[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KJWXM81VPXG53YSSPZCEB8":3,"skill-same:01M6KJWXM81VPXG53YSSPZCEB8":51},{"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":24,"linkOnly":25,"markdownContent":26,"markdownBody":27,"frontMatter":28,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M6KJWXM81VPXG53YSSPZCEB8","pareto-optimization",null,"Multi-objective optimization with Pareto frontiers. Use when optimizing multiple conflicting objectives simultaneously, finding trade-off solutions, or computing Pareto-optimal points.","cxcscmu\u002FSkillLearnBench","cxcscmu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F142838272?v=4","01M6KCQDFQWPDSN0MKZY96MSQP","01M6KCQDM7G70TKJ28NTSQC0RZ",93,"MIT","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fb4-skill-creator-claude-opus-4-6\u002Fdbscan-parameter-tuning\u002Fpareto-optimization\u002FSKILL.md",[],[18,19,20,21,22,23],"Optimization","pareto optimization","use","trade","multi","with","2026-11-10 10:12:30",false,"---\nname: pareto-optimization\ndescription: Multi-objective optimization with Pareto frontiers. Use when optimizing multiple conflicting objectives simultaneously, finding trade-off solutions, or computing Pareto-optimal points.\n---\n\n# Pareto Frontier Computation\n\n## When to Use\n\nUse this skill whenever you need to find the set of non-dominated solutions from multi-objective optimization results — e.g., balancing accuracy vs. cost, F1 vs. distance, precision vs. recall.\n\n## Core Algorithm\n\nA solution is Pareto-optimal if no other solution is better on all objectives simultaneously.\n\n```python\nimport numpy as np\n\ndef pareto_frontier(objectives, maximize=None):\n    \"\"\"\n    Find Pareto-optimal points.\n\n    Args:\n        objectives: array of shape (n, k) where k is the number of objectives\n        maximize: list of bools, True = maximize that objective, False = minimize\n                  Default: all maximize\n\n    Returns:\n        Boolean mask of Pareto-optimal points\n    \"\"\"\n    n = len(objectives)\n    if maximize is None:\n        maximize = [True] * objectives.shape[1]\n\n    # Flip sign for objectives to maximize (so we can treat all as minimize)\n    obj = objectives.copy().astype(float)\n    for i, m in enumerate(maximize):\n        if m:\n            obj[:, i] = -obj[:, i]\n\n    is_pareto = np.ones(n, dtype=bool)\n    for i in range(n):\n        if not is_pareto[i]:\n            continue\n        # A point dominates i if it's \u003C= on all objectives and \u003C on at least one\n        for j in range(n):\n            if i == j or not is_pareto[j]:\n                continue\n            if np.all(obj[j] \u003C= obj[i]) and np.any(obj[j] \u003C obj[i]):\n                is_pareto[i] = False\n                break\n    return is_pareto\n```\n\n## Usage Pattern for Grid Search Results\n\n```python\nimport pandas as pd\n\n# results_df has columns: F1, delta, param1, param2, ...\n# Maximize F1, minimize delta\nobjectives = results_df[['F1', 'delta']].values\nmask = pareto_frontier(objectives, maximize=[True, False])\npareto_df = results_df[mask]\n```\n\n## Notes\n\n- Filter out invalid\u002Funwanted results before computing the frontier\n- The frontier is sensitive to objective scales — normalization isn't needed for finding Pareto points but matters for visualization\n- For two objectives, sorting by one and scanning for improvements in the other gives O(n log n) performance\n","# Pareto Frontier Computation\n\n## When to Use\n\nUse this skill whenever you need to find the set of non-dominated solutions from multi-objective optimization results — e.g., balancing accuracy vs. cost, F1 vs. distance, precision vs. recall.\n\n## Core Algorithm\n\nA solution is Pareto-optimal if no other solution is better on all objectives simultaneously.\n\n```python\nimport numpy as np\n\ndef pareto_frontier(objectives, maximize=None):\n    \"\"\"\n    Find Pareto-optimal points.\n\n    Args:\n        objectives: array of shape (n, k) where k is the number of objectives\n        maximize: list of bools, True = maximize that objective, False = minimize\n                  Default: all maximize\n\n    Returns:\n        Boolean mask of Pareto-optimal points\n    \"\"\"\n    n = len(objectives)\n    if maximize is None:\n        maximize = [True] * objectives.shape[1]\n\n    # Flip sign for objectives to maximize (so we can treat all as minimize)\n    obj = objectives.copy().astype(float)\n    for i, m in enumerate(maximize):\n        if m:\n            obj[:, i] = -obj[:, i]\n\n    is_pareto = np.ones(n, dtype=bool)\n    for i in range(n):\n        if not is_pareto[i]:\n            continue\n        # A point dominates i if it's \u003C= on all objectives and \u003C on at least one\n        for j in range(n):\n            if i == j or not is_pareto[j]:\n                continue\n            if np.all(obj[j] \u003C= obj[i]) and np.any(obj[j] \u003C obj[i]):\n                is_pareto[i] = False\n                break\n    return is_pareto\n```\n\n## Usage Pattern for Grid Search Results\n\n```python\nimport pandas as pd\n\n# results_df has columns: F1, delta, param1, param2, ...\n# Maximize F1, minimize delta\nobjectives = results_df[['F1', 'delta']].values\nmask = pareto_frontier(objectives, maximize=[True, False])\npareto_df = results_df[mask]\n```\n\n## Notes\n\n- Filter out invalid\u002Funwanted results before computing the frontier\n- The frontier is sensitive to objective scales — normalization isn't needed for finding Pareto points but matters for visualization\n- For two objectives, sorting by one and scanning for improvements in the other gives O(n log n) performance\n",{"name":5,"description":7},"main","726e1f79b96b0cb3d729d0e55a1c847e0b5353ae","skills\u002Fb4-skill-creator-claude-opus-4-6\u002Fdbscan-parameter-tuning\u002Fpareto-optimization",8,"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":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add cxcscmu\u002FSkillLearnBench --skill pareto-optimization",{"tool":43,"command":44},"bunx","bunx skills add cxcscmu\u002FSkillLearnBench --skill pareto-optimization",{"tool":46,"command":47},"pnpm","pnpm dlx skills add cxcscmu\u002FSkillLearnBench --skill pareto-optimization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fb4-skill-creator-claude-opus-4-6\u002Fdbscan-parameter-tuning\u002Fpareto-optimization\u002FSKILL.md",true,[],[52,70,95,113,133,145],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":63,"publishedAt":24},"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",[58],{"categoryNo":59,"categoryName":60,"taxonomyType":61,"taxonomyTypeDesc":62},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[64,65,66,67,68,69],"object counter","object","vision","computer","Computer Vision","image",{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":79,"publishedAt":24},"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",[76],{"categoryNo":77,"categoryName":78,"taxonomyType":61,"taxonomyTypeDesc":62},"01JBSEEDCAT000000000000023","Skill与智能体开发",[80,81,82,83,84,85,86,87,88,89,90,91,92,93,94],"workflow","planning","planning workflow","travel","travel planning","travel planning workflow","structured","performing","plan","for","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":24},"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",[],[102,103,104,105,106,107,108,83,109,110,84,111,89,112,81],"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":24},"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",[],[120,121,122,89,123,124,125,126,127,128,129,130,111,131,132],"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":24},"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":77,"categoryName":78,"taxonomyType":61,"taxonomyTypeDesc":62},[141,132,122,121,127,126,123,142,143,89,144],"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":24},"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",[],[152,122,126,153,141,132,89,121,154,155,156,20,157,158,123],"glm basics","inspect","relevant","files","good","how","Evaluation"]