[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KFZH5PFF5F3JXMJZ2QQJPM":3,"skill-same:01M6KFZH5PFF5F3JXMJZ2QQJPM":52},{"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":17,"publishedAt":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":35,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M6KFZH5PFF5F3JXMJZ2QQJPM","run2_advanced-pareto",null,"Efficient and robust Pareto frontier calculation for multi-objective optimization.","cxcscmu\u002FSkillLearnBench","cxcscmu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F142838272?v=4","01M6KCQDFQWPDSN0MKZY96MSQP","01M6KCQDM7G70TKJ28NTSQC0RZ",92,"MIT","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fb2-self-feedback-gemini-3-flash-preview\u002Fdbscan-parameter-tuning\u002Frun2_advanced-pareto\u002FSKILL.md",[],[18,19,20,21,22,23,24],"advanced","run2 advanced pareto","Optimization","multi","calculation","for","pareto frontier","2026-11-10 10:12:30",false,"---\nname: run2_advanced-pareto\ndescription: Efficient and robust Pareto frontier calculation for multi-objective optimization.\n---\n\n# Advanced Pareto Frontier\n\nA robust implementation to find Pareto-optimal points where some objectives are maximized and others minimized.\n\n## Implementation\n\n```python\nimport numpy as np\n\ndef find_pareto_frontier(data, maximize=None, minimize=None):\n    \"\"\"\n    data: np.ndarray of shape (n_samples, n_objectives)\n    maximize: list of indices to maximize\n    minimize: list of indices to minimize\n    \"\"\"\n    costs = data.copy()\n    if maximize:\n        costs[:, maximize] = -costs[:, maximize]\n    \n    n_samples = costs.shape[0]\n    is_efficient = np.ones(n_samples, dtype=bool)\n    for i, c in enumerate(costs):\n        if is_efficient[i]:\n            # Keep only points that are not dominated by c\n            # A point p is dominated by c if p >= c in all and p > c in at least one\n            # So we keep p if p \u003C c in at least one or p == c in all\n            is_efficient[is_efficient] = np.any(costs[is_efficient] \u003C c, axis=1) | np.all(costs[is_efficient] == c, axis=1)\n    return is_efficient\n```\n","# Advanced Pareto Frontier\n\nA robust implementation to find Pareto-optimal points where some objectives are maximized and others minimized.\n\n## Implementation\n\n```python\nimport numpy as np\n\ndef find_pareto_frontier(data, maximize=None, minimize=None):\n    \"\"\"\n    data: np.ndarray of shape (n_samples, n_objectives)\n    maximize: list of indices to maximize\n    minimize: list of indices to minimize\n    \"\"\"\n    costs = data.copy()\n    if maximize:\n        costs[:, maximize] = -costs[:, maximize]\n    \n    n_samples = costs.shape[0]\n    is_efficient = np.ones(n_samples, dtype=bool)\n    for i, c in enumerate(costs):\n        if is_efficient[i]:\n            # Keep only points that are not dominated by c\n            # A point p is dominated by c if p >= c in all and p > c in at least one\n            # So we keep p if p \u003C c in at least one or p == c in all\n            is_efficient[is_efficient] = np.any(costs[is_efficient] \u003C c, axis=1) | np.all(costs[is_efficient] == c, axis=1)\n    return is_efficient\n```\n",{"name":5,"description":7},"main","726e1f79b96b0cb3d729d0e55a1c847e0b5353ae","skills\u002Fb2-self-feedback-gemini-3-flash-preview\u002Fdbscan-parameter-tuning\u002Frun2_advanced-pareto",7,"https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench","https:\u002F\u002Fcxcscmu.github.io\u002FSkillLearnBench","https:\u002F\u002Fgithub.com\u002Fcxcscmu","2026-10-02 22:55:36",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add cxcscmu\u002FSkillLearnBench --skill run2_advanced-pareto",{"tool":44,"command":45},"bunx","bunx skills add cxcscmu\u002FSkillLearnBench --skill run2_advanced-pareto",{"tool":47,"command":48},"pnpm","pnpm dlx skills add cxcscmu\u002FSkillLearnBench --skill run2_advanced-pareto","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fb2-self-feedback-gemini-3-flash-preview\u002Fdbscan-parameter-tuning\u002Frun2_advanced-pareto\u002FSKILL.md",true,[],[53,71,95,113,133,145],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":64,"publishedAt":25},"01M6KM5KH175P5ABP5JMX2SBDQ","object_counter","Count occurrences of an object in the image using computer vision algorithm.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Fvideo-object-counting\u002Fobject_counter\u002FSKILL.md",[59],{"categoryNo":60,"categoryName":61,"taxonomyType":62,"taxonomyTypeDesc":63},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[65,66,67,68,69,70],"object counter","object","vision","computer","Computer Vision","image",{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":80,"publishedAt":25},"01M6KM51TMVXG79MMPCS6Y8G86","travel-planning-workflow","Invoke this skill when performing travel planning. It defines a structured workflow for generating itineraries. Following this workflow is essential to ensure the final plan satisfies user requirements.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftravel-planning\u002Ftravel-planning-workflow\u002FSKILL.md",[77],{"categoryNo":78,"categoryName":79,"taxonomyType":62,"taxonomyTypeDesc":63},"01JBSEEDCAT000000000000023","Skill与智能体开发",[81,82,83,84,85,86,87,88,89,23,90,91,92,93,94],"workflow","planning","planning workflow","travel","travel planning","travel planning workflow","structured","performing","plan","user","it","requirements","essential","itineraries",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":25},"01M6KM4DY820XHS9YTSK5QP5HD","bundled-dataset-search-tool","invoke this skill when you need to perform database search for travel planning. This skill provides some useful pre-packaged tools to look up accommodations, attractions, cities, driving distance, flights, and restaurants from the bundled dataset.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftravel-planning\u002Fbundled-dataset-search-tool\u002FSKILL.md",[],[102,103,104,105,106,107,108,84,109,110,85,111,23,112,82],"search","tool","dataset","bundled dataset search tool","restaurants","Tools","up","look","flights","you","database",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":25},"01M6KM465BB9PQ0B548HQSVAWZ","glm-output","Output-processing guidance for GLM tasks. Especially useful after glm-basics and glm-calibration when you need verifier-matching metrics from output.nc and a final \u002Froot\u002Fmetrics.json.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-output\u002FSKILL.md",[],[120,121,122,23,123,124,125,126,127,128,129,130,111,131,132],"glm output","output","glm","tasks","metrics","json","basics","guidance","matching","verifier","processing","root","calibration",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":140,"publishedAt":25},"01M6KM40KY3QWDW5W97S39R2BC","glm-calibration","Calibration guidance for GLM tasks. Often most effective after glm-basics has clarified the setup; glm-output is the companion skill for exact final metric computation.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-calibration\u002FSKILL.md",[139],{"categoryNo":78,"categoryName":79,"taxonomyType":62,"taxonomyTypeDesc":63},[141,132,122,121,127,126,123,142,143,23,144],"glm calibration","setup","companion","metric",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":25},"01M6KM3VHHVSGMGHJQB3PPT6YG","glm-basics","A good starting point for GLM calibration tasks. Use to inspect glm3.nml, confirm how GLM runs, and identify the relevant files before moving on to calibration and output evaluation.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-basics\u002FSKILL.md",[],[152,122,126,153,141,132,23,121,154,155,156,157,158,159,123],"glm basics","inspect","relevant","files","good","use","how","Evaluation"]