[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DENG22R761RTDSG11WWJB3":3,"skill-same:01M7DENG22R761RTDSG11WWJB3":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},"01M7DENG22R761RTDSG11WWJB3","szl-unit-invariants",null,"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.","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-unit-invariants\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: szl-unit-invariants\ndescription: \"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.\"\nlicense: Apache-2.0\n---\n\n# Unit invariants\n\nA µg column read as mg survives every statistical test and ruins the paper. Declare what each column\nis supposed to be and let the helper check dimensions, ranges and the relations that must hold\npointwise. Python 3.9+, stdlib, offline, decimal arithmetic at 50 significant digits.\n\n## Use when\n\n- Combining plate-reader, LC-MS and clinical exports that report the same quantity in different units.\n- Checking that mass, energy or charge is conserved row by row in a simulation output.\n- A flow rate, dose or concentration column has values 1000x off from the declared range.\n\n## Quick start\n\n```bash\npython scripts\u002Frun.py assets\u002Fexample.json --output unit-report.json\n```\n\nThe invented example (a duration, a length in cm and a speed check) returns\n`\"status\": \"PASS_DECLARED_CHECKS\"` with each quantity's SI dimension vector, `declared_dimension_match`\nand SI-normalized values. Introduce a cm\u002Fm mix-up and the report carries `SCALE_MISMATCH` or\n`RANGE_VIOLATION` with the exact factor.\n\n## Declaring checks\n\nSelect a bounded set of columns; declare unit, SI dimension, expected range and prespecified\ninvariants. Use decimal strings when precision matters. Read `references\u002Fcontract.md` for the unit\ntable, dimension order and operation grammar. Call `szl_audit_unit_invariants(record)` in `kernel.py`\nor run the CLI. Inspect dimension failures before interpreting numeric agreement; review range\nviolations, numerical discrepancies, undefined ratios and flagged factors of at least 1000.\nPreserve original values: a corrected declaration is a new audit, not evidence that the original passed.\n\n## What it does not do\n\nOffset units (Celsius), logarithmic units, implicit broadcasting, arbitrary formulas and units absent\nfrom the table are rejected. Success means the declared checks pass on supplied values; observed units,\nphysical laws and scientific conclusions are not verified, and finite decimal arithmetic does not replace\nuncertainty propagation or a symbolic proof. Limits: 1 MiB input, 1000 quantities and invariants,\n10,000 samples. Provenance: `references\u002Fprovenance.md`.\n","# Unit invariants\n\nA µg column read as mg survives every statistical test and ruins the paper. Declare what each column\nis supposed to be and let the helper check dimensions, ranges and the relations that must hold\npointwise. Python 3.9+, stdlib, offline, decimal arithmetic at 50 significant digits.\n\n## Use when\n\n- Combining plate-reader, LC-MS and clinical exports that report the same quantity in different units.\n- Checking that mass, energy or charge is conserved row by row in a simulation output.\n- A flow rate, dose or concentration column has values 1000x off from the declared range.\n\n## Quick start\n\n```bash\npython scripts\u002Frun.py assets\u002Fexample.json --output unit-report.json\n```\n\nThe invented example (a duration, a length in cm and a speed check) returns\n`\"status\": \"PASS_DECLARED_CHECKS\"` with each quantity's SI dimension vector, `declared_dimension_match`\nand SI-normalized values. Introduce a cm\u002Fm mix-up and the report carries `SCALE_MISMATCH` or\n`RANGE_VIOLATION` with the exact factor.\n\n## Declaring checks\n\nSelect a bounded set of columns; declare unit, SI dimension, expected range and prespecified\ninvariants. Use decimal strings when precision matters. Read `references\u002Fcontract.md` for the unit\ntable, dimension order and operation grammar. Call `szl_audit_unit_invariants(record)` in `kernel.py`\nor run the CLI. Inspect dimension failures before interpreting numeric agreement; review range\nviolations, numerical discrepancies, undefined ratios and flagged factors of at least 1000.\nPreserve original values: a corrected declaration is a new audit, not evidence that the original passed.\n\n## What it does not do\n\nOffset units (Celsius), logarithmic units, implicit broadcasting, arbitrary formulas and units absent\nfrom the table are rejected. Success means the declared checks pass on supplied values; observed units,\nphysical laws and scientific conclusions are not verified, and finite decimal arithmetic does not replace\nuncertainty propagation or a symbolic proof. Limits: 1 MiB input, 1000 quantities and invariants,\n10,000 samples. Provenance: `references\u002Fprovenance.md`.\n",{"name":5,"license":15,"description":7},"main","8dd614e1f5097564340e36915f849d7d893cd68a","skills\u002Fszl-unit-invariants","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-unit-invariants",{"tool":38,"command":39},"bunx","bunx skills add szl-holdings\u002Fszl-skills --skill szl-unit-invariants",{"tool":41,"command":42},"pnpm","pnpm dlx skills add szl-holdings\u002Fszl-skills --skill szl-unit-invariants","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-unit-invariants\u002FSKILL.md",true,[46,52,58,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"assets\u002Fexample.json","ASSET","资产文件",874,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-unit-invariants\u002Fassets\u002Fexample.json",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"kernel.py","SCRIPT","脚本",13108,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-unit-invariants\u002Fkernel.py",{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fcontract.md","REFERENCE","参考文档",5096,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-unit-invariants\u002Freferences\u002Fcontract.md",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fprovenance.md",1237,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-unit-invariants\u002Freferences\u002Fprovenance.md",{"path":69,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":70,"sourceHtmlUrl":71},"scripts\u002Frun.py",2230,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-unit-invariants\u002Fscripts\u002Frun.py",[73,80,87,93,98,105],{"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},"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":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},"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":88,"name":89,"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":90,"categories":91,"keywords":92,"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":94,"name":89,"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":95,"categories":96,"keywords":97,"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":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":104,"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",[],[],{"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},"01M7DEMKV29EMH203F3Y1WGD99","szl-skill-conformance","Checks retained scientific skill-sharing evidence: exact local source and supplied host-export resource bytes, explicit import aliases, task and result digests, positive versus irrelevant-task trigger declarations, and optional artifact-to-trace byte bindings. Use when a shared skill appears imported but invocation is uncertain, when comparing retained trials across hosts, or when an update may invalidate an earlier result. Offline checking never executes the candidate and never certifies real host invocation or scientific correctness.","https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-skill-conformance\u002FSKILL.md",[],[]]