[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CY709E07KYYGVRST7DFEQM":3,"skill-same:01M6CY709E07KYYGVRST7DFEQM":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":14,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":6,"updatedAt":51,"install":52,"resources":65},"01M6CY709E07KYYGVRST7DFEQM","drift-check",null,"Compares a new batch with the data the model was built on. Only when the inputs include a reference set and a newer batch. Check: expects reports\u002Fdrift.md.","Riteesh-2k6\u002Fbeyondml","Riteesh-2k6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F140528424?v=4","01M6CY6V18JEE5K6V3V28ZWQNK","Riteesh Thiruveedhula","01M6CY6V5BAR5VMFSG62KXRNA4",0,"MIT","https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml\u002Fblob\u002Fmain\u002Fbeyondml\u002Fskills\u002Fdrift-check\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"check","drift","drift check","batch","file","data","SET","model","read","write","list","only","finish","reports","reference","files","2026-11-10 10:12:30",false,"---\nname: drift-check\ndescription: \"Compares a new batch with the data the model was built on. Only when the inputs include a reference set and a newer batch. Check: expects reports\u002Fdrift.md.\"\nallowed-tools: read_file list_files write_file drift chart finish_step\nmetadata:\n  beyondml:\n    kind: step\n    modality: tabular\n---\nYou check whether new data still looks like the training data.\n\n1. Call drift(reference=\u003Cthe training file>, current=\u003Cthe new batch>).\n2. For the drifted columns, draw a histogram of each with chart(\"hist\", ...).\n3. Write reports\u002Fdrift.md with write_file: drifted columns with p-values, and whether retraining is advisable.\n4. Call finish_step with the drifted columns, outputs=[\"reports\u002Fdrift.md\"].\n","You check whether new data still looks like the training data.\n\n1. Call drift(reference=\u003Cthe training file>, current=\u003Cthe new batch>).\n2. For the drifted columns, draw a histogram of each with chart(\"hist\", ...).\n3. Write reports\u002Fdrift.md with write_file: drifted columns with p-values, and whether retraining is advisable.\n4. Call finish_step with the drifted columns, outputs=[\"reports\u002Fdrift.md\"].\n",{"name":5,"metadata":40,"description":7,"allowed-tools":44},{"beyondml":41},{"kind":42,"modality":43},"step","tabular","read_file list_files write_file drift chart finish_step","main","724a833f3e23c83a25b2ded06208fe53a1a1f460","beyondml\u002Fskills\u002Fdrift-check","https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml","https:\u002F\u002Fgithub.com\u002FRiteesh-2k6","riteeshvnsp.onrender.com","2026-10-25 14:58:25",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add Riteesh-2k6\u002Fbeyondml --skill drift-check",{"tool":58,"command":59},"bunx","bunx skills add Riteesh-2k6\u002Fbeyondml --skill drift-check",{"tool":61,"command":62},"pnpm","pnpm dlx skills add Riteesh-2k6\u002Fbeyondml --skill drift-check","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml\u002Fblob\u002Fmain\u002Fbeyondml\u002Fskills\u002Fdrift-check\u002FSKILL.md",true,[],[67,78,87,95,111,128],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":35},"01M6CY8269784EN3M5TCSD07EB","tabular-demo","Demo step skill for tabular data.","https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml\u002Fblob\u002Fmain\u002Ftests\u002Fdata\u002Fskills\u002Ftabular-demo\u002FSKILL.md",[],[74,75,27,31,24,23,76,77],"tabular demo","demo","run","python",{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":35},"01M6CY80AQNXNZT62N6GQZXA52","leakage-demo","Demo knowledge skill about target leakage.","https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml\u002Fblob\u002Fmain\u002Ftests\u002Fdata\u002Fskills\u002Fleakage-demo\u002FSKILL.md",[],[75,85,86],"leakage demo","knowledge",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":35},"01M6CY7YDZB93PX14NDCJDBPRX","bad-name","Name does not match its folder.","https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml\u002Fblob\u002Fmain\u002Ftests\u002Fdata\u002Fskills\u002FBadName\u002FSKILL.md",[],[94],"bad name",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":106,"publishedAt":35},"01M6CY7VZ7MJXVVQ5GCKTJWEXV","train-test-split","How to split data so the score is honest.","https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml\u002Fblob\u002Fmain\u002Fbeyondml\u002Fskills\u002Ftrain-test-split\u002FSKILL.md",[101],{"categoryNo":102,"categoryName":103,"taxonomyType":104,"taxonomyTypeDesc":105},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[107,108,109,24,110,86],"test","train","train test split","how",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":35},"01M6CY7SHBNZXKWXVNYXJFJRX3","tabular-features","Writes src\u002Ffeatures.py with derived features (ratios, logs, interactions) and no target use. Usually right after tabular-eda. Check: run src\u002Ffeatures.py, expects data\u002Fprocessed\u002Ffeatures.csv.","https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml\u002Fblob\u002Fmain\u002Fbeyondml\u002Fskills\u002Ftabular-features\u002FSKILL.md",[],[118,29,119,120,121,31,34,122,123,27,28,77,76,23,124,125,24,126,19,127],"tabular features","user","profile","use","scan","eda","logs","csv","src","ask",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":35},"01M6CY7Q2GNHM2NM7ZVRMGRX7P","tabular-export","Writes the shipped code (src\u002Fpipeline.py, src\u002Ftrain.py, src\u002Fpredict.py) from the winning run and trains it. Usually right after evolve-search or tabular-ensemble. Check: run src\u002Ftrain.py, expects models\u002Fmodel.joblib, metric accuracy (classification) or r2 (regression) with a minimum.","https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml\u002Fblob\u002Fmain\u002Fbeyondml\u002Fskills\u002Ftabular-export\u002FSKILL.md",[],[135,136,31,76,137,138,23,139,140,126,26,141,142,27,28,29,34,143,108,77],"tabular export","export","code","search","pipeline","classification","regression","evolve","models"]