[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CY74TFA1BSZNGTMW33V976":3,"skill-same:01M6CY74TFA1BSZNGTMW33V976":61},{"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":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":14,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6CY74TFA1BSZNGTMW33V976","evolve-search",null,"Searches models and hyperparameters with the genetic algorithm (or Optuna for expensive models). Usually right after tabular-features. Check: metric mu_cv with a minimum.","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\u002Fevolve-search\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29],"search","evolve","evolve search","file","check","read","list","profile","finish","files","models","2026-11-10 10:12:30",false,"---\nname: evolve-search\ndescription: \"Searches models and hyperparameters with the genetic algorithm (or Optuna for expensive models). Usually right after tabular-features. Check: metric mu_cv with a minimum.\"\nallowed-tools: read_file list_files profile evolve tune finish_step\nmetadata:\n  beyondml:\n    kind: step\n    modality: tabular\n---\nYou find the best model with BeyondML's search.\n\n1. Call profile(path=\"data\u002Fprocessed\u002Ffeatures.csv\", target=\u003Cthe target>) to see rows, columns and the problem type.\n2. Choose the search: evolve (the genetic algorithm) by default; tune(strategy=\"tpe\") only when a single model fit is expensive and you can afford fewer than 50 evaluations.\n3. Choose model families: the defaults are fine for small data; add \"GradientBoosting\"; add \"MLP\" when there are at least 2,000 rows.\n4. Seed the search with 2-4 sensible starting configurations, e.g. [{\"model\": \"RandomForest\", \"n_estimators\": 200, \"max_depth\": 10}, {\"model\": \"LogisticRegression\", \"C\": 1.0, \"max_iter\": 1000}].\n5. Call evolve(data=\"data\u002Fprocessed\u002Ffeatures.csv\", target=\u003Cthe target>, models=[...], seeds=[...]). Use minutes=\u003Ca budget> on large data.\n6. Call finish_step with a summary that includes \"run_id=\u003Cthe run_id>\" and mu_cv, outputs=[].\n","You find the best model with BeyondML's search.\n\n1. Call profile(path=\"data\u002Fprocessed\u002Ffeatures.csv\", target=\u003Cthe target>) to see rows, columns and the problem type.\n2. Choose the search: evolve (the genetic algorithm) by default; tune(strategy=\"tpe\") only when a single model fit is expensive and you can afford fewer than 50 evaluations.\n3. Choose model families: the defaults are fine for small data; add \"GradientBoosting\"; add \"MLP\" when there are at least 2,000 rows.\n4. Seed the search with 2-4 sensible starting configurations, e.g. [{\"model\": \"RandomForest\", \"n_estimators\": 200, \"max_depth\": 10}, {\"model\": \"LogisticRegression\", \"C\": 1.0, \"max_iter\": 1000}].\n5. Call evolve(data=\"data\u002Fprocessed\u002Ffeatures.csv\", target=\u003Cthe target>, models=[...], seeds=[...]). Use minutes=\u003Ca budget> on large data.\n6. Call finish_step with a summary that includes \"run_id=\u003Cthe run_id>\" and mu_cv, outputs=[].\n",{"name":5,"metadata":35,"description":7,"allowed-tools":39},{"beyondml":36},{"kind":37,"modality":38},"step","tabular","read_file list_files profile evolve tune finish_step","main","724a833f3e23c83a25b2ded06208fe53a1a1f460","beyondml\u002Fskills\u002Fevolve-search","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":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add Riteesh-2k6\u002Fbeyondml --skill evolve-search",{"tool":53,"command":54},"bunx","bunx skills add Riteesh-2k6\u002Fbeyondml --skill evolve-search",{"tool":56,"command":57},"pnpm","pnpm dlx skills add Riteesh-2k6\u002Fbeyondml --skill evolve-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml\u002Fblob\u002Fmain\u002Fbeyondml\u002Fskills\u002Fevolve-search\u002FSKILL.md",true,[],[62,74,83,91,107,124],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":30},"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",[],[69,70,24,27,71,22,72,73],"tabular demo","demo","data","run","python",{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":30},"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",[],[70,81,82],"leakage demo","knowledge",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":30},"01M6CY7YDZB93PX14NDCJDBPRX","bad-name","Name does not match its folder.","https:\u002F\u002Fgithub.com\u002FRiteesh-2k6\u002Fbeyondml\u002Fblob\u002Fmain\u002Ftests\u002Fdata\u002Fskills\u002FBadName\u002FSKILL.md",[],[90],"bad name",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":102,"publishedAt":30},"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",[97],{"categoryNo":98,"categoryName":99,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[103,104,105,71,106,82],"test","train","train test split","how",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":30},"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",[],[114,25,115,26,116,27,28,117,118,24,119,73,72,22,120,121,71,122,23,123],"tabular features","user","use","scan","eda","write","logs","csv","src","ask",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":30},"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",[],[131,132,27,72,133,19,22,134,135,122,136,137,20,24,119,25,28,29,104,73],"tabular export","export","code","pipeline","classification","model","regression"]