[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EDZ6XMJGCBTD249C1K1DFQ":3,"skill-same:01M7EDZ6XMJGCBTD249C1K1DFQ":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":28,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7EDZ6XMJGCBTD249C1K1DFQ","scientific-rust-differential-test-design",null,"Design differential and invariant tests for scientific Rust against a characterized independent reference, including floating-point edge cases and reproducible failing inputs.","Plaetorius\u002Fengineering-harness","Plaetorius","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F46137705?v=4","01M7EDZ4R8H5FQXH3HRT7PQCCT","01M7EDZ4TJ6VR9DVHS97FTHVEY",0,"MIT","https:\u002F\u002Fgithub.com\u002FPlaetorius\u002Fengineering-harness\u002Fblob\u002Fmain\u002Fpacks\u002Fscientific-rust\u002Fskills\u002Fscientific-rust-differential-test-design\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: scientific-rust-differential-test-design\ndescription: Design differential and invariant tests for scientific Rust against a characterized independent reference, including floating-point edge cases and reproducible failing inputs.\n---\n\nRead [numerical contracts](..\u002F..\u002Fstandards\u002Fnumerical-correctness.md). Establish the reference contract first; use the reference-characterization skill when it is genuinely missing. Identify the slice's scientific claim, reference uncertainty and intended precision\u002Ffeature\u002Foptimized-build matrix.\n\nDesign paired cases over the justified input domain, including near-zero outputs, boundaries, scale extremes, ill-conditioned regions and invalid inputs. Specify conversions, units, shape\u002Flength checks and nonfinite handling before any tolerance expression. State absolute\u002Frelative\u002Fnorm or statistical criteria with a scientific rationale. Include at least one case that exposes a plausible implementation defect; passing identical copies of an algorithm does not provide independence.\n\nCombine reference comparisons with applicable analytical solutions, convergence tests, conservation\u002Fmetamorphic properties and negative cases. Explain why each property follows from this method. For randomized cases record seeds and streams, retain\u002Fminimize failing examples, and distinguish deterministic regression from statistical assurance. Never widen tolerances or discard failures without investigating their cause and obtaining any required criteria revision.\n\nFit the cases into existing project tests and named `scientific-differential` \u002F `scientific-invariants` commands. For a design request, produce the test matrix and proposed commands without editing code. When implementation is requested, add tests within the allowed slice and run only authorized checks. Report actual results, missing reference coverage and resource limits; absent mandatory commands must remain visible as skipped\u002Fblocked checks.\n","Read [numerical contracts](..\u002F..\u002Fstandards\u002Fnumerical-correctness.md). Establish the reference contract first; use the reference-characterization skill when it is genuinely missing. Identify the slice's scientific claim, reference uncertainty and intended precision\u002Ffeature\u002Foptimized-build matrix.\n\nDesign paired cases over the justified input domain, including near-zero outputs, boundaries, scale extremes, ill-conditioned regions and invalid inputs. Specify conversions, units, shape\u002Flength checks and nonfinite handling before any tolerance expression. State absolute\u002Frelative\u002Fnorm or statistical criteria with a scientific rationale. Include at least one case that exposes a plausible implementation defect; passing identical copies of an algorithm does not provide independence.\n\nCombine reference comparisons with applicable analytical solutions, convergence tests, conservation\u002Fmetamorphic properties and negative cases. Explain why each property follows from this method. For randomized cases record seeds and streams, retain\u002Fminimize failing examples, and distinguish deterministic regression from statistical assurance. Never widen tolerances or discard failures without investigating their cause and obtaining any required criteria revision.\n\nFit the cases into existing project tests and named `scientific-differential` \u002F `scientific-invariants` commands. For a design request, produce the test matrix and proposed commands without editing code. When implementation is requested, add tests within the allowed slice and run only authorized checks. Report actual results, missing reference coverage and resource limits; absent mandatory commands must remain visible as skipped\u002Fblocked checks.\n",{"name":5,"description":7},"main","d5f52b0a47554bbb7a19a178d3bd242c175b1621","packs\u002Fscientific-rust\u002Fskills\u002Fscientific-rust-differential-test-design","https:\u002F\u002Fgithub.com\u002FPlaetorius\u002Fengineering-harness","https:\u002F\u002Fgithub.com\u002FPlaetorius","https:\u002F\u002Fprediction.live","cybersecurity for real estate agencies","2026-10-30 08:07:26",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Plaetorius\u002Fengineering-harness --skill scientific-rust-differential-test-design",{"tool":37,"command":38},"bunx","bunx skills add Plaetorius\u002Fengineering-harness --skill scientific-rust-differential-test-design",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Plaetorius\u002Fengineering-harness --skill scientific-rust-differential-test-design","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPlaetorius\u002Fengineering-harness\u002Fblob\u002Fmain\u002Fpacks\u002Fscientific-rust\u002Fskills\u002Fscientific-rust-differential-test-design\u002FSKILL.md",true,[],[46,53,60,67,74,81],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M7EE15EJFDDRMJJZD4J5DX52","example-review","Review synthetic example changes for their stated acceptance criteria.","https:\u002F\u002Fgithub.com\u002FPlaetorius\u002Fengineering-harness\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fexample-pack\u002Fskills\u002Fexample-review\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M7EE0ZKM50KENXQEXBMYY4C6","second-reader","Independent second reader for supply-chain and data documents (RFQs, supplier quotes, emails, PDFs including scanned, spreadsheets, CSV\u002FJSON). Extracts values with source evidence, runs deterministic checks, compares quotes against an RFQ and a bid price, and briefs the human on what they may have missed while they review the same material. Every step is logged in a SQLite ledger.","https:\u002F\u002Fgithub.com\u002FPlaetorius\u002Fengineering-harness\u002Fblob\u002Fmain\u002Fskills\u002Fsecond-reader\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M7EE0TPNA6DJGNCD1BFRTNN6","second-reader-offline","The no-AI, no-network variant of second-reader for confidential client documents. Reads with local rules and OCR, checks and compares with code, and produces a self-contained HTML report on the user's own machine. The assistant must not read the documents or the report.","https:\u002F\u002Fgithub.com\u002FPlaetorius\u002Fengineering-harness\u002Fblob\u002Fmain\u002Fskills\u002Fsecond-reader-offline\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M7EE0QDXBTY46Y0A53YBFV11","review","Review an engineering plan, diff, code or architecture from a general or selected professional perspective, challenging assumptions with evidence and no automatic implementation edits.","https:\u002F\u002Fgithub.com\u002FPlaetorius\u002Fengineering-harness\u002Fblob\u002Fmain\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7EE0NFB4M0J33ZT16E57269","review-diff","Compatibility entry point for evidence-based diff review; establish the intended baseline and inspect consequential changes read-only.","https:\u002F\u002Fgithub.com\u002FPlaetorius\u002Fengineering-harness\u002Fblob\u002Fmain\u002Fskills\u002Freview-diff\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M7EE0J9AQG23MYB6VCHPWAK8","plan-feature","Plan a new subsystem, cross-cutting feature, migration or explicitly requested design before implementation. Routine local edits can proceed directly.","https:\u002F\u002Fgithub.com\u002FPlaetorius\u002Fengineering-harness\u002Fblob\u002Fmain\u002Fskills\u002Fplan-feature\u002FSKILL.md",[],[]]