[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KEMVY6EFC4HTX0XTP2V9YB":3,"skill-same:01M6KEMVY6EFC4HTX0XTP2V9YB":56},{"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":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":41,"install":42,"resources":55},"01M6KEMVY6EFC4HTX0XTP2V9YB","model-verification-unit-tests",null,"Verifies model components like loss functions using unit tests and saves the results as NumPy archives.","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\u002Fb1-one-shot-gemini-3-flash-preview\u002Fnlp-paper-reproduction\u002Fmodel-verification-unit-tests\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28],"unit tests","verification","model","tests","unit","model verification unit tests","components","results","functions","numpy","as","2026-11-10 10:12:30",false,"---\nname: model-verification-unit-tests\ndescription: Verifies model components like loss functions using unit tests and saves the results as NumPy archives.\n---\n\n# Model Verification with Unit Tests\n\nVerifying individual components of a training pipeline, such as a loss function, ensures mathematical correctness before full-scale training.\n\n## Running Tests\n\nUse the `unittest` framework or `pytest`. For a script like `unit_test_1.py`:\n\n```bash\npython unit_test\u002Funit_test_1.py\n```\n\n## Data Persistence\n\nTo allow external verification of results, save computed tensors to a `.npz` file:\n\n```python\nimport numpy as np\n\n# In the test code:\nnp.savez(\n    \"\u002Fpath\u002Fto\u002Floss.npz\",\n    losses=losses.detach().cpu().numpy(),\n)\n```\n\n## Fixed Tensor Inputs\n\nWhen verifying a loss function, use fixed tensors to ensure deterministic output:\n\n```python\n# Loading pre-computed tensors\npolicy_chosen_logps = torch.load(\"path\u002Fto\u002Ftensor.pt\")\n```\n","# Model Verification with Unit Tests\n\nVerifying individual components of a training pipeline, such as a loss function, ensures mathematical correctness before full-scale training.\n\n## Running Tests\n\nUse the `unittest` framework or `pytest`. For a script like `unit_test_1.py`:\n\n```bash\npython unit_test\u002Funit_test_1.py\n```\n\n## Data Persistence\n\nTo allow external verification of results, save computed tensors to a `.npz` file:\n\n```python\nimport numpy as np\n\n# In the test code:\nnp.savez(\n    \"\u002Fpath\u002Fto\u002Floss.npz\",\n    losses=losses.detach().cpu().numpy(),\n)\n```\n\n## Fixed Tensor Inputs\n\nWhen verifying a loss function, use fixed tensors to ensure deterministic output:\n\n```python\n# Loading pre-computed tensors\npolicy_chosen_logps = torch.load(\"path\u002Fto\u002Ftensor.pt\")\n```\n",{"name":5,"description":7},"main","726e1f79b96b0cb3d729d0e55a1c847e0b5353ae","skills\u002Fb1-one-shot-gemini-3-flash-preview\u002Fnlp-paper-reproduction\u002Fmodel-verification-unit-tests",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":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add cxcscmu\u002FSkillLearnBench --skill model-verification-unit-tests",{"tool":48,"command":49},"bunx","bunx skills add cxcscmu\u002FSkillLearnBench --skill model-verification-unit-tests",{"tool":51,"command":52},"pnpm","pnpm dlx skills add cxcscmu\u002FSkillLearnBench --skill model-verification-unit-tests","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fb1-one-shot-gemini-3-flash-preview\u002Fnlp-paper-reproduction\u002Fmodel-verification-unit-tests\u002FSKILL.md",true,[],[57,75,100,118,138,150],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":68,"publishedAt":29},"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",[63],{"categoryNo":64,"categoryName":65,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[69,70,71,72,73,74],"object counter","object","vision","computer","Computer Vision","image",{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":84,"publishedAt":29},"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",[81],{"categoryNo":82,"categoryName":83,"taxonomyType":66,"taxonomyTypeDesc":67},"01JBSEEDCAT000000000000023","Skill与智能体开发",[85,86,87,88,89,90,91,92,93,94,95,96,97,98,99],"workflow","planning","planning workflow","travel","travel planning","travel planning workflow","structured","performing","plan","for","user","it","requirements","essential","itineraries",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":29},"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",[],[107,108,109,110,111,112,113,88,114,115,89,116,94,117,86],"search","tool","dataset","bundled dataset search tool","restaurants","Tools","up","look","flights","you","database",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":29},"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",[],[125,126,127,94,128,129,130,131,132,133,134,135,116,136,137],"glm output","output","glm","tasks","metrics","json","basics","guidance","matching","verifier","processing","root","calibration",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":145,"publishedAt":29},"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",[144],{"categoryNo":82,"categoryName":83,"taxonomyType":66,"taxonomyTypeDesc":67},[146,137,127,126,132,131,128,147,148,94,149],"glm calibration","setup","companion","metric",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":29},"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",[],[157,127,131,158,146,137,94,126,159,160,161,162,163,164,128],"glm basics","inspect","relevant","files","good","use","how","Evaluation"]