[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EW7SP4PX1W8CD89SMZ442V":3,"skill-same:01M7EW7SP4PX1W8CD89SMZ442V":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7EW7SP4PX1W8CD89SMZ442V","transformers-library",null,"Work with the Transformers ecosystem — pipelines, tokenizers, model loading, training loops, and the hub. Use when using pretrained models for NLP tasks or fine-tuning.","TanNhatCMS\u002Fjarvis","TanNhatCMS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113796420?v=4","01M753MV17KG5CD3152G3WQEQY","KietNT","01M7EKEDYVYQ6PWVJJMZ911VMX",0,"MIT","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-transformers-library\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: transformers-library\ndescription: Work with the Transformers ecosystem — pipelines, tokenizers, model loading, training loops, and the hub. Use when using pretrained models for NLP tasks or fine-tuning.\ncategory: ai-research\n---\n\n# Transformers Library\n\nThe Transformers library is the standard interface to pretrained models: tens of thousands of \nmodels behind a uniform API — load any architecture, tokenize correctly, run inference or \ntraining with the same patterns.\n\n## Overview\n\nThree abstractions do most of the work: tokenizers (text → model inputs, model-specific), models \n(the architectures, loaded from the hub with matching configs), and pipelines (task-level wrappers: \nsentiment, QA, summarization). Underneath, the Trainer handles training loops with all the standard \nmachinery. Learn these four and you can use nearly any open model.\n\n## When to use\n\n- Using pretrained models for classification, extraction, generation, or embeddings.\n- Fine-tuning open models on your data.\n- Prototyping NLP features quickly with pipelines.\n- Understanding model architectures through their implementations.\n\n## Core concepts\n\n- **Pipelines**: one-line task interfaces (`sentiment-analysis`, `question-answering`, \n`summarization`). Start here for prototyping; drop to models when you need control.\n- **Tokenizers**: model-specific text processing — always use the tokenizer paired with the \nmodel. Mismatched tokenizers silently corrupt inputs. Handle truncation, padding, and special \ntokens explicitly.\n- **Auto classes**: `AutoModel`, `AutoTokenizer` load the right implementation from the model name. \nArchitecture-agnostic code that works across models.\n- **Model loading**: from the hub by name, with options for precision (fp16), device mapping, and \nquantization. Know what `device_map` and dtype choices do to memory.\n- **Trainer**: the training loop — data collation, optimization, evaluation, checkpointing, \nlogging. Configure via training arguments; custom callbacks for special needs.\n- **The Hub**: model versioning, model cards (read them — they document training data and \nlimitations), and community models. Pin revisions for reproducibility.\n\n## Practical workflow\n\n1. Prototype with a pipeline on your data; verify the task framing works before investing.\n2. Move to Auto classes when you need control: load model + matching tokenizer, handle batching \nyourself.\n3. For fine-tuning: prepare the dataset in the model's expected format, configure Trainer arguments \n(learning rate, epochs, eval strategy), train with evaluation.\n4. Save and version: model + tokenizer + config together, pinned to a hub revision or local \nsnapshot.\n5. Evaluate on held-out data with task metrics; compare against the pipeline baseline.\n6. For deployment: export to optimized formats (quantized, ONNX) as needed; document the exact \nmodel revision.\n\n```text\nStandard flow:\npipeline (prototype) → AutoModel + AutoTokenizer (control)\n→ Trainer (fine-tune) → save (model+tokenizer+config)\n→ evaluate (held-out) → optimize + deploy (pinned revision)\n```\n\n## Common pitfalls\n\n- **Tokenizer mismatch**: using a generic or wrong tokenizer. Always pair with the model; verify \nspecial tokens.\n- **Unpinned hub revisions**: models update; your results shift. Pin the revision.\n- **Padding\u002Ftruncation bugs**: silent corruption from wrong padding side or missing attention \nmasks. Handle explicitly, verify shapes.\n- **Trainer defaults**: default hyperparameters are starting points, not answers. Tune learning \nrate and epochs for your data size.\n- **Ignoring model cards**: training data, biases, and limitations documented there. Read before \ndeploying.\n- **GPU memory surprises**: models bigger than expected once loaded with optimizer states. \nCalculate before training; use gradient accumulation and mixed precision.\n","# Transformers Library\n\nThe Transformers library is the standard interface to pretrained models: tens of thousands of \nmodels behind a uniform API — load any architecture, tokenize correctly, run inference or \ntraining with the same patterns.\n\n## Overview\n\nThree abstractions do most of the work: tokenizers (text → model inputs, model-specific), models \n(the architectures, loaded from the hub with matching configs), and pipelines (task-level wrappers: \nsentiment, QA, summarization). Underneath, the Trainer handles training loops with all the standard \nmachinery. Learn these four and you can use nearly any open model.\n\n## When to use\n\n- Using pretrained models for classification, extraction, generation, or embeddings.\n- Fine-tuning open models on your data.\n- Prototyping NLP features quickly with pipelines.\n- Understanding model architectures through their implementations.\n\n## Core concepts\n\n- **Pipelines**: one-line task interfaces (`sentiment-analysis`, `question-answering`, \n`summarization`). Start here for prototyping; drop to models when you need control.\n- **Tokenizers**: model-specific text processing — always use the tokenizer paired with the \nmodel. Mismatched tokenizers silently corrupt inputs. Handle truncation, padding, and special \ntokens explicitly.\n- **Auto classes**: `AutoModel`, `AutoTokenizer` load the right implementation from the model name. \nArchitecture-agnostic code that works across models.\n- **Model loading**: from the hub by name, with options for precision (fp16), device mapping, and \nquantization. Know what `device_map` and dtype choices do to memory.\n- **Trainer**: the training loop — data collation, optimization, evaluation, checkpointing, \nlogging. Configure via training arguments; custom callbacks for special needs.\n- **The Hub**: model versioning, model cards (read them — they document training data and \nlimitations), and community models. Pin revisions for reproducibility.\n\n## Practical workflow\n\n1. Prototype with a pipeline on your data; verify the task framing works before investing.\n2. Move to Auto classes when you need control: load model + matching tokenizer, handle batching \nyourself.\n3. For fine-tuning: prepare the dataset in the model's expected format, configure Trainer arguments \n(learning rate, epochs, eval strategy), train with evaluation.\n4. Save and version: model + tokenizer + config together, pinned to a hub revision or local \nsnapshot.\n5. Evaluate on held-out data with task metrics; compare against the pipeline baseline.\n6. For deployment: export to optimized formats (quantized, ONNX) as needed; document the exact \nmodel revision.\n\n```text\nStandard flow:\npipeline (prototype) → AutoModel + AutoTokenizer (control)\n→ Trainer (fine-tune) → save (model+tokenizer+config)\n→ evaluate (held-out) → optimize + deploy (pinned revision)\n```\n\n## Common pitfalls\n\n- **Tokenizer mismatch**: using a generic or wrong tokenizer. Always pair with the model; verify \nspecial tokens.\n- **Unpinned hub revisions**: models update; your results shift. Pin the revision.\n- **Padding\u002Ftruncation bugs**: silent corruption from wrong padding side or missing attention \nmasks. Handle explicitly, verify shapes.\n- **Trainer defaults**: default hyperparameters are starting points, not answers. Tune learning \nrate and epochs for your data size.\n- **Ignoring model cards**: training data, biases, and limitations documented there. Read before \ndeploying.\n- **GPU memory surprises**: models bigger than expected once loaded with optimizer states. \nCalculate before training; use gradient accumulation and mixed precision.\n",{"name":5,"category":24,"description":7},"ai-research","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-transformers-library",1,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis","https:\u002F\u002Fgithub.com\u002FTanNhatCMS","https:\u002F\u002Fmrkiet.name.vn","2026-11-07 14:23:08",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add TanNhatCMS\u002Fjarvis --skill transformers-library",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill transformers-library",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill transformers-library","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-transformers-library\u002FSKILL.md",true,[],[48,55,63,70,77,84],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7EWYJR0J8DARY7E59Z6Y9MV","web-scrape","Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open\u002Ffetch fails on JS-heavy pages, or when you need clean markdown\u002Fstructured extraction from a site. Requires FIRECRAWL_API_KEY.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fweb-scrape\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":59,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7EWYBN5P6F2AJG3FR24T9BP","design-taste-frontend","tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML\u002FCSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, \"AI-made\", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7EWY8FQFNQ2GB7NZZWGSSDX","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-tdd\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7EWY5SHBFRH1HDHVWM9K7TV","systematic-debugging","Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-debugging\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7EWY3NM0Z0JAKS7HDZ24K66","requesting-code-review","Use when completing tasks, implementing major features, or before merging to verify work meets requirements","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-code-review\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7EWY0WRMWX4M9ZFY0WKC593","brainstorming","You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-brainstorming\u002FSKILL.md",[],[]]