[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EVYM4XTM8SVFNG30QJ18ZB":3,"skill-same:01M7EVYM4XTM8SVFNG30QJ18ZB":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},"01M7EVYM4XTM8SVFNG30QJ18ZB","skywork-guide",null,"Build with Skywork's open models — efficient bilingual models with practical deployment sizing.","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-skywork-guide\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skywork-guide\ndescription: Build with Skywork's open models — efficient bilingual models with practical deployment sizing.\ncategory: ai-research\n---\n\n## Overview\n\nSkywork (Kunlun Tech) releases open bilingual models positioned for practical\ndeployment — efficient sizes, bilingual Chinese-English capability, and a\nfocus on models that are actually deployable rather than maximally large.\nThe positioning is pragmatic: good capability at sizes teams can afford to\nrun.\n\nFor builders, Skywork is a candidate in efficient bilingual evaluations —\nparticularly when deployment economics matter and you want options beyond the\nmost-discussed families. As always with lesser-known families: benchmark on\nyour tasks; don't rely on reputation (in either direction).\n\nThe practical stance: include Skywork when you're surveying efficient\nbilingual options. The evaluation is cheap; the information is valuable.\n\n## When to use\n\n- Efficient bilingual deployment where model size affects economics.\n- Broad bilingual open-model surveys (don't skip lesser-known families).\n- Cost-sensitive Chinese-English applications.\n- Fine-tuning efficient bilingual bases.\n- Self-hosting where smaller capable models win.\n\n## Core concepts\n\n- **Efficiency positioning**: models sized for practical deployment. Test\n  whether the efficiency claims hold on your tasks.\n- **Bilingual capability**: Chinese-English. Per-language evals.\n- **Deployment-friendly sizes**: the practical focus — validate serving\n  costs at your volume.\n- **Open weights**: downloadable; verify licensing per release.\n- **Standard stacks**: common inference frameworks and provider APIs —\n  verify hosting for specific releases.\n- **Reasoning variants**: check for specialized versions (math, reasoning)\n  matching your tasks.\n- **Release tracking**: newer families evolve quickly; evaluate current\n  releases, not first impressions.\n- **Peer context**: the value is relative — always benchmark against known\n  alternatives.\n\n## Practical workflow\n\n1. **Survey current releases.** Identify the current recommended models and\n   variants.\n2. **Benchmark against efficient peers.** Skywork vs. Qwen small, Gemma,\n   Phi, Llama small — on your bilingual eval set.\n3. **Validate efficiency claims.** Measure actual serving cost\u002Flatency at\n   your volume vs. alternatives.\n4. **Test your languages.** Per-language quality on your real tasks.\n5. **Check licensing and hosting.** Terms per release; provider availability\n   for your deployment plan.\n6. **Right-size.** Ladder-test within the family.\n7. **Pin and revisit.** Version pins; re-survey as the family evolves.\n\nChecklist for Skywork in production:\n- Current releases identified and benchmarked vs. efficient peers.\n- Serving economics validated at your volume.\n- Per-language quality confirmed.\n- License verified; hosting confirmed.\n- Re-evaluation cadence set.\n\n## Common pitfalls\n\n- **Reputation-based dismissal.** Skipping lesser-known families without\n  testing. Benchmarks are cheap; blind spots are expensive.\n- **Reputation-based adoption.** The reverse — adopting on marketing without\n  peer comparison.\n- **Efficiency assumed.** \"Efficient\" positioning without measuring your\n  serving costs vs. alternatives.\n- **Stale evaluation.** Judging the family by early releases.\n- **No peer benchmarks.** Evaluating in isolation.\n- **License\u002Fhosting unchecked.** Assuming availability and terms.\n- **Single-language testing.** For bilingual use, test both.\n- **Static decision.** Not re-surveying as efficient-model options evolve.\n","## Overview\n\nSkywork (Kunlun Tech) releases open bilingual models positioned for practical\ndeployment — efficient sizes, bilingual Chinese-English capability, and a\nfocus on models that are actually deployable rather than maximally large.\nThe positioning is pragmatic: good capability at sizes teams can afford to\nrun.\n\nFor builders, Skywork is a candidate in efficient bilingual evaluations —\nparticularly when deployment economics matter and you want options beyond the\nmost-discussed families. As always with lesser-known families: benchmark on\nyour tasks; don't rely on reputation (in either direction).\n\nThe practical stance: include Skywork when you're surveying efficient\nbilingual options. The evaluation is cheap; the information is valuable.\n\n## When to use\n\n- Efficient bilingual deployment where model size affects economics.\n- Broad bilingual open-model surveys (don't skip lesser-known families).\n- Cost-sensitive Chinese-English applications.\n- Fine-tuning efficient bilingual bases.\n- Self-hosting where smaller capable models win.\n\n## Core concepts\n\n- **Efficiency positioning**: models sized for practical deployment. Test\n  whether the efficiency claims hold on your tasks.\n- **Bilingual capability**: Chinese-English. Per-language evals.\n- **Deployment-friendly sizes**: the practical focus — validate serving\n  costs at your volume.\n- **Open weights**: downloadable; verify licensing per release.\n- **Standard stacks**: common inference frameworks and provider APIs —\n  verify hosting for specific releases.\n- **Reasoning variants**: check for specialized versions (math, reasoning)\n  matching your tasks.\n- **Release tracking**: newer families evolve quickly; evaluate current\n  releases, not first impressions.\n- **Peer context**: the value is relative — always benchmark against known\n  alternatives.\n\n## Practical workflow\n\n1. **Survey current releases.** Identify the current recommended models and\n   variants.\n2. **Benchmark against efficient peers.** Skywork vs. Qwen small, Gemma,\n   Phi, Llama small — on your bilingual eval set.\n3. **Validate efficiency claims.** Measure actual serving cost\u002Flatency at\n   your volume vs. alternatives.\n4. **Test your languages.** Per-language quality on your real tasks.\n5. **Check licensing and hosting.** Terms per release; provider availability\n   for your deployment plan.\n6. **Right-size.** Ladder-test within the family.\n7. **Pin and revisit.** Version pins; re-survey as the family evolves.\n\nChecklist for Skywork in production:\n- Current releases identified and benchmarked vs. efficient peers.\n- Serving economics validated at your volume.\n- Per-language quality confirmed.\n- License verified; hosting confirmed.\n- Re-evaluation cadence set.\n\n## Common pitfalls\n\n- **Reputation-based dismissal.** Skipping lesser-known families without\n  testing. Benchmarks are cheap; blind spots are expensive.\n- **Reputation-based adoption.** The reverse — adopting on marketing without\n  peer comparison.\n- **Efficiency assumed.** \"Efficient\" positioning without measuring your\n  serving costs vs. alternatives.\n- **Stale evaluation.** Judging the family by early releases.\n- **No peer benchmarks.** Evaluating in isolation.\n- **License\u002Fhosting unchecked.** Assuming availability and terms.\n- **Single-language testing.** For bilingual use, test both.\n- **Static decision.** Not re-surveying as efficient-model options evolve.\n",{"name":5,"category":24,"description":7},"ai-research","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-skywork-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 skywork-guide",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill skywork-guide",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill skywork-guide","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-skywork-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",[],[]]