[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EWFJJRY2V520E693KGHCX6":3,"skill-same:01M7EWFJJRY2V520E693KGHCX6":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},"01M7EWFJJRY2V520E693KGHCX6","yi-guide",null,"Build with 01.AI's Yi models — capable bilingual open models with strong Chinese-English performance.","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-yi-guide\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: yi-guide\ndescription: Build with 01.AI's Yi models — capable bilingual open models with strong Chinese-English performance.\ncategory: ai-research\n---\n\n## Overview\n\nYi (01.AI, founded by Kai-Fu Lee) is a bilingual open-model family with\nparticularly strong Chinese-English performance — the Yi models debuted with\nimpressive benchmark scores in their size classes and a focus on high-quality\nbilingual training. Available in multiple sizes including long-context\nvariants, Yi serves builders needing strong Chinese language capability in an\nopen model.\n\nFor builders, Yi's place is in the bilingual open-model evaluation set: if\nyour application serves Chinese-speaking users, Yi deserves benchmarking\nalongside Qwen, DeepSeek, and other bilingual families. The models run on\nstandard stacks and are hosted by inference providers.\n\nThe practical stance: evaluate Yi where bilingual quality matters. Include it\nin the comparison set; let your evals decide.\n\n## When to use\n\n- Bilingual Chinese-English applications needing strong Chinese quality.\n- Open-model evaluations for Chinese-language tasks.\n- Long-context bilingual document processing (Yi's long-context variants).\n- Fine-tuning bilingual base models.\n- Self-hosting capable bilingual open models.\n- Diversifying beyond the most common open families.\n\n## Core concepts\n\n- **Bilingual training focus**: strong Chinese and English from the training\n  mix. For Chinese-language products, this is the relevant axis — test it\n  directly.\n- **Size options**: multiple sizes across releases. Benchmark the ladder to\n  right-size for your task.\n- **Long-context variants**: extended-context versions for document-scale\n  bilingual work. Test long-context quality on your real documents.\n- **Open weights**: downloadable, self-hostable, fine-tunable. Check license\n  terms per release.\n- **Standard-stack compatibility**: runs on vLLM, TGI, llama.cpp, and\n  provider APIs. No special deployment requirements.\n- **Instruction-tuned variants**: chat-tuned versions for assistants and\n  dialogue.\n- **Vision extensions**: multimodal Yi variants for image+text bilingual\n  tasks — evaluate against alternatives on your images.\n- **Release cadence**: the family evolves; track new releases and re-benchmark\n  deliberately.\n\n## Practical workflow\n\n1. **Define bilingual requirements.** Which tasks in Chinese, which in English,\n   which mixed? The eval set should reflect the real language mix.\n2. **Benchmark against bilingual peers.** Yi vs. Qwen, DeepSeek, and others on\n   your bilingual eval set. Per-language scores, not just aggregates.\n3. **Test long-context if relevant.** Your longest real bilingual documents;\n   questions spanning the input.\n4. **Right-size via the ladder.** Smallest adequate size for your quality bar.\n5. **Check licensing.** Verify terms per release for your use case.\n6. **Evaluate deployment.** API for speed; self-hosted for volume economics.\n7. **Pin versions; track releases.** Production pins; deliberate re-evaluation\n   on new releases.\n\nChecklist for Yi in production:\n- Bilingual eval set reflecting your real language mix.\n- Benchmarked against bilingual peer models.\n- Long-context validated on real documents (if used).\n- License verified; version pinned.\n- Deployment economics modeled.\n\n## Common pitfalls\n\n- **Aggregate-score blindness.** A good average hiding weak Chinese (or\n  English). Score per language.\n- **Ignoring bilingual peers.** Evaluating Yi alone instead of against Qwen,\n  DeepSeek, and others. The decision is relative.\n- **Long-context assumed.** Extended window without testing quality over long\n  bilingual inputs.\n- **License not verified.** Assuming terms across releases.\n- **Wrong size.** Not ladder-testing; over- or under-provisioning.\n- ** monolingual evals for bilingual products.** Testing only English for a\n  Chinese-serving product (or vice versa).\n- **Version drift.** Floating references updating underneath production.\n- **Static choice.** Not re-evaluating as the bilingual open-model field\n  advances.\n","## Overview\n\nYi (01.AI, founded by Kai-Fu Lee) is a bilingual open-model family with\nparticularly strong Chinese-English performance — the Yi models debuted with\nimpressive benchmark scores in their size classes and a focus on high-quality\nbilingual training. Available in multiple sizes including long-context\nvariants, Yi serves builders needing strong Chinese language capability in an\nopen model.\n\nFor builders, Yi's place is in the bilingual open-model evaluation set: if\nyour application serves Chinese-speaking users, Yi deserves benchmarking\nalongside Qwen, DeepSeek, and other bilingual families. The models run on\nstandard stacks and are hosted by inference providers.\n\nThe practical stance: evaluate Yi where bilingual quality matters. Include it\nin the comparison set; let your evals decide.\n\n## When to use\n\n- Bilingual Chinese-English applications needing strong Chinese quality.\n- Open-model evaluations for Chinese-language tasks.\n- Long-context bilingual document processing (Yi's long-context variants).\n- Fine-tuning bilingual base models.\n- Self-hosting capable bilingual open models.\n- Diversifying beyond the most common open families.\n\n## Core concepts\n\n- **Bilingual training focus**: strong Chinese and English from the training\n  mix. For Chinese-language products, this is the relevant axis — test it\n  directly.\n- **Size options**: multiple sizes across releases. Benchmark the ladder to\n  right-size for your task.\n- **Long-context variants**: extended-context versions for document-scale\n  bilingual work. Test long-context quality on your real documents.\n- **Open weights**: downloadable, self-hostable, fine-tunable. Check license\n  terms per release.\n- **Standard-stack compatibility**: runs on vLLM, TGI, llama.cpp, and\n  provider APIs. No special deployment requirements.\n- **Instruction-tuned variants**: chat-tuned versions for assistants and\n  dialogue.\n- **Vision extensions**: multimodal Yi variants for image+text bilingual\n  tasks — evaluate against alternatives on your images.\n- **Release cadence**: the family evolves; track new releases and re-benchmark\n  deliberately.\n\n## Practical workflow\n\n1. **Define bilingual requirements.** Which tasks in Chinese, which in English,\n   which mixed? The eval set should reflect the real language mix.\n2. **Benchmark against bilingual peers.** Yi vs. Qwen, DeepSeek, and others on\n   your bilingual eval set. Per-language scores, not just aggregates.\n3. **Test long-context if relevant.** Your longest real bilingual documents;\n   questions spanning the input.\n4. **Right-size via the ladder.** Smallest adequate size for your quality bar.\n5. **Check licensing.** Verify terms per release for your use case.\n6. **Evaluate deployment.** API for speed; self-hosted for volume economics.\n7. **Pin versions; track releases.** Production pins; deliberate re-evaluation\n   on new releases.\n\nChecklist for Yi in production:\n- Bilingual eval set reflecting your real language mix.\n- Benchmarked against bilingual peer models.\n- Long-context validated on real documents (if used).\n- License verified; version pinned.\n- Deployment economics modeled.\n\n## Common pitfalls\n\n- **Aggregate-score blindness.** A good average hiding weak Chinese (or\n  English). Score per language.\n- **Ignoring bilingual peers.** Evaluating Yi alone instead of against Qwen,\n  DeepSeek, and others. The decision is relative.\n- **Long-context assumed.** Extended window without testing quality over long\n  bilingual inputs.\n- **License not verified.** Assuming terms across releases.\n- **Wrong size.** Not ladder-testing; over- or under-provisioning.\n- ** monolingual evals for bilingual products.** Testing only English for a\n  Chinese-serving product (or vice versa).\n- **Version drift.** Floating references updating underneath production.\n- **Static choice.** Not re-evaluating as the bilingual open-model field\n  advances.\n",{"name":5,"category":24,"description":7},"ai-research","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-yi-guide",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 yi-guide",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill yi-guide",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill yi-guide","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-yi-guide\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",[],[]]