[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skills:stats":3,"skills:sce6":8,"skills:pro6":55,"skills:creators9":100,"skills:all:stars:10824:":195},{"skillCount":4,"professionCount":5,"scenarioCount":6,"creatorCount":7},196852,11,7,1926,[9,20,27,34,41,48],{"categoryNo":10,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":13,"categoryNameEn":14,"description":15,"level":16,"skillCount":17,"parentNo":18,"parentName":18,"children":19},"01JBSEEDCAT000000000000022","SCENARIO","使用场景","智能体与自动化","Agents & Automation","Skill、MCP、智能体与工作流自动化",1,39458,null,[],{"categoryNo":21,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":22,"categoryNameEn":23,"description":24,"level":16,"skillCount":25,"parentNo":18,"parentName":18,"children":26},"01JBSEEDCAT000000000000006","软件开发","Software Development","编码、测试、部署等软件研发任务",26531,[],{"categoryNo":28,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":29,"categoryNameEn":30,"description":31,"level":16,"skillCount":32,"parentNo":18,"parentName":18,"children":33},"01JBSEEDCAT000000000000014","设计创意","Design & Creative","视觉设计、品牌与多媒体创作",13569,[],{"categoryNo":35,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":36,"categoryNameEn":37,"description":38,"level":16,"skillCount":39,"parentNo":18,"parentName":18,"children":40},"01JBSEEDCAT000000000000001","办公效率","Office Productivity","日常办公文档、表格、演示与沟通类任务",6289,[],{"categoryNo":42,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":43,"categoryNameEn":44,"description":45,"level":16,"skillCount":46,"parentNo":18,"parentName":18,"children":47},"01JBSEEDCAT000000000000017","内容创作","Content Creation","写作、文案与营销内容生产",6029,[],{"categoryNo":49,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":50,"categoryNameEn":51,"description":52,"level":16,"skillCount":53,"parentNo":18,"parentName":18,"children":54},"01JBSEEDCAT000000000000020","研究与学习","Research & Learning","资料检索、知识整理与学习辅导",5531,[],[56,65,72,79,86,93],{"categoryNo":57,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":60,"categoryNameEn":61,"description":62,"level":16,"skillCount":63,"parentNo":18,"parentName":18,"children":64},"01JBSEEDCAT000000000000030","PROFESSION","适用职业","开发工程师","Software Engineer","从事软件编码、测试与运维的工程师",13274,[],{"categoryNo":66,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":67,"categoryNameEn":68,"description":69,"level":16,"skillCount":70,"parentNo":18,"parentName":18,"children":71},"01JBSEEDCAT000000000000032","设计师","Designer","视觉、交互与品牌设计人员",7775,[],{"categoryNo":73,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":74,"categoryNameEn":75,"description":76,"level":16,"skillCount":77,"parentNo":18,"parentName":18,"children":78},"01JBSEEDCAT000000000000033","数据分析师","Data Analyst","数据分析、报表与商业智能人员",4988,[],{"categoryNo":80,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":81,"categoryNameEn":82,"description":83,"level":16,"skillCount":84,"parentNo":18,"parentName":18,"children":85},"01JBSEEDCAT000000000000036","内容创作者","Content Creator","作者、编辑与自媒体创作者",3940,[],{"categoryNo":87,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":88,"categoryNameEn":89,"description":90,"level":16,"skillCount":91,"parentNo":18,"parentName":18,"children":92},"01JBSEEDCAT000000000000035","市场营销","Marketer","市场推广、增长与品牌运营人员",3446,[],{"categoryNo":94,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":95,"categoryNameEn":96,"description":97,"level":16,"skillCount":98,"parentNo":18,"parentName":18,"children":99},"01JBSEEDCAT000000000000037","律师与法务","Legal","合同、合规与法律事务人员",3316,[],{"records":101,"total":7,"current":16,"size":194},[102,114,123,133,143,153,163,172,182],{"accountNo":103,"login":104,"displayName":105,"avatarUrl":106,"accountType":107,"accountTypeDesc":108,"profileDescription":109,"skillCount":110,"repoCount":111,"professionCount":5,"scenarioCount":6,"totalStars":112,"updatedAt":113},"01M698VYDXZ6JW5WH3CRV650R8","microsoft","Microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","ORGANIZATION","组织","Open source projects and samples from Microsoft",4160,229,828772,"2026-11-13 04:10:52",{"accountNo":115,"login":116,"displayName":116,"avatarUrl":117,"accountType":107,"accountTypeDesc":108,"profileDescription":118,"skillCount":119,"repoCount":120,"professionCount":6,"scenarioCount":6,"totalStars":121,"updatedAt":122},"01M698P3FSAZ6B4R928ZF19KPT","openclaw","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252820863?v=4","Your personal, open source AI assistant.",362,32,437711,"2026-11-13 03:02:05",{"accountNo":124,"login":125,"displayName":126,"avatarUrl":127,"accountType":107,"accountTypeDesc":108,"profileDescription":18,"skillCount":128,"repoCount":129,"professionCount":6,"scenarioCount":130,"totalStars":131,"updatedAt":132},"01M6AC29YGCR4S2NTJFV0G8B81","openai","OpenAI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F14957082?v=4",171,23,6,342695,"2026-11-13 04:03:41",{"accountNo":134,"login":135,"displayName":136,"avatarUrl":137,"accountType":107,"accountTypeDesc":108,"profileDescription":18,"skillCount":138,"repoCount":139,"professionCount":140,"scenarioCount":6,"totalStars":141,"updatedAt":142},"01M6AC83E6K4FDKK7HZ8WNMQKE","apache","The Apache Software Foundation","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F47359?v=4",420,75,8,298176,"2026-11-13 03:14:28",{"accountNo":144,"login":145,"displayName":146,"avatarUrl":147,"accountType":107,"accountTypeDesc":108,"profileDescription":148,"skillCount":149,"repoCount":150,"professionCount":5,"scenarioCount":6,"totalStars":151,"updatedAt":152},"01M698VYEFDM0VJBZDYYJ2T83S","google","Google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","Google ❤️ Open Source",535,48,242366,"2026-11-13 04:17:09",{"accountNo":154,"login":155,"displayName":156,"avatarUrl":157,"accountType":107,"accountTypeDesc":108,"profileDescription":158,"skillCount":159,"repoCount":160,"professionCount":5,"scenarioCount":6,"totalStars":161,"updatedAt":162},"01M6AC83DS133TPXFSP1DHNCC6","github","GitHub","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","How people build software.",940,28,238441,"2026-11-13 03:57:35",{"accountNo":164,"login":165,"displayName":166,"avatarUrl":167,"accountType":107,"accountTypeDesc":108,"profileDescription":18,"skillCount":168,"repoCount":169,"professionCount":5,"scenarioCount":6,"totalStars":170,"updatedAt":171},"01M697XGDPXJAVQ8391V2BCYTE","anthropics","Anthropic","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4",674,17,231826,"2026-11-13 04:18:26",{"accountNo":173,"login":174,"displayName":175,"avatarUrl":176,"accountType":107,"accountTypeDesc":108,"profileDescription":18,"skillCount":177,"repoCount":178,"professionCount":179,"scenarioCount":6,"totalStars":180,"updatedAt":181},"01M6AC83EPDGBFN19MWYRREJD0","Significant-Gravitas","AutoGPT","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130738209?v=4",86,2,10,188014,"2026-11-13 02:38:59",{"accountNo":183,"login":184,"displayName":185,"avatarUrl":186,"accountType":187,"accountTypeDesc":188,"profileDescription":189,"skillCount":190,"repoCount":191,"professionCount":130,"scenarioCount":6,"totalStars":192,"updatedAt":193},"01M6DJCCDDG53MTYYRTXAXFG17","garrytan","Garry Tan","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F19957?v=4","USER","个人作者","Writes software, dreams. ",324,3,174614,"2026-11-13 04:05:07",9,{"records":196,"total":4,"current":591,"size":592},[197,235,264,292,319,343,366,386,409,428,446,467,492,506,522,541,561,574],{"skillNo":198,"name":199,"nameZh":18,"description":200,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":209,"categories":210,"keywords":214,"publishedAt":234},"01M6XFQRBQF48NQV23ZJHVYNK5","shap","Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.","fadrienne\u002FMyGitHub","fadrienne","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F197874571?v=4","01M6X64V8VWCRSMFZ4EPS2BWXG","Francesca Adrienne","01M6X64VD5MW4F9PHDWQKS7ZAF",0,"MIT","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcoding\u002Fshap\u002FSKILL.md",[211],{"categoryNo":212,"categoryName":213,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000023","Skill与智能体开发",[199,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233],"deep learning","pytorch","debugging","analyzing","learning","model","coding","use","models","deep","bias","black","synthetic","random forest","predictions","Interpretability","random","implementing","when","2026-11-10 10:12:30",{"skillNo":236,"name":237,"nameZh":18,"description":238,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":239,"categories":240,"keywords":245,"publishedAt":234},"01M6XFPSG0T0JZRHFZFMFW5271","multi-objective-optimization","Pareto-aware molecular design balancing multiple ADMET properties simultaneously. Based on MultiMol (Yu 2025) and MOLLM (Ran 2025).","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcoding\u002Fmulti-objective-optimization\u002FSKILL.md",[241,244],{"categoryNo":242,"categoryName":243,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":66,"categoryName":67,"taxonomyType":58,"taxonomyTypeDesc":59},[246,247,248,249,250,251,252,253,254,221,255,256,257,227,258,259,260,261,262,263],"Optimization","multi","objective","multi objective optimization","design","pandas","pypi","rdkit","discovery","properties","numpy","molecular","drug-discovery","2025","pareto","ADMET","molecular-design","multi-objective",{"skillNo":265,"name":266,"nameZh":18,"description":267,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":268,"categories":269,"keywords":275,"publishedAt":234},"01M6XFPAH16H1JPF9ST6CZY1H5","exploratory-data-analysis","Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates detailed markdown reports with format-specific analysis, quality metrics, and downstream analysis recommendations. Covers chemistry, bioinformatics, microscopy, spectroscopy, proteomics, metabolomics, and general scientific data formats.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcoding\u002Fexploratory-data-analysis\u002FSKILL.md",[270,273,274],{"categoryNo":271,"categoryName":272,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":212,"categoryName":213,"taxonomyType":11,"taxonomyTypeDesc":12},{"categoryNo":73,"categoryName":74,"taxonomyType":58,"taxonomyTypeDesc":59},[276,277,278,279,280,281,218,282,221,283,284,285,286,287,288,227,289,290,291,233],"data analysis","data","exploratory data analysis","analysis","metrics","file","markdown","reports","files","general","structure","across","recommendations","metabolomics","scientific","formats",{"skillNo":293,"name":294,"nameZh":18,"description":295,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":296,"categories":297,"keywords":301,"publishedAt":234},"01M6XFNZ8VKGFW971ZAY7MKW25","audiocraft-audio-generation","PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcoding\u002Faudiocraft\u002FSKILL.md",[298],{"categoryNo":299,"categoryName":300,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000016","图像与多媒体",[302,303,304,305,306,216,307,308,309,310,311,312,313,227,314,315,316,317,318,233],"Audio","audiocraft audio generation","generation","Audio Generation","audiocraft","create","generate","multimodal","library","Transformers","music","text","Text-to-Music","music generation","you","audiogen","effects",{"skillNo":320,"name":321,"nameZh":18,"description":322,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":323,"categories":324,"keywords":327,"publishedAt":234},"01M6XFNNM446TQ1M6PVW5WCJQ0","together-ai-inference","Serverless inference, fine-tuning, embeddings, image generation, and batch processing on 200+ open-source models via an OpenAI-compatible API. Use when you need fast, cost-effective access to open-source LLMs without managing infrastructure.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Ftogether-ai\u002FSKILL.md",[325,326],{"categoryNo":299,"categoryName":300,"taxonomyType":11,"taxonomyTypeDesc":12},{"categoryNo":57,"categoryName":60,"taxonomyType":58,"taxonomyTypeDesc":59},[328,329,330,331,332,333,125,334,335,336,337,338,339,222,227,340,316,341,342,233],"inference","together ai","together ai inference","image","llms","infrastructure","batch","embeddings","tuning","api","open","access","processing","openai-compatible","source",{"skillNo":344,"name":345,"nameZh":18,"description":346,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":347,"categories":348,"keywords":352,"publishedAt":234},"01M6XFNFN2546XP43M65QD1M5F","tinker-fine-tuning","Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. Use when running supervised fine-tuning, reinforcement learning (GRPO\u002FPPO), or LoRA training on cloud GPUs via Tinker's managed infrastructure instead of local compute.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Ftinker\u002FSKILL.md",[349],{"categoryNo":350,"categoryName":351,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000010","后端与接口",[336,353,354,332,333,355,311,337,356,357,358,227,359,360,361,233,362,363,364,365],"fine tuning","tinker fine tuning","training","vision","thinking","local","cookbook","managed","supervised","running","Tinker","Supervised Learning","Cloud Training",{"skillNo":367,"name":368,"nameZh":18,"description":369,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":370,"categories":371,"keywords":372,"publishedAt":234},"01M6XFN96T11K8SM8495R7X84A","tinker-training-cost","Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Ftinker-training-cost\u002FSKILL.md",[],[355,373,363,374,375,376,311,336,377,220,222,378,379,380,227,381,382,383,233,384,385],"cost","tinker training cost","pricing","Fine-Tuning","correct","datasets","compute","tokens","counting","prices","for","Training Cost","Token Counting",{"skillNo":387,"name":388,"nameZh":18,"description":389,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":390,"categories":391,"keywords":392,"publishedAt":234},"01M6XFN4SHSBBRBWX1V1KGNRMQ","tensorpool-gpu-cloud","On-demand GPU clusters and training jobs with git-style interface. Use when you need multi-node GPU clusters (B200, H200, H100), persistent NFS storage, or batch training jobs with the TensorPool CLI.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Ftensorpool\u002FSKILL.md",[],[393,394,395,396,397,398,355,399,334,400,227,401,402,316,403,404,233,405,406,407,408],"gpu","cloud","GPU Cloud","tensorpool gpu cloud","cli","storage","git","node","H100","interface","nfs storage","nfs","On-Demand GPU","Clusters","TensorPool","Training Jobs",{"skillNo":410,"name":411,"nameZh":18,"description":412,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":413,"categories":414,"keywords":415,"publishedAt":234},"01M6XFMZGKCAXA6QCGWB3F3KGY","skypilot-multi-cloud-orchestration","Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Fskypilot\u002FSKILL.md",[],[416,394,417,418,419,247,355,420,334,421,422,423,424,287,425,227,316,426,233,427],"orchestration","SkyPilot","skypilot multi cloud orchestration","multi cloud","run","Providers","auto","instances","optimize","leverage","automatic","Synthetic Sciencestion",{"skillNo":429,"name":430,"nameZh":18,"description":431,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":432,"categories":433,"keywords":435,"publishedAt":234},"01M6XFMR277RA0ZPHM4GAE920Z","modal-serverless-gpu","Serverless GPU cloud platform for ML workloads — inference serving, batch processing, training, web endpoints, sandboxes, and scheduled jobs. Use when you need on-demand GPUs without infrastructure management, deploying models as auto-scaling APIs, running batch jobs, or executing untrusted code in sandboxes.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Fmodal\u002FSKILL.md",[434],{"categoryNo":57,"categoryName":60,"taxonomyType":58,"taxonomyTypeDesc":59},[393,436,437,438,333,355,439,334,440,422,441,227,340,442,443,316,444,233,362,445],"modal","serverless","modal serverless gpu","code","Inference Serving","scaling","Auto-Scaling","infrastructure management","scheduled","Web Endpoints",{"skillNo":447,"name":448,"nameZh":18,"description":449,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":450,"categories":451,"keywords":455,"publishedAt":234},"01M6XFMK2K7MPJT9KQFHRXPQ80","modal-research-gpu","GPU-accelerated scientific research on Modal — simulations, numerical methods, Monte Carlo, molecular dynamics, large-scale data processing. NOT for ML training or inference (use gpu-training or modal skills instead).","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Fmodal-research-gpu\u002FSKILL.md",[452],{"categoryNo":453,"categoryName":454,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000021","资料检索与研究",[456,393,436,457,458,355,277,222,459,460,257,227,461,290,340,383,462,463,464,465,466],"research","modal research gpu","ml","methods","molecular dynamics","dynamics","numerical","hpc","Simulations","Numerical Methods","Monte Carlo",{"skillNo":468,"name":469,"nameZh":18,"description":470,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":471,"categories":472,"keywords":479,"publishedAt":234},"01M6XFMDXWSA7G43Y7QVQSXPG5","modal-ml-training","Disconnect-safe patterns for long-running ML training on Modal serverless GPU. Covers the deploy+spawn pattern (survives laptop shutdown\u002FSSH disconnect), checkpoint-resume for preemption recovery, PyTorch\u002FCUDA version pinning, volume reload\u002Fcommit discipline, and batch parameter sweeps. Use for any training job >30 min where losing progress is expensive. Complements the broader `modal-serverless-gpu` skill.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Fmodal-ml-training\u002FSKILL.md",[473,476],{"categoryNo":474,"categoryName":475,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":477,"categoryName":478,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000038","人力资源",[458,355,436,480,481,482,216,334,483,484,485,486,487,488,489,227,490,383,362,491],"modal ml training","safe","commit","checkpoint","spawn","discipline","shutdown","patterns","pattern","volume","progress","Preemption",{"skillNo":493,"name":494,"nameZh":18,"description":495,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":496,"categories":497,"keywords":498,"publishedAt":234},"01M6XFM7PEC3JB7WKFVGTV8DH0","lambda-labs-gpu-cloud","Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Flambda-labs\u002FSKILL.md",[],[393,394,395,499,500,501,502,333,355,503,339,400,423,227,504,505,316,383,233,405,406],"Lambda Labs","lambda","lambda labs gpu cloud","performance","Large-Scale Training","high-performance","Multi-Node",{"skillNo":507,"name":508,"nameZh":18,"description":509,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":510,"categories":511,"keywords":512,"publishedAt":234},"01M6XFM16RV432VJS9A9D08V29","fireworks-ai-inference","Fast inference and fine-tuning platform with serverless and on-demand GPU deployments. OpenAI-compatible API for chat completions, embeddings, function calling, vision, and structured output. Supports SFT, DPO, and RL fine-tuning. SOC2 + HIPAA compliant.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fcloud-compute\u002Ffireworks-ai\u002FSKILL.md",[],[328,513,514,125,335,376,515,336,516,337,517,356,518,519,520,521,227,341,383,405],"fireworks ai","fireworks ai inference","Fast Inference","soc2","function calling","deployments","calling","platform","structured output",{"skillNo":523,"name":524,"nameZh":18,"description":525,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":526,"categories":527,"keywords":528,"publishedAt":234},"01M6XFKK172Y3JMKDJA75Y6000","structure-prediction","Protein structure prediction from sequence. ESMFold-based, single GPU, no MSA needed. Predicts 3D structures with pLDDT confidence scores for drug discovery targets.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fstructure-prediction\u002FSKILL.md",[],[286,529,530,215,393,531,532,254,219,533,224,227,534,535,536,537,383,538,539,540],"prediction","Structure Prediction","biopython","3D","msa","protein structure prediction","protein structure","targets","with","single","Protein","ESMFold",{"skillNo":542,"name":543,"nameZh":18,"description":544,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":545,"categories":546,"keywords":547,"publishedAt":234},"01M6XFKFD0WD67PCQB4XGX2SK9","smiles-validation","Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fsmiles-validation\u002FSKILL.md",[],[548,549,550,551,252,253,552,553,554,555,556,557,227,558,559,560],"validation","SMILES","smiles validation","verification","quality","generated","cheminformatics","structural","control","invalid","comparison","quality-control","Molecules",{"skillNo":562,"name":563,"nameZh":18,"description":564,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":565,"categories":566,"keywords":567,"publishedAt":234},"01M6XFK3R4B33Q61HXRJ0J6EVG","pytdc","Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fpytdc\u002FSKILL.md",[],[563,568,458,277,254,569,378,570,257,227,571,383,572,529,573],"scaffold","ready","benchmarks","drug discovery","splits","toxicity",{"skillNo":575,"name":576,"nameZh":18,"description":577,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":578,"categories":579,"keywords":580,"publishedAt":234},"01M6XFJR9KC0YYSYMQW0WHDDS4","pocket-detection","Multi-method binding pocket detection and druggability assessment. Grid-based, fpocket, and P2Rank detection with druggability scoring, visualization, and cross-structure comparison.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fchemistry\u002Fpocket-detection\u002FSKILL.md",[],[581,582,250,583,584,531,254,256,585,586,286,227,571,587,247,558,537,588,589,590],"detection","Pocket Detection","assessment","visualization","scipy","scoring","binding","grid","Druggability","Structure-Based Design",10824,18]