[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EDZF6669V7QYT83VSSF4RM":3,"skill-same:01M7EDZF6669V7QYT83VSSF4RM":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},"01M7EDZF6669V7QYT83VSSF4RM","scientific-rust-performance-benchmarking",null,"Design or run an explicitly budgeted scientific Rust benchmark comparing equivalent numerical workloads with reproducible timing, memory and scaling evidence.","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-performance-benchmarking\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: scientific-rust-performance-benchmarking\ndescription: Design or run an explicitly budgeted scientific Rust benchmark comparing equivalent numerical workloads with reproducible timing, memory and scaling evidence.\n---\n\nRead [Rust performance](..\u002F..\u002Fstandards\u002Frust-performance.md) and [reproducibility](..\u002F..\u002Fstandards\u002Freproducible-research.md). Establish the performance question, baseline revision, workload, accuracy contract and resource budget. Confirm correctness equivalence before interpreting speed differences. Inspect existing benchmark targets\u002Ftools and actual project commands; do not install a framework or assume a nightly harness.\n\nDefine inputs, optimized profile, target\u002Ffeatures, precision, thread counts, warmup, repetitions, noise controls and reported statistic. Specify which costs are included (setup, transfer, I\u002FO, kernel, full run) and relevant memory\u002Fscaling metrics. Account for dead-code elimination, caches and nested thread pools. Record hardware and software context without environment\u002Fcredential dumps.\n\nPrefer a small representative experiment before an expensive run. Execute only authorized workloads within declared wall-time\u002Fmemory\u002Fdisk\u002Fworker limits using existing project\u002FOS controls. Pack activation and a runner timeout are not authorization or resource isolation. Missing hardware, references or budget block claims that depend on them; do not submit cluster jobs or download large data automatically.\n\nUse the profile's `scientific-benchmark` command for repeatable runs. Return baseline\u002Fcandidate commands and revisions, accuracy evidence, sample\u002Fvariability statistics, memory\u002Fresource observations, artifact locations, limitations and the scope of any supported claim. For design-only requests return a protocol, not invented timings. Unmeasured optimizations remain hypotheses; do not cherry-pick samples or silently change tolerances\u002Fworkloads.\n","Read [Rust performance](..\u002F..\u002Fstandards\u002Frust-performance.md) and [reproducibility](..\u002F..\u002Fstandards\u002Freproducible-research.md). Establish the performance question, baseline revision, workload, accuracy contract and resource budget. Confirm correctness equivalence before interpreting speed differences. Inspect existing benchmark targets\u002Ftools and actual project commands; do not install a framework or assume a nightly harness.\n\nDefine inputs, optimized profile, target\u002Ffeatures, precision, thread counts, warmup, repetitions, noise controls and reported statistic. Specify which costs are included (setup, transfer, I\u002FO, kernel, full run) and relevant memory\u002Fscaling metrics. Account for dead-code elimination, caches and nested thread pools. Record hardware and software context without environment\u002Fcredential dumps.\n\nPrefer a small representative experiment before an expensive run. Execute only authorized workloads within declared wall-time\u002Fmemory\u002Fdisk\u002Fworker limits using existing project\u002FOS controls. Pack activation and a runner timeout are not authorization or resource isolation. Missing hardware, references or budget block claims that depend on them; do not submit cluster jobs or download large data automatically.\n\nUse the profile's `scientific-benchmark` command for repeatable runs. Return baseline\u002Fcandidate commands and revisions, accuracy evidence, sample\u002Fvariability statistics, memory\u002Fresource observations, artifact locations, limitations and the scope of any supported claim. For design-only requests return a protocol, not invented timings. Unmeasured optimizations remain hypotheses; do not cherry-pick samples or silently change tolerances\u002Fworkloads.\n",{"name":5,"description":7},"main","d5f52b0a47554bbb7a19a178d3bd242c175b1621","packs\u002Fscientific-rust\u002Fskills\u002Fscientific-rust-performance-benchmarking","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-performance-benchmarking",{"tool":37,"command":38},"bunx","bunx skills add Plaetorius\u002Fengineering-harness --skill scientific-rust-performance-benchmarking",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Plaetorius\u002Fengineering-harness --skill scientific-rust-performance-benchmarking","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPlaetorius\u002Fengineering-harness\u002Fblob\u002Fmain\u002Fpacks\u002Fscientific-rust\u002Fskills\u002Fscientific-rust-performance-benchmarking\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",[],[]]