[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DEECQTNPQJACEK7F85XD6Q":3,"skill-same:01M7DEECQTNPQJACEK7F85XD6Q":72},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":28,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7DEECQTNPQJACEK7F85XD6Q","szl-dataset-readiness",null,"Audits a tabular dataset before training or evaluation for exact duplicate rows across train\u002Ftest, the same subject, patient, cell line or sensor appearing in both splits, labels observed after the prediction time, and preprocessing fitted on held-out rows, all bound to actual row IDs. Use when the user is about to split data, asks 'is my test set clean', reports suspiciously high held-out accuracy, or a reviewer asks about leakage. Not a data-cleaning or imputation tool; it does not approve scientific suitability or data rights.","szl-holdings\u002Fszl-skills","szl-holdings","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F273360816?v=4","01M7DEC83S24HX3V8G1JSWKHD0","SZL Holdings","01M7DEC85084EGHEJH2KMAA53K",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-dataset-readiness\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: szl-dataset-readiness\ndescription: \"Audits a tabular dataset before training or evaluation for exact duplicate rows across train\u002Ftest, the same subject, patient, cell line or sensor appearing in both splits, labels observed after the prediction time, and preprocessing fitted on held-out rows, all bound to actual row IDs. Use when the user is about to split data, asks 'is my test set clean', reports suspiciously high held-out accuracy, or a reviewer asks about leakage. Not a data-cleaning or imputation tool; it does not approve scientific suitability or data rights.\"\nlicense: Apache-2.0\n---\n\n# Dataset readiness\n\nMost impossible accuracies come from a test set that already knows the answer. This audit finds\nthe mechanical versions of that mistake and names the rows involved. Python 3.10+, stdlib, offline.\n\n## Use when\n\n- A patient, mouse, cell line, sensor or template family appears in both train and test.\n- Two rows are byte-identical except for the split they landed in.\n- A label (diagnosis, failure, churn) was recorded after the moment the prediction would have been made.\n- A scaler, imputer or vocabulary was fitted on all rows and then \"held-out\" rows were scored.\n\n## Quick start\n\n```bash\npython scripts\u002Frun.py assets\u002Fexample.json\npython scripts\u002Frun.py assets\u002Fleakage-clean.json\n```\n\nThe first synthetic table returns `\"status\": \"ISSUES_FOUND\"`, `\"readiness\": \"REVIEW\"` with\n`\"issues\": [\"EXACT_FEATURE_DUPLICATES\", \"CROSS_SPLIT_FEATURE_LEAKAGE\", \"CROSS_SPLIT_GROUP_LEAKAGE\"]`\nand the offending row indexes (`[0, 2]`, one in test, one in train). The second is a clean design and\nreturns `NO_CHECKED_ISSUES` for every supplied check while readiness stays `REVIEW`.\n\n## Preparing the input\n\nDecide first what one observation is (a sample, a visit, a plate well), where predictions originate\nin time, which column identifies the entity that must not straddle splits, and how the split was\ndesigned. Then call `szl_audit_dataset` in `kernel.py` on explicitly bounded rows, or write the JSON\nthe CLI reads. Use content-defining feature columns that exclude row ids and split names. Add a\n`leakage_spec` to check entity, temporal and preprocessing evidence; bind transform fit row ids to the\nevidence you actually have, and distinguish when a label became available from when it was observed.\nA `TRAIN_ONLY` declaration alone does not establish train-only fitting. Read `references\u002Fcontract.md`\nwhen preparing that manifest or interpreting missing evidence.\n\nThe helper never samples silently, never imputes missing timestamps, and never infers timezone or\ncolumn meaning. Metadata records the source revision and license as declared without verifying them.\n\n## What it does not do\n\n`NO_CHECKED_ISSUES` applies only to the supplied checks and selected rows; readiness remains `REVIEW`\nuntil a human decides. Semantic near-duplicates, causal leakage through derived features, label\nvalidity and population suitability are outside its reach and need separate investigation. Digests\nare not anonymization. No network, model calls, training, upload or performance claim follows.\n","# Dataset readiness\n\nMost impossible accuracies come from a test set that already knows the answer. This audit finds\nthe mechanical versions of that mistake and names the rows involved. Python 3.10+, stdlib, offline.\n\n## Use when\n\n- A patient, mouse, cell line, sensor or template family appears in both train and test.\n- Two rows are byte-identical except for the split they landed in.\n- A label (diagnosis, failure, churn) was recorded after the moment the prediction would have been made.\n- A scaler, imputer or vocabulary was fitted on all rows and then \"held-out\" rows were scored.\n\n## Quick start\n\n```bash\npython scripts\u002Frun.py assets\u002Fexample.json\npython scripts\u002Frun.py assets\u002Fleakage-clean.json\n```\n\nThe first synthetic table returns `\"status\": \"ISSUES_FOUND\"`, `\"readiness\": \"REVIEW\"` with\n`\"issues\": [\"EXACT_FEATURE_DUPLICATES\", \"CROSS_SPLIT_FEATURE_LEAKAGE\", \"CROSS_SPLIT_GROUP_LEAKAGE\"]`\nand the offending row indexes (`[0, 2]`, one in test, one in train). The second is a clean design and\nreturns `NO_CHECKED_ISSUES` for every supplied check while readiness stays `REVIEW`.\n\n## Preparing the input\n\nDecide first what one observation is (a sample, a visit, a plate well), where predictions originate\nin time, which column identifies the entity that must not straddle splits, and how the split was\ndesigned. Then call `szl_audit_dataset` in `kernel.py` on explicitly bounded rows, or write the JSON\nthe CLI reads. Use content-defining feature columns that exclude row ids and split names. Add a\n`leakage_spec` to check entity, temporal and preprocessing evidence; bind transform fit row ids to the\nevidence you actually have, and distinguish when a label became available from when it was observed.\nA `TRAIN_ONLY` declaration alone does not establish train-only fitting. Read `references\u002Fcontract.md`\nwhen preparing that manifest or interpreting missing evidence.\n\nThe helper never samples silently, never imputes missing timestamps, and never infers timezone or\ncolumn meaning. Metadata records the source revision and license as declared without verifying them.\n\n## What it does not do\n\n`NO_CHECKED_ISSUES` applies only to the supplied checks and selected rows; readiness remains `REVIEW`\nuntil a human decides. Semantic near-duplicates, causal leakage through derived features, label\nvalidity and population suitability are outside its reach and need separate investigation. Digests\nare not anonymization. No network, model calls, training, upload or performance claim follows.\n",{"name":5,"license":15,"description":7},"main","8dd614e1f5097564340e36915f849d7d893cd68a","skills\u002Fszl-dataset-readiness","https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills","https:\u002F\u002Fa-11-oy.com","https:\u002F\u002Fgithub.com\u002Fszl-holdings","Governed AI infrastructure for inspectable decisions: source, runtime state, receipts, and proof boundaries.","2026-11-15 03:52:34",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add szl-holdings\u002Fszl-skills --skill szl-dataset-readiness",{"tool":38,"command":39},"bunx","bunx skills add szl-holdings\u002Fszl-skills --skill szl-dataset-readiness",{"tool":41,"command":42},"pnpm","pnpm dlx skills add szl-holdings\u002Fszl-skills --skill szl-dataset-readiness","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-dataset-readiness\u002FSKILL.md",true,[46,52,56,62,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"assets\u002Fexample.json","ASSET","资产文件",584,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-dataset-readiness\u002Fassets\u002Fexample.json",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"assets\u002Fleakage-clean.json",1161,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-dataset-readiness\u002Fassets\u002Fleakage-clean.json",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"kernel.py","SCRIPT","脚本",17913,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-dataset-readiness\u002Fkernel.py",{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fcontract.md","REFERENCE","参考文档",5190,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-dataset-readiness\u002Freferences\u002Fcontract.md",{"path":69,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":70,"sourceHtmlUrl":71},"scripts\u002Frun.py",3369,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-dataset-readiness\u002Fscripts\u002Frun.py",[73,80,87,94,100,105],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7DENG22R761RTDSG11WWJB3","szl-unit-invariants","Checks declared SI dimensions, allowlisted unit conversions, expected ranges and fixed pointwise invariants (equal, sum, difference, product, ratio) over selected measurement or simulation columns, flagging incompatible quantities, scale errors of 1000x and broken conservation checks. Use when merging instrument exports with different units, validating simulation output against conservation laws, or when a reviewer asks how unit errors were ruled out. Not an uncertainty-propagation or symbolic tool.","https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-unit-invariants\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7DENAVBJ6GSCRT3E1PWK56D","szl-uncertainty-lineage","Propagate declared measurement uncertainty through a small arithmetic dependency graph using a first-order delta approximation. Use when a researcher needs to see how corrected inputs or shared-source correlation change a reported standard uncertainty; require unit checks separately.","https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-uncertainty-lineage\u002FSKILL.md",[],[],{"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":19},"01M7DEN2M7P59RTM6RJE99PGN8","szl-typesafe-ai","TypeSafe\u002FJev: Choice\u002FNoul\u002FScore in code, not TypeScript types. System One models turn natural language and application state into probabilities that software can compose. Use when building routing, ranking, extraction, verification, or replacing an LLM prompt-and-parse step with structured decisions; also when brainstorming what TypeSafe could make possible. Do not use for TypeScript\u002FJava\u002FRust static types, Zod\u002FPydantic\u002Fmypy\u002FJSON Schema\u002Fprotobuf codegen, or asking whether a pipeline is type-safe. At SZL, Jev is an optional second reader only.","https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-typesafe-ai\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7DEN1C9G4H12N9HRHYK2HZ7","demo","https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-skill-update-review\u002Fassets\u002Fexample\u002Fold-package\u002Fskills\u002Fdemo\u002FSKILL.md",[],[],{"skillNo":101,"name":96,"nameZh":6,"description":6,"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":104,"publishedAt":19},"01M7DEMZYRXT5CG2XPXERAM218","https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-skill-update-review\u002Fassets\u002Fexample\u002Fnew-package\u002Fskills\u002Fdemo\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M7DEMVH2NMG4PS0DZTMGATAF","szl-skill-update-review","Compare pinned local skill packages using inventories and a retained lock; report changed skills, files, declarations and reruns without approving safety or validity.","https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-skill-update-review\u002FSKILL.md",[],[]]