[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DEJSYXNWYJK4W8V4T7YNT1":3,"skill-same:01M7DEJSYXNWYJK4W8V4T7YNT1":96},{"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},"01M7DEJSYXNWYJK4W8V4T7YNT1","szl-reproducibility-capsule",null,"Creates an exact-byte manifest (path, size, SHA-256) for the explicitly selected files of an experiment, verifies them later as changed \u002F missing \u002F unsafe, and validates a bounded replay declaration (inputs, source, environment, plan, outputs) without executing anything. Use when handing an analysis to a collaborator, archiving a result, preparing a replication or when the user asks 'did anything change since the run'. Not a container, not a signature, and it does not reproduce the experiment.","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-reproducibility-capsule\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: szl-reproducibility-capsule\ndescription: \"Creates an exact-byte manifest (path, size, SHA-256) for the explicitly selected files of an experiment, verifies them later as changed \u002F missing \u002F unsafe, and validates a bounded replay declaration (inputs, source, environment, plan, outputs) without executing anything. Use when handing an analysis to a collaborator, archiving a result, preparing a replication or when the user asks 'did anything change since the run'. Not a container, not a signature, and it does not reproduce the experiment.\"\nlicense: Apache-2.0\n---\n\n# Reproducibility capsule\n\nPick the files that define an experiment and freeze their bytes. Later, prove they are the same\nbytes or list exactly which ones moved. Python 3.10+, stdlib, offline.\n\n## Use when\n\n- Archiving the input tables, scripts, environment file and reference outputs behind a figure.\n- A collaborator re-runs your pipeline and gets different numbers: verify the capsule first.\n- Preparing a replay package for a separate sandbox review with declared seed and limits.\n\n## Quick start\n\n```bash\npython scripts\u002Frun.py assets\u002Fexample.json --root .\n```\n\nCreates a `szl.reproducibility-capsule.v1` record listing `assets\u002Fprotocol.txt` (270 bytes, its\nSHA-256), the synthetic metadata, `signed: false` and a `capsule_sha256`. Verification on retained\nbytes reports changed, missing and unsafe or unreadable files separately. `assets\u002Freplay-example.json`\nadds a replay declaration over the files in `assets\u002Freplay`.\n\n## Creating and verifying\n\n`szl_make_capsule(root, files, metadata=None, replay=None)` accepts plain path lists or role-tagged\nentries (`path` plus `role`). Paths must be canonical relative POSIX paths, unique, within hard\ncount and byte bounds; traversal, symlinks, junctions, reparse points and credential-like names\nare refused. `szl_verify_capsule(root, capsule)` re-hashes. All bytes matching plus a complete,\nvalid replay declaration yields `replay_ready: true`, meaning prepared for a separate sandbox review;\n`execution: NOT_RUN`, `capability_denial: DECLARED_ONLY` and `tolerance_application: NOT_RUN` stay\nexplicit. Read `references\u002Fcontracts.md` before authoring a replay.\n\nKeep an independently retained copy of the manifest when integrity across sessions matters: an\nunsigned self-digest cannot detect replacement of the whole manifest. `authentic: false` stays false\neven when every byte matches; real signing needs a key and a verifier (see szl-session-receipt for the\noptional signing path).\n\n## What it does not do\n\nNever executes argv or source, installs dependencies, launches processes, applies numerical\ncomparisons to outputs, or inspects file contents for secrets (credential-name guards look at names).\nLimits: 128 files, 8 MiB per file, 32 MiB total. It cannot prove source safety, enforce a sandbox or\nverify preregistration. Hashes are not signatures; readiness is not reproduction.\n","# Reproducibility capsule\n\nPick the files that define an experiment and freeze their bytes. Later, prove they are the same\nbytes or list exactly which ones moved. Python 3.10+, stdlib, offline.\n\n## Use when\n\n- Archiving the input tables, scripts, environment file and reference outputs behind a figure.\n- A collaborator re-runs your pipeline and gets different numbers: verify the capsule first.\n- Preparing a replay package for a separate sandbox review with declared seed and limits.\n\n## Quick start\n\n```bash\npython scripts\u002Frun.py assets\u002Fexample.json --root .\n```\n\nCreates a `szl.reproducibility-capsule.v1` record listing `assets\u002Fprotocol.txt` (270 bytes, its\nSHA-256), the synthetic metadata, `signed: false` and a `capsule_sha256`. Verification on retained\nbytes reports changed, missing and unsafe or unreadable files separately. `assets\u002Freplay-example.json`\nadds a replay declaration over the files in `assets\u002Freplay`.\n\n## Creating and verifying\n\n`szl_make_capsule(root, files, metadata=None, replay=None)` accepts plain path lists or role-tagged\nentries (`path` plus `role`). Paths must be canonical relative POSIX paths, unique, within hard\ncount and byte bounds; traversal, symlinks, junctions, reparse points and credential-like names\nare refused. `szl_verify_capsule(root, capsule)` re-hashes. All bytes matching plus a complete,\nvalid replay declaration yields `replay_ready: true`, meaning prepared for a separate sandbox review;\n`execution: NOT_RUN`, `capability_denial: DECLARED_ONLY` and `tolerance_application: NOT_RUN` stay\nexplicit. Read `references\u002Fcontracts.md` before authoring a replay.\n\nKeep an independently retained copy of the manifest when integrity across sessions matters: an\nunsigned self-digest cannot detect replacement of the whole manifest. `authentic: false` stays false\neven when every byte matches; real signing needs a key and a verifier (see szl-session-receipt for the\noptional signing path).\n\n## What it does not do\n\nNever executes argv or source, installs dependencies, launches processes, applies numerical\ncomparisons to outputs, or inspects file contents for secrets (credential-name guards look at names).\nLimits: 128 files, 8 MiB per file, 32 MiB total. It cannot prove source safety, enforce a sandbox or\nverify preregistration. Hashes are not signatures; readiness is not reproduction.\n",{"name":5,"license":15,"description":7},"main","8dd614e1f5097564340e36915f849d7d893cd68a","skills\u002Fszl-reproducibility-capsule","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-reproducibility-capsule",{"tool":38,"command":39},"bunx","bunx skills add szl-holdings\u002Fszl-skills --skill szl-reproducibility-capsule",{"tool":41,"command":42},"pnpm","pnpm dlx skills add szl-holdings\u002Fszl-skills --skill szl-reproducibility-capsule","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-reproducibility-capsule\u002FSKILL.md",true,[46,52,56,60,66,70,74,78,82,86,92],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"assets\u002Fexample.json","ASSET","资产文件",184,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-reproducibility-capsule\u002Fassets\u002Fexample.json",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"assets\u002Fprotocol.txt",270,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-reproducibility-capsule\u002Fassets\u002Fprotocol.txt",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"assets\u002Freplay-example.json",1166,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-reproducibility-capsule\u002Fassets\u002Freplay-example.json",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"assets\u002Freplay\u002Fanalysis.py","SCRIPT","脚本",110,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-reproducibility-capsule\u002Fassets\u002Freplay\u002Fanalysis.py",{"path":67,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":68,"sourceHtmlUrl":69},"assets\u002Freplay\u002Fenvironment.json",77,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-reproducibility-capsule\u002Fassets\u002Freplay\u002Fenvironment.json",{"path":71,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":72,"sourceHtmlUrl":73},"assets\u002Freplay\u002Finput.txt",58,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-reproducibility-capsule\u002Fassets\u002Freplay\u002Finput.txt",{"path":75,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":76,"sourceHtmlUrl":77},"assets\u002Freplay\u002Fplan.json",107,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-reproducibility-capsule\u002Fassets\u002Freplay\u002Fplan.json",{"path":79,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":80,"sourceHtmlUrl":81},"assets\u002Freplay\u002Fresult.txt",46,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-reproducibility-capsule\u002Fassets\u002Freplay\u002Fresult.txt",{"path":83,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":84,"sourceHtmlUrl":85},"kernel.py",15798,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-reproducibility-capsule\u002Fkernel.py",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fcontracts.md","REFERENCE","参考文档",5404,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-reproducibility-capsule\u002Freferences\u002Fcontracts.md",{"path":93,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Frun.py",3507,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-reproducibility-capsule\u002Fscripts\u002Frun.py",[97,104,111,118,124,129],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":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":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":119,"name":120,"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":121,"categories":122,"keywords":123,"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":125,"name":120,"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":126,"categories":127,"keywords":128,"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":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"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",[],[]]