[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DEMC43TC2W8YEBYY2JC1SH":3,"skill-same:01M7DEMC43TC2W8YEBYY2JC1SH":80},{"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},"01M7DEMC43TC2W8YEBYY2JC1SH","szl-session-receipt",null,"Writes a verifiable record of an analysis session: SHA-256 of every input, script and output file, the commands and environment as declared, a root digest, and a plain-language Methods paragraph; later re-hashes the files to report MATCH \u002F MISMATCH \u002F MISSING. Use at the end of a Claude Science or notebook session, when handing an analysis to a collaborator, when a journal asks for a reproducibility statement, or when the user says 'record what we just did'. Not a signature of correctness.","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-session-receipt\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: szl-session-receipt\ndescription: \"Writes a verifiable record of an analysis session: SHA-256 of every input, script and output file, the commands and environment as declared, a root digest, and a plain-language Methods paragraph; later re-hashes the files to report MATCH \u002F MISMATCH \u002F MISSING. Use at the end of a Claude Science or notebook session, when handing an analysis to a collaborator, when a journal asks for a reproducibility statement, or when the user says 'record what we just did'. Not a signature of correctness.\"\nlicense: Apache-2.0\n---\n\n# Session receipt\n\nA methods section that can be checked. While working, keep a manifest of the files read, the\nscripts run, the files produced and the commands used. `record` hashes all of it and writes the\nparagraph; `verify` re-hashes it tomorrow, or in a reviewer's hands, and says whether anything\nchanged. Stdlib only, offline; signing is optional and absence is stated, never hidden.\n\n## Use when\n\n- Ending an agent-assisted analysis: \"record this session\" produces the receipt and the paragraph.\n- Submitting: the Methods paragraph and the receipt file go in supplementary material.\n- Receiving a colleague's analysis: run `verify` against their files before reading their conclusions.\n- Re-running months later: a MISMATCH on the raw data file explains the different numbers before anyone argues.\n\n## Quick start\n\n```bash\npython scripts\u002Frun.py record assets\u002Fexample.json --root assets\u002Fproject --output \u002Ftmp\u002Freceipt.json\npython scripts\u002Frun.py verify \u002Ftmp\u002Freceipt.json --root assets\u002Fproject\npython scripts\u002Frun.py methods \u002Ftmp\u002Freceipt.json\n```\n\nThe synthetic project gives `\"status\": \"RECORDED\"`, `verify` gives `\"status\": \"MATCH\"` over 3 files, and\nthe paragraph reads:\n\n> Analysis for SYNTHETIC dose-response reanalysis was performed by an AI agent (Claude (Claude Science))\n> between 2026-10-01T14:00:00Z and 2026-10-01T14:25:00Z. It read 1 input file(s), executed 1 script(s) via\n> 1 recorded command(s), and produced 1 output file(s); the SHA-256 digest of every file is recorded in\n> session receipt e042750035a157ae (root digest ...). The environment was declared as Python 3.12.1 with\n> numpy 2.1.0, pandas 2.2.3. The receipt is unsigned; integrity can be re-verified by re-hashing the\n> listed files, authenticity is not established.\n\n## Manifest\n\n```json\n{\"project\": \"...\", \"session_id\": \"...\", \"started_at\": \"...Z\", \"finished_at\": \"...Z\",\n \"actor\": {\"kind\": \"agent|human\", \"name\": \"...\"},\n \"inputs\": [\"data\u002Fraw.csv\"], \"code\": [\"analysis.py\"], \"outputs\": [\"results\u002Fsummary.csv\"],\n \"commands\": [\"python analysis.py\"],\n \"environment\": {\"python\": \"3.12.1\", \"platform\": \"...\", \"packages\": {\"numpy\": \"2.1.0\"}}}\n```\n\nPaths are relative to `--root` and may not escape it. Fields under `declared_only` (commands,\nenvironment, actor, timestamps) are recorded as stated, not observed. Optional `--sign-key KEY.pem`\nproduces a DSSE signature when `szl-receipt-dsse` is installed; otherwise the receipt says UNSIGNED.\n\n## What it does not do\n\nA MATCH means the files are byte-identical to the recorded ones. It does not mean the analysis is\ncorrect, that the recorded commands were the only ones run, or that the declared environment was\nreal. It does not capture files you did not list. Details: `references\u002Fcontract.md`.\n","# Session receipt\n\nA methods section that can be checked. While working, keep a manifest of the files read, the\nscripts run, the files produced and the commands used. `record` hashes all of it and writes the\nparagraph; `verify` re-hashes it tomorrow, or in a reviewer's hands, and says whether anything\nchanged. Stdlib only, offline; signing is optional and absence is stated, never hidden.\n\n## Use when\n\n- Ending an agent-assisted analysis: \"record this session\" produces the receipt and the paragraph.\n- Submitting: the Methods paragraph and the receipt file go in supplementary material.\n- Receiving a colleague's analysis: run `verify` against their files before reading their conclusions.\n- Re-running months later: a MISMATCH on the raw data file explains the different numbers before anyone argues.\n\n## Quick start\n\n```bash\npython scripts\u002Frun.py record assets\u002Fexample.json --root assets\u002Fproject --output \u002Ftmp\u002Freceipt.json\npython scripts\u002Frun.py verify \u002Ftmp\u002Freceipt.json --root assets\u002Fproject\npython scripts\u002Frun.py methods \u002Ftmp\u002Freceipt.json\n```\n\nThe synthetic project gives `\"status\": \"RECORDED\"`, `verify` gives `\"status\": \"MATCH\"` over 3 files, and\nthe paragraph reads:\n\n> Analysis for SYNTHETIC dose-response reanalysis was performed by an AI agent (Claude (Claude Science))\n> between 2026-10-01T14:00:00Z and 2026-10-01T14:25:00Z. It read 1 input file(s), executed 1 script(s) via\n> 1 recorded command(s), and produced 1 output file(s); the SHA-256 digest of every file is recorded in\n> session receipt e042750035a157ae (root digest ...). The environment was declared as Python 3.12.1 with\n> numpy 2.1.0, pandas 2.2.3. The receipt is unsigned; integrity can be re-verified by re-hashing the\n> listed files, authenticity is not established.\n\n## Manifest\n\n```json\n{\"project\": \"...\", \"session_id\": \"...\", \"started_at\": \"...Z\", \"finished_at\": \"...Z\",\n \"actor\": {\"kind\": \"agent|human\", \"name\": \"...\"},\n \"inputs\": [\"data\u002Fraw.csv\"], \"code\": [\"analysis.py\"], \"outputs\": [\"results\u002Fsummary.csv\"],\n \"commands\": [\"python analysis.py\"],\n \"environment\": {\"python\": \"3.12.1\", \"platform\": \"...\", \"packages\": {\"numpy\": \"2.1.0\"}}}\n```\n\nPaths are relative to `--root` and may not escape it. Fields under `declared_only` (commands,\nenvironment, actor, timestamps) are recorded as stated, not observed. Optional `--sign-key KEY.pem`\nproduces a DSSE signature when `szl-receipt-dsse` is installed; otherwise the receipt says UNSIGNED.\n\n## What it does not do\n\nA MATCH means the files are byte-identical to the recorded ones. It does not mean the analysis is\ncorrect, that the recorded commands were the only ones run, or that the declared environment was\nreal. It does not capture files you did not list. Details: `references\u002Fcontract.md`.\n",{"name":5,"license":15,"description":7},"main","8dd614e1f5097564340e36915f849d7d893cd68a","skills\u002Fszl-session-receipt","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-session-receipt",{"tool":38,"command":39},"bunx","bunx skills add szl-holdings\u002Fszl-skills --skill szl-session-receipt",{"tool":41,"command":42},"pnpm","pnpm dlx skills add szl-holdings\u002Fszl-skills --skill szl-session-receipt","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-session-receipt\u002FSKILL.md",true,[46,52,58,62,66,70,76],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"assets\u002Fexample.json","ASSET","资产文件",531,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-session-receipt\u002Fassets\u002Fexample.json",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"assets\u002Fproject\u002Fanalysis.py","SCRIPT","脚本",76,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-session-receipt\u002Fassets\u002Fproject\u002Fanalysis.py",{"path":59,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":60,"sourceHtmlUrl":61},"assets\u002Fproject\u002Fdata\u002Fraw.csv",31,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-session-receipt\u002Fassets\u002Fproject\u002Fdata\u002Fraw.csv",{"path":63,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":64,"sourceHtmlUrl":65},"assets\u002Fproject\u002Fresults\u002Fsummary.csv",23,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-session-receipt\u002Fassets\u002Fproject\u002Fresults\u002Fsummary.csv",{"path":67,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":68,"sourceHtmlUrl":69},"kernel.py",9384,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-session-receipt\u002Fkernel.py",{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fcontract.md","REFERENCE","参考文档",961,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-session-receipt\u002Freferences\u002Fcontract.md",{"path":77,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":78,"sourceHtmlUrl":79},"scripts\u002Frun.py",2069,"https:\u002F\u002Fgithub.com\u002Fszl-holdings\u002Fszl-skills\u002Fblob\u002Fmain\u002Fskills\u002Fszl-session-receipt\u002Fscripts\u002Frun.py",[81,88,95,102,108,113],{"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":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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"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":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"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":103,"name":104,"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":105,"categories":106,"keywords":107,"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":109,"name":104,"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":110,"categories":111,"keywords":112,"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":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"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",[],[]]