[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PB8KYEB2807W7BQ6ECHT9N":3,"skill-same:01M6PB8KYEB2807W7BQ6ECHT9N":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":31,"commitSha":58,"skillDirectory":59,"forksCount":13,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":62,"install":63,"resources":76},"01M6PB8KYEB2807W7BQ6ECHT9N","optim-agent",null,"Guide agent-driven parameter optimization for configurable systems with measurable objectives. Use for HPO, inference tuning, simulations, or RL\u002Fcontrol experiments.","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Foptim-agent\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"optim agent","rl","for","hyperparameter-optimization","with","systems","parameter optimization","control","main","community","safe","use","cursor","tuning","Optimization","https","license","codex","github","gemini","2026-11-10 10:12:30",false,"---\nname: optim-agent\ndescription: \"Guide agent-driven parameter optimization for configurable systems with measurable objectives. Use for HPO, inference tuning, simulations, or RL\u002Fcontrol experiments.\"\ncategory: data\nrisk: safe\nsource: community\nsource_repo: Optim-Agent\u002Foptim-agent\nsource_type: community\ndate_added: \"2026-07-15\"\nauthor: Optim-Agent\ntags: [optimization, hyperparameter-optimization, experiments, tuning]\ntools: [claude, cursor, gemini, codex]\nlicense: MIT\nlicense_source: \"https:\u002F\u002Fgithub.com\u002FOptim-Agent\u002Foptim-agent\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# Optim Agent\n\n## Overview\n\nUse this skill to optimize configurable systems against a measurable scalar objective. It helps an agent turn vague tuning requests into bounded experiments with a defined search space, budget, baseline, and evidence-backed recommendation.\n\n## When to Use This Skill\n\n- Use when tuning hyperparameters, prompts, inference settings, simulation parameters, quantitative strategies, or RL\u002Fcontrol policies.\n- Use when the objective can be measured as a scalar score, loss, accuracy, cost, latency, reward, or risk-adjusted metric.\n- Use when the user needs a small-budget optimization loop with trial history, comparisons, and stop criteria.\n\n## Do not use this skill when\n\n- The objective is purely subjective and cannot be scored consistently.\n- The user has not provided permission to run experiments or consume compute\u002FAPI budget.\n- The task is a one-shot implementation, debugging, or code review request with no configurable search space.\n\n## Instructions\n\n1. Define the optimization target in one sentence: maximize or minimize one scalar metric.\n2. List the tunable parameters, valid ranges, types, defaults, and any forbidden combinations.\n3. Establish at least one baseline before proposing agent-guided trials.\n4. Set the budget up front: number of trials, time, compute, money, or dataset subsample.\n5. Run or request trials one at a time unless the user explicitly approves parallel execution.\n6. Record every trial with parameters, metric value, notes, and failure status.\n7. Compare the best result against the baseline and a simple search strategy when possible.\n8. Stop when the budget is exhausted, the improvement plateaus, or the next trial cannot be justified from evidence.\n9. Report the recommended configuration, measured gain, tradeoffs, and any validation still needed before production use.\n\n## Examples\n\n### Example 1: Hyperparameter optimization\n\nTune learning rate, regularization, and tree depth for a credit-default model. Track validation AUC for each trial, compare against the default configuration, and recommend the best setting only if it improves the baseline under the agreed trial budget.\n\n### Example 2: Inference tuning\n\nTune retrieval depth, temperature, and reranker threshold for a RAG workflow. Optimize answer quality under a latency or cost ceiling, then report the best configuration with quality, latency, and cost tradeoffs.\n\n### Example 3: Simulation or control\n\nTune controller gains or environment parameters for a simulator. Optimize reward or error while logging failed trials separately so unstable configurations do not bias the recommendation.\n\n## Best Practices\n\n- Keep the first run small; expand only after the loop produces useful signal.\n- Prefer parameters with clear operational meaning over arbitrary knobs.\n- Treat failed trials as data and record why they failed.\n- Validate the final configuration on held-out data, a fresh seed, or a separate scenario before calling it robust.\n- Ask before running expensive, long, or externally billed experiments.\n\n## Limitations\n\n- This skill does not guarantee a global optimum.\n- Results depend on objective quality, noise, search-space design, and experiment reproducibility.\n- Use domain review before applying tuned configurations to production, financial, safety-critical, or user-impacting systems.\n\n## Additional Resources\n\n- [Optim-Agent repository](https:\u002F\u002Fgithub.com\u002FOptim-Agent\u002Foptim-agent)\n- [Optim-Agent documentation](https:\u002F\u002Foptim-agent.github.io\u002Foptim-agent\u002F)\n","# Optim Agent\n\n## Overview\n\nUse this skill to optimize configurable systems against a measurable scalar objective. It helps an agent turn vague tuning requests into bounded experiments with a defined search space, budget, baseline, and evidence-backed recommendation.\n\n## When to Use This Skill\n\n- Use when tuning hyperparameters, prompts, inference settings, simulation parameters, quantitative strategies, or RL\u002Fcontrol policies.\n- Use when the objective can be measured as a scalar score, loss, accuracy, cost, latency, reward, or risk-adjusted metric.\n- Use when the user needs a small-budget optimization loop with trial history, comparisons, and stop criteria.\n\n## Do not use this skill when\n\n- The objective is purely subjective and cannot be scored consistently.\n- The user has not provided permission to run experiments or consume compute\u002FAPI budget.\n- The task is a one-shot implementation, debugging, or code review request with no configurable search space.\n\n## Instructions\n\n1. Define the optimization target in one sentence: maximize or minimize one scalar metric.\n2. List the tunable parameters, valid ranges, types, defaults, and any forbidden combinations.\n3. Establish at least one baseline before proposing agent-guided trials.\n4. Set the budget up front: number of trials, time, compute, money, or dataset subsample.\n5. Run or request trials one at a time unless the user explicitly approves parallel execution.\n6. Record every trial with parameters, metric value, notes, and failure status.\n7. Compare the best result against the baseline and a simple search strategy when possible.\n8. Stop when the budget is exhausted, the improvement plateaus, or the next trial cannot be justified from evidence.\n9. Report the recommended configuration, measured gain, tradeoffs, and any validation still needed before production use.\n\n## Examples\n\n### Example 1: Hyperparameter optimization\n\nTune learning rate, regularization, and tree depth for a credit-default model. Track validation AUC for each trial, compare against the default configuration, and recommend the best setting only if it improves the baseline under the agreed trial budget.\n\n### Example 2: Inference tuning\n\nTune retrieval depth, temperature, and reranker threshold for a RAG workflow. Optimize answer quality under a latency or cost ceiling, then report the best configuration with quality, latency, and cost tradeoffs.\n\n### Example 3: Simulation or control\n\nTune controller gains or environment parameters for a simulator. Optimize reward or error while logging failed trials separately so unstable configurations do not bias the recommendation.\n\n## Best Practices\n\n- Keep the first run small; expand only after the loop produces useful signal.\n- Prefer parameters with clear operational meaning over arbitrary knobs.\n- Treat failed trials as data and record why they failed.\n- Validate the final configuration on held-out data, a fresh seed, or a separate scenario before calling it robust.\n- Ask before running expensive, long, or externally billed experiments.\n\n## Limitations\n\n- This skill does not guarantee a global optimum.\n- Results depend on objective quality, noise, search-space design, and experiment reproducibility.\n- Use domain review before applying tuned configurations to production, financial, safety-critical, or user-impacting systems.\n\n## Additional Resources\n\n- [Optim-Agent repository](https:\u002F\u002Fgithub.com\u002FOptim-Agent\u002Foptim-agent)\n- [Optim-Agent documentation](https:\u002F\u002Foptim-agent.github.io\u002Foptim-agent\u002F)\n",{"name":5,"risk":33,"tags":48,"tools":51,"author":53,"source":32,"license":14,"category":54,"date_added":55,"description":7,"source_repo":56,"source_type":32,"license_source":57},[49,26,50,36],"optimization","experiments",[52,35,42,40],"claude","Optim-Agent","data","2026-07-15","Optim-Agent\u002Foptim-agent","https:\u002F\u002Fgithub.com\u002FOptim-Agent\u002Foptim-agent\u002Fblob\u002Fmain\u002FLICENSE","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Foptim-agent","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill optim-agent",{"tool":69,"command":70},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill optim-agent",{"tool":72,"command":73},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill optim-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Foptim-agent\u002FSKILL.md",true,[],[78,105,129,149,176,200],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":87,"publishedAt":43},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[84],{"categoryNo":85,"categoryName":86,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[88,89,90,91,92,93,80,94,95,96,97,98,32,31,99,100,101,102,103,104],"ZeRO","trust","zero trust","architecture","assessment","verification","segmentation","devops-security","access","configure","only","active","critical","scope","scripts","relevant","implementing",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":43},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[112,113,114,115,116,117,118,119,120,121,122,123,124,98,125,32,126,127,100,128],"delegate","zcode","zcode delegate","review","cli","orchestration","tasks","run","Bash","model","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":135,"publishedAt":43},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[136,137,138,33,41,40,139,39,38,140,141,142,143,32,31,144,145,146,147,148],"transcript","youtube transcript","youtube","research","text","fetch","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":166,"publishedAt":43},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[155,158,161],{"categoryNo":156,"categoryName":157,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":159,"categoryName":160,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":162,"categoryName":163,"taxonomyType":164,"taxonomyTypeDesc":165},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[136,137,138,167,33,42,41,40,39,168,169,170,171,141,172,32,31,173,174,175],"youtube transcript skills","search","api","Video","browse","api-integration","free","card","channels",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":186,"publishedAt":43},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker","Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[182,185],{"categoryNo":183,"categoryName":184,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":159,"categoryName":160,"taxonomyType":20,"taxonomyTypeDesc":21},[138,187,188,116,33,189,190,191,192,39,170,193,194,195,196,31,197,144,198,199],"youtube notetaker","notetaker","workflow","official","notes","code","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":207,"publishedAt":43},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[206],{"categoryNo":156,"categoryName":157,"taxonomyType":20,"taxonomyTypeDesc":21},[208,138,209,210,33,42,168,211,212,169,170,171,141,213,172,32,31,173,214,147],"youtube full","full","google","server","dlp","credits","automatic"]