[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DJD3TJCDCXKN7D9CB87WKB":3,"skill-same:01M6DJD3TJCDCXKN7D9CB87WKB":83},{"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":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":14,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M6DJD3TJCDCXKN7D9CB87WKB","audit-scientific-claim",null,"Audit claims against hashed evidence while separating verification, validation, and uncertainty quantification.","dasobral\u002Fskills","dasobral","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108470360?v=4","01M6DJBRR588S4TSNFT0ZYY6BV","Daniel SB","01M6DJBRWBDEBPCQ874SWDZWZR",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Faudit-scientific-claim\u002FSKILL.md",[],[19,20,21,22,23,24],"audit","claim","audit scientific claim","validation","verification","evidence","2026-11-10 10:12:30",false,"---\nname: audit-scientific-claim\ndescription: Audit claims against hashed evidence while separating verification, validation, and uncertainty quantification.\nlicense: MIT\nmetadata:\n  plugin: scientific-claim-ledger\n  version: \"0.1.0\"\n---\n\n# Audit Scientific Claim\n\nBuild a claim-to-evidence graph using\n`references\u002Fclaim-evidence-graph.schema.json`.\n\n## Assurance activities\n\nKeep these activities separate; evidence for one does not satisfy another:\n\n1. **Code verification** — was the intended algorithm implemented correctly?\n2. **Solution verification** — was the mathematical problem solved accurately?\n3. **Model validation** — is the model adequate for the stated context of use?\n4. **Uncertainty quantification** — what uncertainty applies to the predicted\n   quantity and how was it propagated or calibrated?\n\nEvery edge must name its activity, test, run, artifact SHA-256, acceptance\ncriterion, evidence state, reviewer decision, and decision source. Evidence\nstate is exactly `pass`, `fail`, `unknown`, `not-applicable`, or\n`evidence-gap`; reviewer and workflow decisions use separate vocabularies.\n\n## Workflow\n\n1. Normalize claim wording, scope, context of use, and quantity of interest.\n2. Add evidence edges without collapsing the four assurance activities.\n3. Mark absent or inapplicable evidence explicitly.\n4. Store every referenced artifact below an explicit evidence root using a\n   relative path and its SHA-256. Reference each run through its contained\n   run-record path and SHA-256; a caller-supplied run ID alone is not evidence.\n   The run record must recompute to that `run_id` and its `artifacts` map must\n   bind every claim edge's relative path to the same artifact SHA-256. Run\n   `python3 scripts\u002Fvalidate_claim_graph.py --evidence-root \u003Cdirectory> \u003Cclaim-graph.json>`.\n   Validation rejects absolute paths, traversal, symlink escape, missing files,\n   hash mismatches, modified run records, and artifacts unbound to their run.\n5. Route findings to an accountable human reviewer or deterministic acceptance\n   check. Agent analysis alone cannot produce an accepted\u002Fpass decision.\n\n## Rules\n\n- Do not upgrade correlation, low residual, or benchmark performance into model\n  validation.\n- Preserve contradictory evidence and rejected edges.\n- Do not let the claim auditor make the final pass decision.\n","# Audit Scientific Claim\n\nBuild a claim-to-evidence graph using\n`references\u002Fclaim-evidence-graph.schema.json`.\n\n## Assurance activities\n\nKeep these activities separate; evidence for one does not satisfy another:\n\n1. **Code verification** — was the intended algorithm implemented correctly?\n2. **Solution verification** — was the mathematical problem solved accurately?\n3. **Model validation** — is the model adequate for the stated context of use?\n4. **Uncertainty quantification** — what uncertainty applies to the predicted\n   quantity and how was it propagated or calibrated?\n\nEvery edge must name its activity, test, run, artifact SHA-256, acceptance\ncriterion, evidence state, reviewer decision, and decision source. Evidence\nstate is exactly `pass`, `fail`, `unknown`, `not-applicable`, or\n`evidence-gap`; reviewer and workflow decisions use separate vocabularies.\n\n## Workflow\n\n1. Normalize claim wording, scope, context of use, and quantity of interest.\n2. Add evidence edges without collapsing the four assurance activities.\n3. Mark absent or inapplicable evidence explicitly.\n4. Store every referenced artifact below an explicit evidence root using a\n   relative path and its SHA-256. Reference each run through its contained\n   run-record path and SHA-256; a caller-supplied run ID alone is not evidence.\n   The run record must recompute to that `run_id` and its `artifacts` map must\n   bind every claim edge's relative path to the same artifact SHA-256. Run\n   `python3 scripts\u002Fvalidate_claim_graph.py --evidence-root \u003Cdirectory> \u003Cclaim-graph.json>`.\n   Validation rejects absolute paths, traversal, symlink escape, missing files,\n   hash mismatches, modified run records, and artifacts unbound to their run.\n5. Route findings to an accountable human reviewer or deterministic acceptance\n   check. Agent analysis alone cannot produce an accepted\u002Fpass decision.\n\n## Rules\n\n- Do not upgrade correlation, low residual, or benchmark performance into model\n  validation.\n- Preserve contradictory evidence and rejected edges.\n- Do not let the claim auditor make the final pass decision.\n",{"name":5,"license":15,"metadata":30,"description":7},{"plugin":31,"version":32},"scientific-claim-ledger","0.1.0","main","1e047a4b00be0c07efa464cd97f36fa39d4b1718","skills\u002Faudit-scientific-claim","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills","https:\u002F\u002Fgithub.com\u002Fdasobral","https:\u002F\u002Forcid.org\u002Fmy-orcid?orcid=0000-0001-9559-3651","Software Engineer with a Ph. D. in Physics","2026-08-15 21:49:02",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add dasobral\u002Fskills --skill audit-scientific-claim",{"tool":47,"command":48},"bunx","bunx skills add dasobral\u002Fskills --skill audit-scientific-claim",{"tool":50,"command":51},"pnpm","pnpm dlx skills add dasobral\u002Fskills --skill audit-scientific-claim","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Faudit-scientific-claim\u002FSKILL.md",true,[55,61,65,71,75,79],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fapi_reference.md","REFERENCE","参考文档",13117,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fopentrons-integration\u002Freferences\u002Fapi_reference.md",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fclaim-evidence-graph.schema.json",2958,"https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Faudit-scientific-claim\u002Freferences\u002Fclaim-evidence-graph.schema.json",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fbasic_protocol_template.py","SCRIPT","脚本",1537,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fopentrons-integration\u002Fscripts\u002Fbasic_protocol_template.py",{"path":72,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Fpcr_setup_template.py",4538,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fopentrons-integration\u002Fscripts\u002Fpcr_setup_template.py",{"path":76,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fserial_dilution_template.py",3171,"https:\u002F\u002Fgithub.com\u002Fstrmt7\u002Fai_skills_collection_benchmarked\u002Fblob\u002Fmain\u002Fincluded\u002Fskills\u002Fby-category\u002Fscience-research-data-analysis\u002Flatest-release-community\u002Fopentrons-integration\u002Fscripts\u002Fserial_dilution_template.py",{"path":80,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":81,"sourceHtmlUrl":82},"scripts\u002Fvalidate_claim_graph.py",9372,"https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Faudit-scientific-claim\u002Fscripts\u002Fvalidate_claim_graph.py",[84,101,135,155,188,212],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":95,"publishedAt":25},"01M6DJFKJASZX8BMFGRQBEKFY9","fixture-skill","Fixture skill used to prove trust inventory coverage.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Ftools\u002Fskills-export\u002Ftests\u002Ffixtures\u002Fworkflows\u002Fagent-security\u002Frepository\u002F.cursor\u002Fskills\u002Ffixture-skill\u002FSKILL.md",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[96,97,98,99,100],"fixture","fixture skill","trust","coverage","inventory",{"skillNo":102,"name":103,"nameZh":6,"description":104,"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":118,"publishedAt":25},"01M6DJFG24D9X2WAP411JJP71W","write-conformant-code","Write code in any language that matches project conventions exactly. Reads CODING_REQUIREMENTS.md, prior review output, or built-in defaults before writing. Part of Codecraft pipeline: analyze → write → review → audit. Use when implementing features, functions, or any code that should fit seamlessly into an existing codebase.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-conformant-code\u002FSKILL.md",[107,110,115],{"categoryNo":108,"categoryName":109,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":111,"categoryName":112,"taxonomyType":113,"taxonomyTypeDesc":114},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":116,"categoryName":117,"taxonomyType":113,"taxonomyTypeDesc":114},"01JBSEEDCAT000000000000036","内容创作者",[119,120,121,122,123,124,125,126,127,19,128,129,130,131,132,133,134],"code","write","write conformant code","conventions","writing","review","fit","project conventions","requirements","pipeline","analyze","coding","project","use","functions","language",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":144,"publishedAt":25},"01M6DJFDDCWB5VMAYE79YTZB40","test-crypto-interoperability","Record reproducible cryptographic interoperability cases, including negotiation, fallback, sizes, latency, fragmentation, and negative tests.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ftest-crypto-interoperability\u002FSKILL.md",[141],{"categoryNo":142,"categoryName":143,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000008","测试与质量",[145,146,147,148,149,150,151,152,153,154],"test","interoperability","crypto","test crypto interoperability","negotiation","Reproducible","fallback","record","latency","tests",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":170,"publishedAt":25},"01M6DJF68YHCTQA473PSH24HSK","scientific-platform-architect","Design scientific computing platforms combining HPC kernels with modern infrastructure. Enforces compute-layer separation (Rust\u002FPyTorch\u002FPython), emulator-first thinking, and right-sized infrastructure. Use for MCMC pipelines, neural emulators, platform design, or scientific code review.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fscientific-platform-architect\u002FSKILL.md",[161,164,167],{"categoryNo":162,"categoryName":163,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000007","代码审查",{"categoryNo":165,"categoryName":166,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":168,"categoryName":169,"taxonomyType":113,"taxonomyTypeDesc":114},"01JBSEEDCAT000000000000032","设计师",[171,172,173,174,175,176,177,178,179,132,180,181,119,182,183,184,185,124,186,187],"platform","scientific platform architect","architect","emulators","scientific computing","pytorch","thinking","Neural","pipelines","platform design","first","infrastructure","compute","rust","python","design","code review",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":195,"publishedAt":25},"01M6DJF2D8ZNG4439WQ21CQ75D","rust-systems","Rust systems engineering for daemons, HTTP APIs, and AOS components. Enforces Tokio\u002FAxum async-first, LiteLLM-compatible OpenAI APIs, workspace layouts, tracing, and systemd-compatible daemon design. Part of AOS Stack plugin. Use for .rs files, Cargo.toml, daemons, or Rust orchestrator services.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Frust-systems\u002FSKILL.md",[194],{"categoryNo":165,"categoryName":166,"taxonomyType":93,"taxonomyTypeDesc":94},[196,197,184,198,132,199,200,201,202,181,203,204,205,206,207,208,186,209,210,211],"rust systems","systems","openai","orchestrator","litellm","workspace","stack","services","tracing","async","plugin","http","components","cargo","toml","files",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":216,"categories":217,"keywords":219,"publishedAt":25},"01M6DJEYP0JJX0XJPJYR36VRTW","run-agent-attack-replay","Aggregate isolated agent attack trials with deterministic side-effect assertions, Wilson intervals, and preserved trace evidence.","https:\u002F\u002Fgithub.com\u002Fdasobral\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Frun-agent-attack-replay\u002FSKILL.md",[218],{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[220,221,222,223,24,224,225],"run","replay","run agent attack replay","deterministic","effect","trace"]