[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CY7BEJV30HM9J8XM6F3QR0":3,"skill-same:01M6CY7BEJV30HM9J8XM6F3QR0":70},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6CY7BEJV30HM9J8XM6F3QR0","tabular-audit",null,"First step for a table: profile it, fix the target and problem type, find leaking and impossible columns. Usually the first step of a tabular plan. Check: expects reports\u002Faudit.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\u002Ftabular-audit\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"tabular audit","audit","write","scan","files","reports","finish","fix","profile","user","list","python","read","ask","check","find","plan","first","file","run","2026-11-10 10:12:30",false,"---\nname: tabular-audit\ndescription: \"First step for a table: profile it, fix the target and problem type, find leaking and impossible columns. Usually the first step of a tabular plan. Check: expects reports\u002Faudit.md.\"\nallowed-tools: read_file list_files write_file run_python profile scan_leakage chart ask_user finish_step\nmetadata:\n  beyondml:\n    kind: step\n    modality: tabular\n---\nYou audit the raw table before anything is built on it.\n\n1. Call profile(path=\u003Cthe raw file>) and read the target analysis and the ranked target candidates.\n2. Confirm the target. Call ask_user(\"Which column is the target?\", options=\u003Cthe ranked candidates>, recommended=\u003Cthe top candidate>) and use the answer.\n3. Call profile again with target=\u003Cthe target> and note the problem type (classification or regression).\n4. Call scan_leakage(path, target). Treat target_correlation and single_feature_score suspects as leaks; treat id_like columns as drop candidates; name hints need your judgement.\n5. Look for impossible values (sentinels such as age 999 or zip 00000, negative counts, future years). Only flag values that are clearly impossible, not merely rare.\n6. Write reports\u002Faudit.md with write_file: target, problem type, the drop list with one reason per column, impossible values per column.\n7. Call finish_step with a summary that states the target, the problem type and the drop list, and outputs=[\"reports\u002Faudit.md\"].\n","You audit the raw table before anything is built on it.\n\n1. Call profile(path=\u003Cthe raw file>) and read the target analysis and the ranked target candidates.\n2. Confirm the target. Call ask_user(\"Which column is the target?\", options=\u003Cthe ranked candidates>, recommended=\u003Cthe top candidate>) and use the answer.\n3. Call profile again with target=\u003Cthe target> and note the problem type (classification or regression).\n4. Call scan_leakage(path, target). Treat target_correlation and single_feature_score suspects as leaks; treat id_like columns as drop candidates; name hints need your judgement.\n5. Look for impossible values (sentinels such as age 999 or zip 00000, negative counts, future years). Only flag values that are clearly impossible, not merely rare.\n6. Write reports\u002Faudit.md with write_file: target, problem type, the drop list with one reason per column, impossible values per column.\n7. Call finish_step with a summary that states the target, the problem type and the drop list, and outputs=[\"reports\u002Faudit.md\"].\n",{"name":5,"metadata":44,"description":7,"allowed-tools":48},{"beyondml":45},{"kind":46,"modality":47},"step","tabular","read_file list_files write_file run_python profile scan_leakage chart ask_user finish_step","main","724a833f3e23c83a25b2ded06208fe53a1a1f460","beyondml\u002Fskills\u002Ftabular-audit","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":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add Riteesh-2k6\u002Fbeyondml --skill tabular-audit",{"tool":62,"command":63},"bunx","bunx skills add Riteesh-2k6\u002Fbeyondml --skill tabular-audit",{"tool":65,"command":66},"pnpm","pnpm dlx skills add Riteesh-2k6\u002Fbeyondml --skill tabular-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml\u002Fblob\u002Fmain\u002Fbeyondml\u002Fskills\u002Ftabular-audit\u002FSKILL.md",true,[],[71,81,90,98,114,127],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":39},"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",[],[78,79,31,25,80,37,38,30],"tabular demo","demo","data",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":39},"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",[],[79,88,89],"leakage demo","knowledge",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":39},"01M6CY7YDZB93PX14NDCJDBPRX","bad-name","Name does not match its folder.","https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml\u002Fblob\u002Fmain\u002Ftests\u002Fdata\u002Fskills\u002FBadName\u002FSKILL.md",[],[97],"bad name",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":109,"publishedAt":39},"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",[104],{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[110,111,112,80,113,89],"test","train","train test split","how",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":39},"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",[],[121,29,28,27,122,25,23,22,123,31,21,30,38,37,124,125,80,126,33,32],"tabular features","use","eda","logs","csv","src",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":39},"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",[],[134,135,25,38,136,137,37,138,139,126,140,141,142,31,21,29,23,143,111,30],"tabular export","export","code","search","pipeline","classification","model","regression","evolve","models"]