",{"type":42,"tag":51,"props":145,"children":146},{},[147],{"type":48,"value":148},"Preflight command:",{"type":42,"tag":150,"props":151,"children":156},"pre",{"className":152,"code":153,"language":154,"meta":155,"style":155},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","python plugins\u002Fngs-analysis\u002Fscripts\u002Fngs_preflight.py --pipeline chip_cutrun_peaks_qc --emit-install-plan\n","bash","",[157],{"type":42,"tag":57,"props":158,"children":159},{"__ignoreMap":155},[160],{"type":42,"tag":161,"props":162,"children":165},"span",{"class":163,"line":164},"line",1,[166,172,178,183,188],{"type":42,"tag":161,"props":167,"children":169},{"style":168},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[170],{"type":48,"value":171},"python",{"type":42,"tag":161,"props":173,"children":175},{"style":174},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[176],{"type":48,"value":177}," plugins\u002Fngs-analysis\u002Fscripts\u002Fngs_preflight.py",{"type":42,"tag":161,"props":179,"children":180},{"style":174},[181],{"type":48,"value":182}," --pipeline",{"type":42,"tag":161,"props":184,"children":185},{"style":174},[186],{"type":48,"value":187}," chip_cutrun_peaks_qc",{"type":42,"tag":161,"props":189,"children":190},{"style":174},[191],{"type":48,"value":192}," --emit-install-plan\n",{"type":42,"tag":51,"props":194,"children":195},{},[196],{"type":48,"value":197},"For compact FASTQ intake\u002FQC, use the shared epigenomics execution package:",{"type":42,"tag":150,"props":199,"children":201},{"className":152,"code":200,"language":154,"meta":155,"style":155},"python plugins\u002Fngs-analysis\u002Fscripts\u002Frun_fastq_assay_package.py \\\n  --lane epigenomics_peaks \\\n  --sample-sheet chip_or_cutrun_samples.csv \\\n  --execute\n",[202],{"type":42,"tag":57,"props":203,"children":204},{"__ignoreMap":155},[205,223,241,259],{"type":42,"tag":161,"props":206,"children":207},{"class":163,"line":164},[208,212,217],{"type":42,"tag":161,"props":209,"children":210},{"style":168},[211],{"type":48,"value":171},{"type":42,"tag":161,"props":213,"children":214},{"style":174},[215],{"type":48,"value":216}," plugins\u002Fngs-analysis\u002Fscripts\u002Frun_fastq_assay_package.py",{"type":42,"tag":161,"props":218,"children":220},{"style":219},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[221],{"type":48,"value":222}," \\\n",{"type":42,"tag":161,"props":224,"children":226},{"class":163,"line":225},2,[227,232,237],{"type":42,"tag":161,"props":228,"children":229},{"style":174},[230],{"type":48,"value":231},"  --lane",{"type":42,"tag":161,"props":233,"children":234},{"style":174},[235],{"type":48,"value":236}," epigenomics_peaks",{"type":42,"tag":161,"props":238,"children":239},{"style":219},[240],{"type":48,"value":222},{"type":42,"tag":161,"props":242,"children":244},{"class":163,"line":243},3,[245,250,255],{"type":42,"tag":161,"props":246,"children":247},{"style":174},[248],{"type":48,"value":249},"  --sample-sheet",{"type":42,"tag":161,"props":251,"children":252},{"style":174},[253],{"type":48,"value":254}," chip_or_cutrun_samples.csv",{"type":42,"tag":161,"props":256,"children":257},{"style":219},[258],{"type":48,"value":222},{"type":42,"tag":161,"props":260,"children":262},{"class":163,"line":261},4,[263],{"type":42,"tag":161,"props":264,"children":265},{"style":174},[266],{"type":48,"value":267},"  --execute\n",{"type":42,"tag":51,"props":269,"children":270},{},[271],{"type":48,"value":272},"It records FASTQ-level QC and peak-calling readiness.",{"type":42,"tag":51,"props":274,"children":275},{},[276],{"type":48,"value":277},"For local-light alignment, control-aware MACS2 peak calling, FRiP, bigWig tracks, consensus peaks, and motif-handoff artifacts, use the dedicated ChIP\u002FCUT&RUN runner:",{"type":42,"tag":150,"props":279,"children":281},{"className":152,"code":280,"language":154,"meta":155,"style":155},"python plugins\u002Fngs-analysis\u002Fscripts\u002Frun_chip_cutrun_peaks_qc.py \\\n  --sample-sheet chip_or_cutrun_samples.csv \\\n  --assay chipseq \\\n  --target-class tf \\\n  --peak-mode narrow \\\n  --bowtie2-index \u002Frefs\u002FGRCh38\u002Fbowtie2\u002Fgenome \\\n  --genome-size hs \\\n  --blacklist-bed \u002Frefs\u002FGRCh38\u002Fblacklists\u002Fencode_blacklist.bed \\\n  --execute\n",[282],{"type":42,"tag":57,"props":283,"children":284},{"__ignoreMap":155},[285,301,316,333,350,368,386,404,422],{"type":42,"tag":161,"props":286,"children":287},{"class":163,"line":164},[288,292,297],{"type":42,"tag":161,"props":289,"children":290},{"style":168},[291],{"type":48,"value":171},{"type":42,"tag":161,"props":293,"children":294},{"style":174},[295],{"type":48,"value":296}," plugins\u002Fngs-analysis\u002Fscripts\u002Frun_chip_cutrun_peaks_qc.py",{"type":42,"tag":161,"props":298,"children":299},{"style":219},[300],{"type":48,"value":222},{"type":42,"tag":161,"props":302,"children":303},{"class":163,"line":225},[304,308,312],{"type":42,"tag":161,"props":305,"children":306},{"style":174},[307],{"type":48,"value":249},{"type":42,"tag":161,"props":309,"children":310},{"style":174},[311],{"type":48,"value":254},{"type":42,"tag":161,"props":313,"children":314},{"style":219},[315],{"type":48,"value":222},{"type":42,"tag":161,"props":317,"children":318},{"class":163,"line":243},[319,324,329],{"type":42,"tag":161,"props":320,"children":321},{"style":174},[322],{"type":48,"value":323},"  --assay",{"type":42,"tag":161,"props":325,"children":326},{"style":174},[327],{"type":48,"value":328}," chipseq",{"type":42,"tag":161,"props":330,"children":331},{"style":219},[332],{"type":48,"value":222},{"type":42,"tag":161,"props":334,"children":335},{"class":163,"line":261},[336,341,346],{"type":42,"tag":161,"props":337,"children":338},{"style":174},[339],{"type":48,"value":340},"  --target-class",{"type":42,"tag":161,"props":342,"children":343},{"style":174},[344],{"type":48,"value":345}," tf",{"type":42,"tag":161,"props":347,"children":348},{"style":219},[349],{"type":48,"value":222},{"type":42,"tag":161,"props":351,"children":353},{"class":163,"line":352},5,[354,359,364],{"type":42,"tag":161,"props":355,"children":356},{"style":174},[357],{"type":48,"value":358},"  --peak-mode",{"type":42,"tag":161,"props":360,"children":361},{"style":174},[362],{"type":48,"value":363}," narrow",{"type":42,"tag":161,"props":365,"children":366},{"style":219},[367],{"type":48,"value":222},{"type":42,"tag":161,"props":369,"children":371},{"class":163,"line":370},6,[372,377,382],{"type":42,"tag":161,"props":373,"children":374},{"style":174},[375],{"type":48,"value":376},"  --bowtie2-index",{"type":42,"tag":161,"props":378,"children":379},{"style":174},[380],{"type":48,"value":381}," \u002Frefs\u002FGRCh38\u002Fbowtie2\u002Fgenome",{"type":42,"tag":161,"props":383,"children":384},{"style":219},[385],{"type":48,"value":222},{"type":42,"tag":161,"props":387,"children":389},{"class":163,"line":388},7,[390,395,400],{"type":42,"tag":161,"props":391,"children":392},{"style":174},[393],{"type":48,"value":394},"  --genome-size",{"type":42,"tag":161,"props":396,"children":397},{"style":174},[398],{"type":48,"value":399}," hs",{"type":42,"tag":161,"props":401,"children":402},{"style":219},[403],{"type":48,"value":222},{"type":42,"tag":161,"props":405,"children":407},{"class":163,"line":406},8,[408,413,418],{"type":42,"tag":161,"props":409,"children":410},{"style":174},[411],{"type":48,"value":412},"  --blacklist-bed",{"type":42,"tag":161,"props":414,"children":415},{"style":174},[416],{"type":48,"value":417}," \u002Frefs\u002FGRCh38\u002Fblacklists\u002Fencode_blacklist.bed",{"type":42,"tag":161,"props":419,"children":420},{"style":219},[421],{"type":48,"value":222},{"type":42,"tag":161,"props":423,"children":425},{"class":163,"line":424},9,[426],{"type":42,"tag":161,"props":427,"children":428},{"style":174},[429],{"type":48,"value":267},{"type":42,"tag":51,"props":431,"children":432},{},[433,435,441,443,449,451,457,459,465,467,473],{"type":48,"value":434},"This runner emits ",{"type":42,"tag":57,"props":436,"children":438},{"className":437},[],[439],{"type":48,"value":440},"qc\u002Fchip_cutrun_qc_summary.{tsv,json}",{"type":48,"value":442},", ",{"type":42,"tag":57,"props":444,"children":446},{"className":445},[],[447],{"type":48,"value":448},"qc\u002Fchip_cutrun_qc_dashboard.html",{"type":48,"value":450},", native SVG FRiP\u002Fpeak and insert-size plots, browser-track handoff files under ",{"type":42,"tag":57,"props":452,"children":454},{"className":453},[],[455],{"type":48,"value":456},"tracks\u002F",{"type":48,"value":458},", and ",{"type":42,"tag":57,"props":460,"children":462},{"className":461},[],[463],{"type":48,"value":464},"motifs\u002Fmotif_summary.tsv",{"type":48,"value":466},". Add ",{"type":42,"tag":57,"props":468,"children":470},{"className":469},[],[471],{"type":48,"value":472},"--run-motifs --motif-genome \u003Cgenome>",{"type":48,"value":474}," when HOMER motif enrichment should be executed instead of only planned.",{"type":42,"tag":51,"props":476,"children":477},{},[478,480,486,487,493,494,500,501,507,509,515,516,522,523,529],{"type":48,"value":479},"It also emits ",{"type":42,"tag":57,"props":481,"children":483},{"className":482},[],[484],{"type":48,"value":485},"resources\u002Fresource_plan.json",{"type":48,"value":442},{"type":42,"tag":57,"props":488,"children":490},{"className":489},[],[491],{"type":48,"value":492},"resource_manifest.tsv",{"type":48,"value":442},{"type":42,"tag":57,"props":495,"children":497},{"className":496},[],[498],{"type":48,"value":499},"resource_env.sh",{"type":48,"value":458},{"type":42,"tag":57,"props":502,"children":504},{"className":503},[],[505],{"type":48,"value":506},"resource_readiness.md",{"type":48,"value":508},". The resource check is advisory by default for local-light runs; add ",{"type":42,"tag":57,"props":510,"children":512},{"className":511},[],[513],{"type":48,"value":514},"--genome-build",{"type":48,"value":442},{"type":42,"tag":57,"props":517,"children":519},{"className":518},[],[520],{"type":48,"value":521},"--bundle-root \u003Cbundle>=\u003Cpath>",{"type":48,"value":458},{"type":42,"tag":57,"props":524,"children":526},{"className":525},[],[527],{"type":48,"value":528},"--require-resource-plan",{"type":48,"value":530}," when missing registered reference bundles should block readiness.",{"type":42,"tag":51,"props":532,"children":533},{},[534,536,542,544,550],{"type":48,"value":535},"For nf-core execution, use ",{"type":42,"tag":57,"props":537,"children":539},{"className":538},[],[540],{"type":48,"value":541},"plugins\u002Fngs-analysis\u002Fscripts\u002Frun_nfcore_pipeline.py --pipeline chipseq",{"type":48,"value":543}," or ",{"type":42,"tag":57,"props":545,"children":547},{"className":546},[],[548],{"type":48,"value":549},"--pipeline cutandrun",{"type":48,"value":551},".",{"type":42,"tag":66,"props":553,"children":555},{"id":554},"decision-points",[556],{"type":48,"value":557},"Decision Points",{"type":42,"tag":78,"props":559,"children":560},{},[561,566,571,576,581],{"type":42,"tag":82,"props":562,"children":563},{},[564],{"type":48,"value":565},"Choose narrow versus broad peak mode from target biology, not from convenience.",{"type":42,"tag":82,"props":567,"children":568},{},[569],{"type":48,"value":570},"Preserve control pairing and spike-in metadata through sample sheets.",{"type":42,"tag":82,"props":572,"children":573},{},[574],{"type":48,"value":575},"For histone marks, expect broad or domain-like signal for many marks; for TFs, expect sharper peaks and stronger replicate checks.",{"type":42,"tag":82,"props":577,"children":578},{},[579],{"type":48,"value":580},"Review alignment rate, duplicate rate, fragment size, FRiP\u002Fpeak signal, blacklist overlap, and replicate concordance.",{"type":42,"tag":82,"props":582,"children":583},{},[584],{"type":48,"value":585},"Keep consensus peak generation and differential binding design separate from raw peak calling.",{"type":42,"tag":66,"props":587,"children":589},{"id":588},"outputs",[590],{"type":48,"value":591},"Outputs",{"type":42,"tag":51,"props":593,"children":594},{},[595],{"type":48,"value":596},"Produce:",{"type":42,"tag":78,"props":598,"children":599},{},[600,605,610,615,620,625],{"type":42,"tag":82,"props":601,"children":602},{},[603],{"type":48,"value":604},"assay\u002Ftarget\u002Fcontrol manifest",{"type":42,"tag":82,"props":606,"children":607},{},[608],{"type":48,"value":609},"command\u002Fprofile and sample sheet",{"type":42,"tag":82,"props":611,"children":612},{},[613],{"type":48,"value":614},"QC summary with replicate\u002Fcontrol status",{"type":42,"tag":82,"props":616,"children":617},{},[618],{"type":48,"value":619},"peaks, bigWigs, browser-track manifests, browser-track preview HTML, native QC dashboard\u002FSVG plots, consensus peaks, and count matrix when requested",{"type":42,"tag":82,"props":621,"children":622},{},[623],{"type":48,"value":624},"motif summary files when a motif backend is requested",{"type":42,"tag":82,"props":626,"children":627},{},[628],{"type":48,"value":629},"differential binding design and caveats for missing controls, weak enrichment, or poor replicate concordance",{"type":42,"tag":631,"props":632,"children":633},"style",{},[634],{"type":48,"value":635},"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":637,"total":842},[638,659,682,699,715,734,753,769,785,799,811,826],{"slug":639,"name":639,"fn":640,"description":641,"org":642,"tags":643,"stars":656,"repoUrl":657,"updatedAt":658},"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},[644,647,650,653],{"name":645,"slug":646,"type":15},"Documents","documents",{"name":648,"slug":649,"type":15},"Healthcare","healthcare",{"name":651,"slug":652,"type":15},"Insurance","insurance",{"name":654,"slug":655,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":660,"name":660,"fn":661,"description":662,"org":663,"tags":664,"stars":679,"repoUrl":680,"updatedAt":681},"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},[665,668,670,673,676],{"name":666,"slug":667,"type":15},".NET","dotnet",{"name":669,"slug":660,"type":15},"ASP.NET Core",{"name":671,"slug":672,"type":15},"Blazor","blazor",{"name":674,"slug":675,"type":15},"C#","csharp",{"name":677,"slug":678,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":683,"name":683,"fn":684,"description":685,"org":686,"tags":687,"stars":679,"repoUrl":680,"updatedAt":698},"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},[688,691,694,697],{"name":689,"slug":690,"type":15},"Apps SDK","apps-sdk",{"name":692,"slug":693,"type":15},"ChatGPT","chatgpt",{"name":695,"slug":696,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":700,"name":700,"fn":701,"description":702,"org":703,"tags":704,"stars":679,"repoUrl":680,"updatedAt":714},"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},[705,708,711],{"name":706,"slug":707,"type":15},"API Development","api-development",{"name":709,"slug":710,"type":15},"CLI","cli",{"name":712,"slug":713,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":716,"name":716,"fn":717,"description":718,"org":719,"tags":720,"stars":679,"repoUrl":680,"updatedAt":733},"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},[721,724,727,730],{"name":722,"slug":723,"type":15},"Cloudflare","cloudflare",{"name":725,"slug":726,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":728,"slug":729,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":731,"slug":732,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":735,"name":735,"fn":736,"description":737,"org":738,"tags":739,"stars":679,"repoUrl":680,"updatedAt":752},"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},[740,743,746,749],{"name":741,"slug":742,"type":15},"Productivity","productivity",{"name":744,"slug":745,"type":15},"Project Management","project-management",{"name":747,"slug":748,"type":15},"Strategy","strategy",{"name":750,"slug":751,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":754,"name":754,"fn":755,"description":756,"org":757,"tags":758,"stars":679,"repoUrl":680,"updatedAt":768},"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},[759,762,764,767],{"name":760,"slug":761,"type":15},"Design","design",{"name":763,"slug":754,"type":15},"Figma",{"name":765,"slug":766,"type":15},"Frontend","frontend",{"name":695,"slug":696,"type":15},"2026-04-12T05:06:47.939943",{"slug":770,"name":770,"fn":771,"description":772,"org":773,"tags":774,"stars":679,"repoUrl":680,"updatedAt":784},"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},[775,776,779,780,781],{"name":760,"slug":761,"type":15},{"name":777,"slug":778,"type":15},"Design System","design-system",{"name":763,"slug":754,"type":15},{"name":765,"slug":766,"type":15},{"name":782,"slug":783,"type":15},"UI Components","ui-components","2026-05-10T05:59:52.971881",{"slug":786,"name":786,"fn":787,"description":788,"org":789,"tags":790,"stars":679,"repoUrl":680,"updatedAt":798},"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},[791,792,793,796,797],{"name":760,"slug":761,"type":15},{"name":777,"slug":778,"type":15},{"name":794,"slug":795,"type":15},"Documentation","documentation",{"name":763,"slug":754,"type":15},{"name":765,"slug":766,"type":15},"2026-05-16T06:07:47.821474",{"slug":800,"name":800,"fn":801,"description":802,"org":803,"tags":804,"stars":679,"repoUrl":680,"updatedAt":810},"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},[805,806,807,808,809],{"name":760,"slug":761,"type":15},{"name":763,"slug":754,"type":15},{"name":765,"slug":766,"type":15},{"name":782,"slug":783,"type":15},{"name":677,"slug":678,"type":15},"2026-05-16T06:07:40.583615",{"slug":812,"name":812,"fn":813,"description":814,"org":815,"tags":816,"stars":679,"repoUrl":680,"updatedAt":825},"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},[817,820,821,824],{"name":818,"slug":819,"type":15},"Animation","animation",{"name":712,"slug":713,"type":15},{"name":822,"slug":823,"type":15},"Creative","creative",{"name":760,"slug":761,"type":15},"2026-05-02T05:31:48.48485",{"slug":827,"name":827,"fn":828,"description":829,"org":830,"tags":831,"stars":679,"repoUrl":680,"updatedAt":841},"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},[832,833,834,837,840],{"name":822,"slug":823,"type":15},{"name":760,"slug":761,"type":15},{"name":835,"slug":836,"type":15},"Image Generation","image-generation",{"name":838,"slug":839,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675,{"items":844,"total":957},[845,861,877,889,907,925,945],{"slug":846,"name":846,"fn":847,"description":848,"org":849,"tags":850,"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},[851,854,857,860],{"name":852,"slug":853,"type":15},"Accessibility","accessibility",{"name":855,"slug":856,"type":15},"Charts","charts",{"name":858,"slug":859,"type":15},"Data Visualization","data-visualization",{"name":760,"slug":761,"type":15},{"slug":862,"name":862,"fn":863,"description":864,"org":865,"tags":866,"stars":25,"repoUrl":26,"updatedAt":876},"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},[867,870,873],{"name":868,"slug":869,"type":15},"Agents","agents",{"name":871,"slug":872,"type":15},"Browser Automation","browser-automation",{"name":874,"slug":875,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":878,"name":878,"fn":879,"description":880,"org":881,"tags":882,"stars":25,"repoUrl":26,"updatedAt":888},"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},[883,884,887],{"name":871,"slug":872,"type":15},{"name":885,"slug":886,"type":15},"Local Development","local-development",{"name":874,"slug":875,"type":15},"2026-04-06T18:41:17.526867",{"slug":890,"name":890,"fn":891,"description":892,"org":893,"tags":894,"stars":25,"repoUrl":26,"updatedAt":906},"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},[895,896,897,900,903],{"name":868,"slug":869,"type":15},{"name":728,"slug":729,"type":15},{"name":898,"slug":899,"type":15},"SDK","sdk",{"name":901,"slug":902,"type":15},"Serverless","serverless",{"name":904,"slug":905,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":908,"name":908,"fn":909,"description":910,"org":911,"tags":912,"stars":25,"repoUrl":26,"updatedAt":924},"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},[913,914,917,920,921],{"name":765,"slug":766,"type":15},{"name":915,"slug":916,"type":15},"React","react",{"name":918,"slug":919,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":782,"slug":783,"type":15},{"name":922,"slug":923,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":926,"name":926,"fn":927,"description":928,"org":929,"tags":930,"stars":25,"repoUrl":26,"updatedAt":944},"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},[931,934,937,940,943],{"name":932,"slug":933,"type":15},"AI Infrastructure","ai-infrastructure",{"name":935,"slug":936,"type":15},"Cost Optimization","cost-optimization",{"name":938,"slug":939,"type":15},"LLM","llm",{"name":941,"slug":942,"type":15},"Performance","performance",{"name":922,"slug":923,"type":15},"2026-04-06T18:40:44.377464",{"slug":946,"name":946,"fn":947,"description":948,"org":949,"tags":950,"stars":25,"repoUrl":26,"updatedAt":956},"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},[951,952,955],{"name":935,"slug":936,"type":15},{"name":953,"slug":954,"type":15},"Database","database",{"name":938,"slug":939,"type":15},"2026-04-06T18:41:08.513425",600]