[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skills:stats":3,"skills:pro6":8,"skills:sce6":55,"skills:creators9":100,"skills:all:stars:25441:":195},{"skillCount":4,"professionCount":5,"scenarioCount":6,"creatorCount":7},482556,11,7,5953,[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},"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",1,13341,null,[],{"categoryNo":21,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":22,"categoryNameEn":23,"description":24,"level":16,"skillCount":25,"parentNo":18,"parentName":18,"children":26},"01JBSEEDCAT000000000000032","设计师","Designer","视觉、交互与品牌设计人员",7902,[],{"categoryNo":28,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":29,"categoryNameEn":30,"description":31,"level":16,"skillCount":32,"parentNo":18,"parentName":18,"children":33},"01JBSEEDCAT000000000000033","数据分析师","Data Analyst","数据分析、报表与商业智能人员",5005,[],{"categoryNo":35,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":36,"categoryNameEn":37,"description":38,"level":16,"skillCount":39,"parentNo":18,"parentName":18,"children":40},"01JBSEEDCAT000000000000036","内容创作者","Content Creator","作者、编辑与自媒体创作者",3978,[],{"categoryNo":42,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":43,"categoryNameEn":44,"description":45,"level":16,"skillCount":46,"parentNo":18,"parentName":18,"children":47},"01JBSEEDCAT000000000000035","市场营销","Marketer","市场推广、增长与品牌运营人员",3454,[],{"categoryNo":49,"taxonomyType":11,"taxonomyTypeDesc":12,"categoryName":50,"categoryNameEn":51,"description":52,"level":16,"skillCount":53,"parentNo":18,"parentName":18,"children":54},"01JBSEEDCAT000000000000037","律师与法务","Legal","合同、合规与法律事务人员",3337,[],[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},"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",39675,[],{"categoryNo":66,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":67,"categoryNameEn":68,"description":69,"level":16,"skillCount":70,"parentNo":18,"parentName":18,"children":71},"01JBSEEDCAT000000000000006","软件开发","Software Development","编码、测试、部署等软件研发任务",26798,[],{"categoryNo":73,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":74,"categoryNameEn":75,"description":76,"level":16,"skillCount":77,"parentNo":18,"parentName":18,"children":78},"01JBSEEDCAT000000000000014","设计创意","Design & Creative","视觉设计、品牌与多媒体创作",13847,[],{"categoryNo":80,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":81,"categoryNameEn":82,"description":83,"level":16,"skillCount":84,"parentNo":18,"parentName":18,"children":85},"01JBSEEDCAT000000000000001","办公效率","Office Productivity","日常办公文档、表格、演示与沟通类任务",6403,[],{"categoryNo":87,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":88,"categoryNameEn":89,"description":90,"level":16,"skillCount":91,"parentNo":18,"parentName":18,"children":92},"01JBSEEDCAT000000000000017","内容创作","Content Creation","写作、文案与营销内容生产",6063,[],{"categoryNo":94,"taxonomyType":58,"taxonomyTypeDesc":59,"categoryName":95,"categoryNameEn":96,"description":97,"level":16,"skillCount":98,"parentNo":18,"parentName":18,"children":99},"01JBSEEDCAT000000000000020","研究与学习","Research & Learning","资料检索、知识整理与学习辅导",5574,[],{"records":101,"total":7,"current":16,"size":194},[102,114,123,132,142,152,162,172,182],{"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",4300,236,832929,"2026-11-15 04:18:35",{"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.",369,32,437811,"2026-11-15 03:04:02",{"accountNo":124,"login":125,"displayName":126,"avatarUrl":127,"accountType":107,"accountTypeDesc":108,"profileDescription":18,"skillCount":128,"repoCount":129,"professionCount":5,"scenarioCount":6,"totalStars":130,"updatedAt":131},"01M697XGDPXJAVQ8391V2BCYTE","anthropics","Anthropic","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F76263028?v=4",716,18,427323,"2026-11-15 05:52:49",{"accountNo":133,"login":134,"displayName":135,"avatarUrl":136,"accountType":107,"accountTypeDesc":108,"profileDescription":18,"skillCount":137,"repoCount":138,"professionCount":6,"scenarioCount":139,"totalStars":140,"updatedAt":141},"01M6AC29YGCR4S2NTJFV0G8B81","openai","OpenAI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F14957082?v=4",177,23,6,344400,"2026-11-15 03:07:28",{"accountNo":143,"login":144,"displayName":145,"avatarUrl":146,"accountType":107,"accountTypeDesc":108,"profileDescription":18,"skillCount":147,"repoCount":148,"professionCount":149,"scenarioCount":6,"totalStars":150,"updatedAt":151},"01M6AC83E6K4FDKK7HZ8WNMQKE","apache","The Apache Software Foundation","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F47359?v=4",440,76,8,298252,"2026-11-15 04:11:16",{"accountNo":153,"login":154,"displayName":155,"avatarUrl":156,"accountType":107,"accountTypeDesc":108,"profileDescription":157,"skillCount":158,"repoCount":159,"professionCount":5,"scenarioCount":6,"totalStars":160,"updatedAt":161},"01M6AC83DS133TPXFSP1DHNCC6","github","GitHub","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","How people build software.",1022,30,278314,"2026-11-15 06:45:15",{"accountNo":163,"login":164,"displayName":165,"avatarUrl":166,"accountType":107,"accountTypeDesc":108,"profileDescription":167,"skillCount":168,"repoCount":169,"professionCount":5,"scenarioCount":6,"totalStars":170,"updatedAt":171},"01M698VYEFDM0VJBZDYYJ2T83S","google","Google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","Google ❤️ Open Source",542,50,243804,"2026-11-15 03:00:30",{"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",87,2,10,188029,"2026-11-15 06:21:09",{"accountNo":183,"login":184,"displayName":185,"avatarUrl":186,"accountType":187,"accountTypeDesc":188,"profileDescription":189,"skillCount":190,"repoCount":191,"professionCount":139,"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. ",340,3,175019,"2026-11-15 03:57:03",9,{"records":196,"total":4,"current":642,"size":129},[197,234,262,286,313,346,377,402,428,449,474,494,515,539,561,585,607,622],{"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":212,"publishedAt":233},"01M6QG7177F1APS2Y58W4EDDNM","torch-geometric","PyTorch Geometric (PyG) for graph neural networks — node\u002Flink\u002Fgraph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-torch-geometric\u002FSKILL.md",[211],{"categoryNo":28,"categoryName":29,"taxonomyType":11,"taxonomyTypeDesc":12},[213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232],"torch geometric","analytics","deep learning","neural networks","pytorch","graph","gnn","data","networks","node","sampling","message","deep","lib","gin","cluster","data-science","org","for","graph neural networks","2026-11-10 10:12:30",{"skillNo":235,"name":236,"nameZh":18,"description":237,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":238,"categories":239,"keywords":243,"publishedAt":233},"01M6QG6ETC6ZAEQMS20SPW8KV3","tiledbvcf","Stores and queries genomic variant data in TileDB-VCF datasets using the tiledbvcf Python API and CLI (create, store, export, list, stat). Covers ingesting single-sample VCF\u002FBCF files with .csi or .tbi indexes, adding samples incrementally, querying regions and samples in parallel, and exporting to VCF\u002FBCF or TSV, on local disk or S3, Azure, and GCS. Use when building a variant database for a cohort, adding new samples to an existing dataset, querying specific regions across many samples, exporting subsets of a large VCF collection, or preparing population genomics data such as allele frequency or GWAS inputs. Not for multi-sample VCFs, which are unsupported, or for one-off parsing of a single VCF file.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-tiledbvcf\u002FSKILL.md",[240],{"categoryNo":241,"categoryName":242,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000010","后端与接口",[236,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,231,259,260,261],"python","create","file","s3","disk","parallel","list","use","files","queries","local","as","vcf","store","which","Existing","variant","variants",{"skillNo":263,"name":264,"nameZh":18,"description":265,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":266,"categories":267,"keywords":268,"publishedAt":233},"01M6QG6636C7V2C19CPP5THQ52","tensorrt-llm","Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100\u002FH100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8\u002FINT4), in-flight batching, and multi-GPU scaling.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-tensorrt-llm\u002FSKILL.md",[],[269,270,217,271,272,273,274,275,276,277,278,251,279,280,281,282,283,284,231,285],"tensorrt llm","tensorrt","ml","deployment","Optimization","FP8","NVIDIA","Inference Serving","llm inference","ops","scaling","latency","H100","throughput","with","you","batching",{"skillNo":287,"name":288,"nameZh":18,"description":289,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":290,"categories":291,"keywords":295,"publishedAt":233},"01M6QG5Z3TTKDYJN3T98V6SQ3F","tensorboard","Logs and views ML training data in TensorBoard using PyTorch SummaryWriter and TensorFlow\u002FKeras callbacks: scalars, images, text, histograms, model graphs, embedding projector, hyperparameter tables, PR curves, and TensorFlow or PyTorch profiler traces. Use when plotting loss and accuracy curves during training, comparing multiple runs in one dashboard, inspecting weight and gradient distributions, projecting embeddings with PCA or t-SNE, tracking hyperparameter experiments, or finding performance bottlenecks in a training loop. Not for hosted experiment tracking with team collaboration; use a dedicated tracking service for that.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-tensorboard\u002FSKILL.md",[292],{"categoryNo":293,"categoryName":294,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000013","分析与可视化",[288,296,297,298,299,300,301,302,303,304,305,251,306,307,308,309,231,310,311,312],"experiments","collaboration","training","mlops","embeddings","logs","team","loop","text","profiling","PCA","Training Metrics","Model Debugging","tables","gradient","accuracy","profiler",{"skillNo":314,"name":315,"nameZh":18,"description":316,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":317,"categories":318,"keywords":328,"publishedAt":233},"01M6QG5NJEEDFSSZM2HDEDR2B3","tamarind","Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required. Tamarind bundles popular open-source models for structure prediction (AlphaFold, Boltz, Chai, ESMFold), protein, binder, and de novo design (RFdiffusion, ProteinMPNN, BoltzGen), antibody and nanobody design and developability, protein-ligand docking (DiffDock, Autodock Vina), binding-affinity prediction, MSA generation, and molecular dynamics. Use when the user mentions Tamarind or tamarind.bio, wants to run any of these open-source tools in the cloud, references app.tamarind.bio\u002Fapi or the x-api-key header, or needs to submit batches of sequences for structural or biophysical characterization.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-tamarind\u002FSKILL.md",[319,320,323,326,327],{"categoryNo":241,"categoryName":242,"taxonomyType":58,"taxonomyTypeDesc":59},{"categoryNo":321,"categoryName":322,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":324,"categoryName":325,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":10,"categoryName":13,"taxonomyType":11,"taxonomyTypeDesc":12},{"categoryNo":21,"categoryName":22,"taxonomyType":11,"taxonomyTypeDesc":12},[315,329,330,331,332,333,334,335,336,337,254,255,338,339,340,341,342,343,344,345],"design","MCP","run","library","server","open","python sdk","msa","structure","app","chai","drug-discovery","de","dynamics","protein structure","at","inverse",{"skillNo":347,"name":348,"nameZh":18,"description":349,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":350,"categories":351,"keywords":360,"publishedAt":233},"01M6QG58TZ7KQ9J8T4DG4R8545","systems-paper-writing","Provides paragraph-level structural blueprints for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Covers page budgets per section, writing patterns (gap analysis, observation-driven, contribution list, thesis formula), evaluation structure, venue checklists, reviewer guidelines, deadlines, and LaTeX templates for OSDI, NSDI, ASPLOS, and SOSP. Use when planning the section and page layout of a systems paper. Use when drafting an introduction, motivation, design, or evaluation section. Use when checking a draft against venue page limits and a pre-submission checklist. Use when anticipating how systems reviewers will assess a paper. Use when looking up conference formats or deadlines. For NeurIPS\u002FICML\u002FICLR papers or citation verification, use ml-paper-writing instead.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-systems-paper-writing\u002FSKILL.md",[352,353,356,359],{"categoryNo":321,"categoryName":322,"taxonomyType":58,"taxonomyTypeDesc":59},{"categoryNo":354,"categoryName":355,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":357,"categoryName":358,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":35,"categoryName":36,"taxonomyType":11,"taxonomyTypeDesc":12},[361,362,363,364,365,329,366,367,250,337,368,369,370,371,372,373,231,374,375,376],"writing","Paper Writing","systems","paper","Systems Paper Writing","Evaluation","how","citation verification","OSDI","NSDI","ASPLOS","SOSP","formats","submission","section","limits",{"skillNo":378,"name":379,"nameZh":18,"description":380,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":381,"categories":382,"keywords":383,"publishedAt":233},"01M6QG4XHRYCGZH239TVP64BAN","systematic-review-prisma","Plan, run and report systematic reviews and meta-analyses to PRISMA 2020 standards. Use when writing a review protocol (PROSPERO\u002FOSF), building reproducible database search strings (PubMed, Embase, Scopus, Web of Science), deduplicating exports, organizing title\u002Fabstract and full-text screening, assessing risk of bias, drawing the PRISMA flow diagram, or completing the PRISMA 2020 checklist. Includes a dedup tool and a checked PRISMA diagram generator.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-systematic-review-prisma\u002FSKILL.md",[],[384,385,386,387,388,361,389,390,391,392,393,394,304,395,396,397,398,399,400,401],"review","prisma","systematic","systematic review","systematic review prisma","diagram","database","search","Meta","analysis","plan","dot","evidence synthesis","literature","pubmed","reviews","strings","title",{"skillNo":403,"name":404,"nameZh":18,"description":405,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":406,"categories":407,"keywords":411,"publishedAt":233},"01M6QG46YAE8SA77YHATDR04YG","statistical-power","Sample-size and statistical power calculations for planning studies. Use whenever someone asks \"how many subjects\u002Fsamples\u002Freplicates do I need\", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB protocol, or pre-registration. Covers closed-form power for t-tests, ANOVA, proportions, correlations, chi-square, and regression, plus simulation-based (Monte Carlo) power for designs with no formula — logistic\u002FPoisson regression, mixed models, cluster-randomized trials, survival, and interactions. Use this skill even when the request only mentions an effect size, alpha, or \"80% power\" without saying \"power analysis\" explicitly. For laying out the study (randomization, blocking, factorial\u002FDOE, crossover, sequential designs) use experimental-design; for analyzing data already collected and reporting it use statistical-analysis.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-statistical-power\u002FSKILL.md",[408,409,410],{"categoryNo":321,"categoryName":322,"taxonomyType":58,"taxonomyTypeDesc":59},{"categoryNo":324,"categoryName":325,"taxonomyType":58,"taxonomyTypeDesc":59},{"categoryNo":21,"categoryName":22,"taxonomyType":11,"taxonomyTypeDesc":12},[412,413,329,244,414,415,416,367,417,418,419,420,421,422,423,424,425,426,427,231],"power","statistical power","MDE","statistical-analysis","simulation","effect","read","write","edit","sample-size","registration","do","scipy","square","tests","form",{"skillNo":429,"name":415,"nameZh":18,"description":430,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":431,"categories":432,"keywords":436,"publishedAt":233},"01M6QG3ZCXN2XKWAY1744SWECQ","Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check statistical assumptions, compute required sample sizes, or write up results - even if they never name a specific test. Covers t-tests, ANOVA, chi-square, correlation, regression, non-parametric and Bayesian methods. For low-level model APIs, see the statsmodels and pymc skills.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-statistical-analysis\u002FSKILL.md",[433],{"categoryNo":434,"categoryName":435,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000008","测试与质量",[393,437,438,439,440,441,417,419,442,251,412,443,444,445,425,446,426,447,231,448],"statistical analysis","testing","research","analyze","check","results","survey","selection","methods","compute","compare","alternatives",{"skillNo":450,"name":451,"nameZh":18,"description":452,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":453,"categories":454,"keywords":458,"publishedAt":233},"01M6QG3R1M59QCGZJQEZ3NRA6K","stable-diffusion-image-generation","Generates images with Stable Diffusion models (SD 1.5, SDXL, SD 3.0, Flux) through the HuggingFace Diffusers library, covering text-to-image, image-to-image, inpainting, outpainting, ControlNet conditioning, LoRA adapters, scheduler swapping, and GPU memory optimization. Use when generating images from text prompts, transforming or restyling an existing image, filling masked regions of an image, adding spatial control from edges, poses, or depth maps, loading LoRA style adapters, or fixing out-of-memory and black-image errors in a Diffusers pipeline. Not for API-only generation without a GPU, where DALL-E 3 fits better.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-stable-diffusion-image-generation\u002FSKILL.md",[455],{"categoryNo":456,"categoryName":457,"taxonomyType":58,"taxonomyTypeDesc":59},"01JBSEEDCAT000000000000016","图像与多媒体",[459,460,461,462,463,464,465,332,466,467,304,251,468,469,470,471,472,473,231,259],"image","Image Generation","Stable Diffusion","stable diffusion image generation","generation","diffusion","multimodal","LoRA","HuggingFace","flux","black","style","Accelerate","Memory Optimization","sd",{"skillNo":475,"name":476,"nameZh":18,"description":477,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":478,"categories":479,"keywords":481,"publishedAt":233},"01M6QG3D2FK4WNNFF7Z7TRQB83","stable-baselines3","Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-stable-baselines3\u002FSKILL.md",[480],{"categoryNo":324,"categoryName":325,"taxonomyType":58,"taxonomyTypeDesc":59},[482,483,296,217,298,484,485,220,486,487,418,419,420,488,489,490,229,491,492,493],"stable baselines3","performance","learn","vectorized","api","Bash","ready","scikit-learn","high-performance","prototyping","quick","production-ready",{"skillNo":495,"name":496,"nameZh":18,"description":497,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":498,"categories":499,"keywords":500,"publishedAt":233},"01M6QG374J4BBWVJB7VWKZT4MN","springer-lncs","Format papers for Springer Lecture Notes in Computer Science (LNCS) and related proceedings series (LNAI, LNBI, CCIS) and Springer Nature journals using the llncs class or Springer Nature's sn-jnl template, covering page limits, abstract and keywords, splncs04 references, ORCID, running heads, camera-ready packages and the consent-to-publish form. Use when writing for conferences published in LNCS (e.g. ECCV, MICCAI, ESWC, many workshops), preparing an LNCS camera-ready, or targeting Springer Nature journals.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-springer-lncs\u002FSKILL.md",[],[501,361,502,503,504,505,506,507,488,508,509,510,511,512,427,513,514,373,231,376],"springer lncs","notes","packages","publish","template","Word","computer","camera","references","formatting","distribution","journal","papers","targeting",{"skillNo":516,"name":517,"nameZh":18,"description":518,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":519,"categories":520,"keywords":521,"publishedAt":233},"01M6QG2Y41EV6HP2Z88VVF8GE6","speculative-decoding","Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-speculative-decoding\u002FSKILL.md",[],[522,465,523,524,249,525,526,527,528,529,530,471,531,532,533,534,535,536,537,538],"speculative decoding","Fast Inference","Transformers","deployment strategies","time","strategies","attention","token","iteration","Emerging Techniques","medusa","Lookahead Decoding","Draft Models","Tree Attention","Parallel Generation","Latency Reduction","tree",{"skillNo":540,"name":541,"nameZh":18,"description":542,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":543,"categories":544,"keywords":545,"publishedAt":233},"01M6QG2QWCDSV2T1GR0G5FGK2V","sparse-autoencoder-training","Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-sparse-autoencoder-training\u002FSKILL.md",[],[298,546,271,366,547,548,549,550,251,551,552,553,554,555,556,557,558,559,231,560],"sparse autoencoder training","analyzing","network","Safety","discovery","decompose","Neural","superposition","feature","saelens","neural network","lens","Transformer","Interpretability","features",{"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":233},"01M6QG2EXPP1ZBXXVZP379VAA5","slime-rl-training","Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-slime-rl-training\u002FSKILL.md",[],[298,568,569,570,571,572,573,574,575,576,577,251,578,579,580,581,582,583,231,584],"rl","slime rl training","slime","workflows","reinforcement learning","integration","GRPO","Post-Training","Ray","learning","router","models","reinforcement","post","megatron","implementing","custom",{"skillNo":586,"name":587,"nameZh":18,"description":588,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":589,"categories":590,"keywords":591,"publishedAt":233},"01M6QG29GAX3VNS4FWXXRM7049","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\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-skypilot-multi-cloud-orchestration\u002FSKILL.md",[],[592,593,594,595,596,597,598,599,298,331,600,601,251,602,603,604,605,284,231,606],"orchestration","cloud","SkyPilot","skypilot multi cloud orchestration","multi cloud","multi","cost optimization","infrastructure","batch","multi-cloud","auto","cost","instances","leverage","automatic",{"skillNo":608,"name":609,"nameZh":18,"description":610,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":611,"categories":612,"keywords":613,"publishedAt":233},"01M6QG1V6QKJY3Q60KHA14VZ5B","simpy","Builds, tests, and analyzes bounded process-based discrete-event simulations in Python with SimPy 4.1.2: Environment, Timeout, Process, AnyOf\u002FAllOf conditions, interrupts, Resource, PriorityResource, PreemptiveResource, Container, Store, time-weighted monitoring, and replication-based output analysis, plus bundled safe CLIs. Use when modeling queues, production lines, logistics, or service operations with generator processes; when contending entities need shared resources or preemption; when instrumenting queue length or utilization correctly; when running independent replications with seeds and confidence intervals; when debugging event ordering or run(until=) boundaries. Not for continuous-time ODE or agent-based modeling frameworks.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-simpy\u002FSKILL.md",[],[609,614,244,331,332,615,416,418,419,420,616,617,526,254,618,426,619,620,231,621],"safe","monitoring","uv","frameworks","shared","resources","replication","queues",{"skillNo":623,"name":624,"nameZh":18,"description":625,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":626,"categories":627,"keywords":628,"publishedAt":233},"01M6QG1NT4BGS0Z5CMXB2KY5CC","simpo-training","Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO\u002FPPO.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-simpo-training\u002FSKILL.md",[],[298,629,630,483,273,575,631,524,632,633,634,471,635,636,637,638,639,640,641,231],"simpo training","simpo","PPO","model","alignment","free","TRL","Efficient Training","Preference Optimization","DPO Alternative","Reference-Free","LLM Alignment","more",25441]