[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skills:stats":3,"skills:sce6":8,"skills:pro6":55,"skills:creators9":100,"skills:all:stars:25451:":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},"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",1,39675,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",26798,[],{"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",13847,[],{"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",6403,[],{"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",6063,[],{"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",5574,[],[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",13341,[],{"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",7902,[],{"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",5005,[],{"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",3978,[],{"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",3454,[],{"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",3337,[],{"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":637,"size":129},[197,236,263,287,304,335,358,385,414,440,460,484,504,522,543,566,589,613],{"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":235},"01M6QEK62MBMMWTY6CCD8D9JST","firecrawl-research-index","Query Firecrawl Research Index paper endpoints for topic discovery, source metadata, question-matched passages, and citation-neighbor expansion. Use when a researcher explicitly asks for Firecrawl Research or its hosted arXiv and biomedical paper records.","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-firecrawl-research-index\u002FSKILL.md",[211],{"categoryNo":212,"categoryName":213,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000021","资料检索与研究",[215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234],"research","index","firecrawl","firecrawl research index","firecrawl research","review","cli","documents","search","ips","api","access","question","query","volume","life","free","literature","pubmed","firecrawl cli","2026-11-10 10:12:30",{"skillNo":237,"name":238,"nameZh":18,"description":239,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":240,"categories":241,"keywords":242,"publishedAt":235},"01M6QEJW8629F697JT0WQD9PN3","fine-tuning-with-trl","Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO\u002FGRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-fine-tuning-with-trl\u002FSKILL.md",[],[243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262],"tuning","fine tuning","fine tuning with trl","TRL","with","llms","training","Optimization","Post-Training","RLHF","Transformers","learning","model","feedback","alignment","align","human","Accelerate","Instruction Tuning","for",{"skillNo":264,"name":265,"nameZh":18,"description":266,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":267,"categories":268,"keywords":269,"publishedAt":235},"01M6QEJH3RP4GYCC5BDBVSYW17","fine-tuning-serving-openpi","Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-fine-tuning-serving-openpi\u002FSKILL.md",[],[243,244,270,271,272,273,274,275,276,277,278,279,280,281,282,283,284,285,262,286],"OpenPI","fine tuning serving openpi","serving","policy","multimodal","stats","Fine-Tuning","use","uv","VLA","Physical Intelligence","JAX","Policy Serving","ALOHA","DROID","pi0","custom",{"skillNo":288,"name":289,"nameZh":18,"description":290,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":291,"categories":292,"keywords":293,"publishedAt":235},"01M6QEHYNYWVZF80RGAC1E5KGG","fine-tuning-openvla-oft","Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-fine-tuning-openvla-oft\u002FSKILL.md",[],[243,244,294,295,249,296,274,297,298,276,299,300,277,301,302,260,283,303,262,286],"OpenVLA","fine tuning openvla oft","deployment","server","actions","LoRA","simulation","chunking","adaptation","uvicorn",{"skillNo":305,"name":306,"nameZh":18,"description":307,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":308,"categories":309,"keywords":316,"publishedAt":235},"01M6QEH7W48BGYYVST5BBR5930","fictiv","Drives the Fictiv on-demand manufacturing web app (app.fictiv.com) in the user's browser, since there is no public API. Covers uploading CAD files (STEP, SLDPRT, STL), configuring process, material, finish, threads and tolerances, reading DFM feedback, instant or manual quotes, lead-time tiers, checkout by card or PO, order tracking and reorders. Use when the user mentions Fictiv. Use when they want a part CNC machined, 3D printed, sheet-metal fabricated, cast, or molded online. Use when they ask to get a quote or order parts from a STEP or STL file. Use when they need to check a Fictiv quote or order status. Use when a Fictiv upload, DFM warning, price or checkout fails. Not for ITAR-controlled parts, which Fictiv does not accept.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-fictiv\u002FSKILL.md",[310,313],{"categoryNo":311,"categoryName":312,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":314,"categoryName":315,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000023","Skill与智能体开发",[306,317,318,319,320,321,322,323,324,325,326,327,328,329,330,331,332,333,334,262],"python","status","library","ui","3D","tool","finish","files","time","live","app","material","card","public api","tolerances","reading","which","at",{"skillNo":336,"name":337,"nameZh":18,"description":338,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":339,"categories":340,"keywords":341,"publishedAt":235},"01M6QEGSWGQJBQXX2N30ZQ5GBG","faiss","Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-faiss\u002FSKILL.md",[],[337,342,343,223,344,345,319,346,347,348,349,350,351,352,353,354,355,356,357,262],"performance","rag","vector","high performance","clustering","applications","knowledge","high-performance","CPU","Facebook AI","GPU Acceleration","Billion-Scale","K-NN","Large Scale","types","you",{"skillNo":359,"name":360,"nameZh":18,"description":361,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":362,"categories":363,"keywords":368,"publishedAt":235},"01M6QEG8DSJ309WVQKFSMT11HT","exploratory-data-analysis","Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV\u002FTSV\u002FJSON profiles; optional NumPy, HDF5, FASTA\u002FFASTQ, and basic image metadata inspection; missingness\u002Fleakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain formats are reference-only and unknown formats fail closed.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-exploratory-data-analysis\u002FSKILL.md",[364,367],{"categoryNo":365,"categoryName":366,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":73,"categoryName":74,"taxonomyType":58,"taxonomyTypeDesc":59},[369,370,371,372,373,374,375,376,377,278,324,378,379,380,381,231,382,383,262,384],"data analysis","data","exploratory data analysis","analysis","image","read","write","edit","snapshot","domain","local","sensitivity","transformation","scientific","formats","unknown",{"skillNo":386,"name":387,"nameZh":18,"description":388,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":389,"categories":390,"keywords":396,"publishedAt":235},"01M6QEFSDQ6DC977XXCSGZ7568","experimental-design","Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. Use whenever someone is planning a study, asks how to assign subjects\u002Fsamples to groups, mentions randomization, blocking, stratification, controls, factorial or fractional-factorial designs, design of experiments (DOE), screening many factors, response-surface optimization, crossover or repeated-measures or split-plot designs, cluster\u002Fgroup randomization, Latin squares, plate layouts, batch\u002Frun-order effects, replication vs. pseudoreplication, or sequential\u002Fadaptive\u002Fgroup-sequential designs. Trigger even for informal phrasings like \"how should I set up this experiment\", \"how do I avoid confounding\", \"what's the best way to test these 6 factors\", or \"assign these mice to conditions\". For computing the sample size or power once the design is chosen, use statistical-power; for analyzing data already collected, use statistical-analysis.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-experimental-design\u002FSKILL.md",[391,394,395],{"categoryNo":392,"categoryName":393,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":314,"categoryName":315,"taxonomyType":11,"taxonomyTypeDesc":12},{"categoryNo":66,"categoryName":67,"taxonomyType":58,"taxonomyTypeDesc":59},[397,398,399,400,401,402,372,403,404,374,405,406,278,407,408,409,410,411,412,413],"design","experimental design","run","batch","pandas","SET","how","Bash","power","up","sample","statistics","scripts","how to","design of experiments","effects","analyzing data",{"skillNo":415,"name":416,"nameZh":18,"description":417,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":418,"categories":419,"keywords":421,"publishedAt":235},"01M6QEFC2BD0HW9XD1YJDRCZRX","experiment-tracking-swanlab","Tracks ML experiments with SwanLab, an open-source tool covering swanlab.init, config and metric logging, scalar charts, and media logging (images, audio, text, GIFs, point clouds, molecules), in cloud, local (mode=\"local\" with swanlab[dashboard]), or self-hosted setups. Includes integrations for PyTorch, Transformers, PyTorch Lightning, and Fastai. Use when logging metrics and hyperparameters for training runs, comparing runs across seeds, checkpoints, or hyperparameters, running an offline or self-hosted dashboard instead of managed SaaS, logging media alongside scalars, or adding tracking callbacks to a Transformers, Lightning, or Fastai training loop. Not for other trackers such as Weights & Biases or MLflow.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-experiment-tracking-swanlab\u002FSKILL.md",[420],{"categoryNo":365,"categoryName":366,"taxonomyType":11,"taxonomyTypeDesc":12},[422,423,424,425,426,427,428,249,429,430,431,432,433,434,435,436,437,379,438,439],"tracking","experiment","Experiment Tracking","SwanLab","experiment tracking swanlab","experiments","config","offline","open source","Media","Audio","Charts","open","loop","text","self-hosted","pillow","mode",{"skillNo":441,"name":442,"nameZh":18,"description":443,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":444,"categories":445,"keywords":449,"publishedAt":235},"01M6QEEZVESFMVXND65WEPS20J","exa-search","Web toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or fetch\u002Fextract URL content. Covers: web search (semantic lookups, research, current info — with optional research-paper category and academic domain filtering) and URL extraction (fetching pages, articles, academic PDFs in batch). Use this skill for web-related tasks when the user wants high-quality search or scholarly filtering via category=research paper. Triggers on requests to search, look up, fetch a page, or extract an article.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-exa-search\u002FSKILL.md",[446,447,448],{"categoryNo":212,"categoryName":213,"taxonomyType":11,"taxonomyTypeDesc":12},{"categoryNo":314,"categoryName":315,"taxonomyType":11,"taxonomyTypeDesc":12},{"categoryNo":80,"categoryName":81,"taxonomyType":58,"taxonomyTypeDesc":59},[223,450,451,220,452,400,225,226,453,454,455,406,456,378,457,232,382,458,459,262],"exa search","exa","tasks","web search","python sdk","fetch","info","article","URL","internet",{"skillNo":461,"name":462,"nameZh":18,"description":463,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":464,"categories":465,"keywords":467,"publishedAt":235},"01M6QEEJK14GNJK196BAJ0239T","evolving-ai-agents","Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-evolving-ai-agents\u002FSKILL.md",[466],{"categoryNo":314,"categoryName":315,"taxonomyType":11,"taxonomyTypeDesc":12},[468,469,470,471,472,347,473,474,475,277,476,477,378,478,479,480,481,482,483,262],"ai agents","evolving ai agents","agentic","agentic ai","Evaluation","discovery","prompt","evolution","skill discovery","guidance","algorithms","across","driven","Prompt Optimization","self-improving","implementing",{"skillNo":485,"name":486,"nameZh":18,"description":487,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":488,"categories":489,"keywords":490,"publishedAt":235},"01M6QEE2WCHSMGSQKFE5JZCPMP","evaluating-llms-harness","Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-evaluating-llms-harness\u002FSKILL.md",[],[248,491,492,493,494,249,495,472,496,497,498,253,499,255,500,277,479,501,502,503],"harness","evaluating llms harness","benchmarking","ml","reporting","HumanEval","MMLU","vLLM","Safety","eval","progress","LM Evaluation Harness","GSM8K",{"skillNo":505,"name":506,"nameZh":18,"description":507,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":508,"categories":509,"keywords":510,"publishedAt":235},"01M6QEDQRDNGWHHFAFA6JEJ5DH","evaluating-cosmos-policy","Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-evaluating-cosmos-policy\u002FSKILL.md",[],[273,511,512,513,514,274,472,515,253,300,277,406,516,379,517,518,519,520,521,262],"cosmos","Cosmos Policy","evaluating cosmos policy","git","NVIDIA","robotics","latency","cluster","rendering","environments","headless",{"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":529,"publishedAt":235},"01M6QEDA7QZPSB5QGSZNK0PVGZ","evaluating-code-models","Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-evaluating-code-models\u002FSKILL.md",[528],{"categoryNo":57,"categoryName":60,"taxonomyType":58,"taxonomyTypeDesc":59},[530,531,532,533,534,535,493,472,536,496,537,538,539,540,253,499,479,541,260,542],"code","Code Models","models","evaluating code models","testing","support","Code Generation","MBPP","MultiPL-E","Pass@k","BigCode","project","multipl",{"skillNo":544,"name":545,"nameZh":18,"description":546,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":547,"licenseFileUrl":18,"sourceHtmlUrl":548,"categories":549,"keywords":553,"publishedAt":235},"01M6QECYSYTMP262ZRDGT91S84","etetoolkit","Analyze, manipulate, compare, annotate, and visualize phylogenetic or other hierarchical trees with ETE 4. Use for Newick\u002FNexus tree I\u002FO, topology edits and pattern matching, Robinson-Foulds comparisons, gene-tree evolutionary events and reconciliation, NCBI\u002FGTDB taxonomy, SmartView exploration, and publication rendering. Do not use it to infer trees from raw sequences; align sequences and infer a tree first.","GPL-3.0","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-etetoolkit\u002FSKILL.md",[550],{"categoryNo":551,"categoryName":552,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000002","文档处理",[545,554,317,555,556,374,375,376,277,557,558,559,560,561,562,519,563,262,564,565],"PDF","topology","analyze","do","exploration","phylogenetics","evolutionary biology","events","compare","trees","gene","static",{"skillNo":567,"name":568,"nameZh":18,"description":569,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":570,"categories":571,"keywords":575,"publishedAt":235},"01M6QECJ8Y3XMF8E8G6JD6YZ8E","esm","Covers the EvolutionaryScale\u002FBiohub `esm` Python SDK: ESM3 generative protein design (sequence, structure and function tracks, chain-of-thought), ESMC embeddings, inverse folding, ESMFold2 structure prediction, and hosted Forge\u002FBiohub inference with ESM_API_KEY. Use when generating or completing proteins with ESM3, extracting ESMC embeddings for classification or similarity, folding a sequence or designing sequences from a structure, or choosing between esm3-open, esmc_300m and Forge-hosted models. Use when batching async Forge or Biohub API calls. Not for other protein models such as AlphaFold or generic Hugging Face transformers usage.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-esm\u002FSKILL.md",[572,573,574],{"categoryNo":311,"categoryName":312,"taxonomyType":11,"taxonomyTypeDesc":12},{"categoryNo":392,"categoryName":393,"taxonomyType":11,"taxonomyTypeDesc":12},{"categoryNo":66,"categoryName":67,"taxonomyType":58,"taxonomyTypeDesc":59},[568,397,576,577,253,225,434,454,578,579,230,580,581,582,583,584,585,586,587,588],"embeddings","forge","hugging face","structure","proteins","as","chain","chain-of-thought","extracting","inverse","sequence","generative","face",{"skillNo":590,"name":591,"nameZh":18,"description":592,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":593,"categories":594,"keywords":596,"publishedAt":235},"01M6QEC3GTJNQJ95NCANT0A24Y","elsevier-cas","Prepare submissions to Elsevier journals (including The Lancet family style notes, Cell-independent Elsevier titles, and thousands of society journals) using the elsarticle LaTeX class, the CAS single\u002Fdouble-column templates or Word, covering highlights, graphical abstracts, keywords, CRediT author statements, declarations of interest, generative-AI disclosure, data availability, reference styles per journal, Editorial Manager submission and \"Your Paper Your Way\" format-free first submission. Use when targeting an Elsevier journal or fixing elsarticle\u002FCAS template issues.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-elsevier-cas\u002FSKILL.md",[595],{"categoryNo":551,"categoryName":552,"taxonomyType":11,"taxonomyTypeDesc":12},[597,598,599,370,600,601,602,603,604,605,231,606,607,383,608,609,587,610,611,612],"elsevier cas","notes","issues","template","Word","family","formatting","distribution","journal","availability","targeting","manager","editorial","submission","generative-ai","single",{"skillNo":614,"name":615,"nameZh":18,"description":616,"descriptionZh":18,"repositoryFullName":201,"ownerLogin":202,"ownerAvatarUrl":203,"ownerAccountNo":204,"ownerDisplayName":205,"repositoryNo":206,"starsCount":207,"licenseSpdxId":208,"licenseFileUrl":18,"sourceHtmlUrl":617,"categories":618,"keywords":624,"publishedAt":235},"01M6QEBPA3F2PK3PS7V98EF6H0","dspy","Builds and optimizes language model programs with DSPy (Stanford NLP), using Signatures, modules (Predict, ChainOfThought, ReAct, ProgramOfThought) and optimizers (BootstrapFewShot, MIPRO, BootstrapFinetune). Use when replacing hand-written prompts with declarative signatures, when automatically tuning prompts against training data and a metric, when building multi-stage RAG pipelines or ReAct agents, when building classifiers or structured-output programs, or when saving and evaluating optimized LM programs across providers such as Anthropic, OpenAI, or Ollama. Not for quick prototypes or simple chains; use manual prompting or LangChain instead.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkal-dspy\u002FSKILL.md",[619,622,623],{"categoryNo":620,"categoryName":621,"taxonomyType":11,"taxonomyTypeDesc":12},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":314,"categoryName":315,"taxonomyType":11,"taxonomyTypeDesc":12},{"categoryNo":57,"categoryName":60,"taxonomyType":58,"taxonomyTypeDesc":59},[615,625,626,627,343,249,347,628,629,474,277,630,631,632,581,633,262,634,635,636],"nlp","react","modular","programming","langchain","modules","signatures","prompting","quick","automatic","predict","declarative",25451]