[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EDC1N2NM7AV9WTYGDNJFTD":3,"skill-same:01M7EDC1N2NM7AV9WTYGDNJFTD":49},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7EDC1N2NM7AV9WTYGDNJFTD","benchmark-optimization-loop",null,"Use when the user asks to make something faster, try many variants, run recursive optimization, benchmark latency\u002Fthroughput\u002Fcost, or choose the best implementation by repeated measured tests.","sanjeevafk\u002Fagent-skills","sanjeevafk","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F230678117?v=4","01M7C540EFY46ETG1NNWKS5X3Q","Sanjeev","01M7C540F366J5C1D587BMKH9Q",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbenchmark-optimization-loop\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: benchmark-optimization-loop\ndescription: Use when the user asks to make something faster, try many variants, run recursive optimization, benchmark latency\u002Fthroughput\u002Fcost, or choose the best implementation by repeated measured tests.\nlicense: MIT\nmetadata:\n  origin: ECC\ntools: Read, Write, Edit, Bash, Grep, Glob\n---\n\n# Benchmark Optimization Loop\n\nUse this skill to convert \"make it 20x faster\" or \"try 50 recursive\noptimizations\" into a bounded measured loop that can actually improve a system.\n\n## Required Baseline\n\nDo not optimize until these exist:\n\n- the operation being optimized;\n- the correctness gate that must stay green;\n- the metric: wall time, p95 latency, rows\u002Fsec, cost\u002Frun, memory, error rate;\n- the current baseline;\n- the search budget: max variants, max time, max spend, max data impact.\n\nIf the user asks for an unrealistic target, keep the ambition but make the loop\nbounded and measurable.\n\n## Loop\n\n1. Measure the baseline.\n2. Identify bottlenecks from evidence.\n3. Generate variants that test one hypothesis each.\n4. Run variants with the same input shape.\n5. Reject variants that fail correctness, safety, or reproducibility.\n6. Promote the fastest safe variant.\n7. Codify the winning path in a script, command, test, config, or doc.\n8. Rerun the baseline and winner to confirm the delta.\n\n## Variant Table\n\nTrack variants like this:\n\n```text\nVariant | Hypothesis | Command | Time | Correct? | Notes\nbaseline | current path | npm run job | 120s | yes | stable\nbatch-500 | fewer round trips | npm run job -- --batch 500 | 42s | yes | winner\nparallel-8 | more workers | npm run job -- --workers 8 | 31s | no | rate limited\n```\n\n## Recursive Search\n\nFor recursive or hyperparameter work:\n\n- persist every run to a ledger;\n- compare against the prior accepted winner, not only the previous run;\n- keep a holdout or replay check;\n- stop when improvement is within noise, correctness fails, cost exceeds the\n  budget, or the search starts changing more variables than it can explain.\n\nUse phrases like \"best measured safe variant\" instead of \"global optimum\" unless\nthe search space was actually exhaustive.\n\n## Promotion Gate\n\nA variant cannot become the new default until:\n\n- correctness tests pass;\n- the performance delta is repeated or explained;\n- rollback is obvious;\n- the change is encoded in source control or a durable runbook;\n- the final summary includes exact commands and measurements.\n","# Benchmark Optimization Loop\n\nUse this skill to convert \"make it 20x faster\" or \"try 50 recursive\noptimizations\" into a bounded measured loop that can actually improve a system.\n\n## Required Baseline\n\nDo not optimize until these exist:\n\n- the operation being optimized;\n- the correctness gate that must stay green;\n- the metric: wall time, p95 latency, rows\u002Fsec, cost\u002Frun, memory, error rate;\n- the current baseline;\n- the search budget: max variants, max time, max spend, max data impact.\n\nIf the user asks for an unrealistic target, keep the ambition but make the loop\nbounded and measurable.\n\n## Loop\n\n1. Measure the baseline.\n2. Identify bottlenecks from evidence.\n3. Generate variants that test one hypothesis each.\n4. Run variants with the same input shape.\n5. Reject variants that fail correctness, safety, or reproducibility.\n6. Promote the fastest safe variant.\n7. Codify the winning path in a script, command, test, config, or doc.\n8. Rerun the baseline and winner to confirm the delta.\n\n## Variant Table\n\nTrack variants like this:\n\n```text\nVariant | Hypothesis | Command | Time | Correct? | Notes\nbaseline | current path | npm run job | 120s | yes | stable\nbatch-500 | fewer round trips | npm run job -- --batch 500 | 42s | yes | winner\nparallel-8 | more workers | npm run job -- --workers 8 | 31s | no | rate limited\n```\n\n## Recursive Search\n\nFor recursive or hyperparameter work:\n\n- persist every run to a ledger;\n- compare against the prior accepted winner, not only the previous run;\n- keep a holdout or replay check;\n- stop when improvement is within noise, correctness fails, cost exceeds the\n  budget, or the search starts changing more variables than it can explain.\n\nUse phrases like \"best measured safe variant\" instead of \"global optimum\" unless\nthe search space was actually exhaustive.\n\n## Promotion Gate\n\nA variant cannot become the new default until:\n\n- correctness tests pass;\n- the performance delta is repeated or explained;\n- rollback is obvious;\n- the change is encoded in source control or a durable runbook;\n- the final summary includes exact commands and measurements.\n",{"name":5,"tools":24,"license":15,"metadata":25,"description":7},"Read, Write, Edit, Bash, Grep, Glob",{"origin":26},"ECC","main","4e084e84eb42fc53e144c89c0f7f48b39c8a4b0f","skills\u002Fbenchmark-optimization-loop",1,"https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills","https:\u002F\u002Fgithub.com\u002Fsanjeevafk","First make it work. Then make it right. Then make it fast.","2026-11-14 13:36:16",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add sanjeevafk\u002Fagent-skills --skill benchmark-optimization-loop",{"tool":41,"command":42},"bunx","bunx skills add sanjeevafk\u002Fagent-skills --skill benchmark-optimization-loop",{"tool":44,"command":45},"pnpm","pnpm dlx skills add sanjeevafk\u002Fagent-skills --skill benchmark-optimization-loop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fbenchmark-optimization-loop\u002FSKILL.md",true,[],[50,57,65,74,82,89],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7EFHX67M3KKXT1BXVPA5ADT","zarr-python","Chunked N-D arrays for cloud storage (Zarr-Python 3). Compressed arrays, parallel I\u002FO, S3\u002FGCS via fsspec, NumPy\u002FDask\u002FXarray compatible, for large-scale scientific computing pipelines.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":61,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7EFFQGM51TZBGRENXY50ZYM","whiteboard-diagrams","Create accurate, simple, hand-drawn whiteboard diagrams from a user's process, system, architecture, learning workflow, comparison, or causal explanation. Use when the user asks for a scribbly whiteboard visual, educational workflow graphic, hand-drawn explainer, or diagram like the bundled reference; ask one focused clarification question when the subject or relationships are missing, then generate and visually verify the final image.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwhiteboard-diagrams\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwhiteboard-diagrams\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7EFF1CSQNTDMHFK4ZGY6NYK","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7EFE8106X6C28FT8PA74427","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7EFCSNZM9G7ZHS6F127Q71X","verification-loop","A comprehensive verification system for Claude Code sessions.","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7EFCE7EZMKPRYDDNKBQ9EEH","vercel-deploy","Deploy applications and websites to Vercel. Use when the user requests deployment actions like \"deploy my app\", \"deploy and give me the link\", \"push this live\", or \"create a preview deployment\".","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-deploy\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fsanjeevafk\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-deploy\u002FSKILL.md",[],[]]