[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EMKG2HH8MCSBHZ9RP64T2D":3,"skill-same:01M7EMKG2HH8MCSBHZ9RP64T2D":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},"01M7EMKG2HH8MCSBHZ9RP64T2D","code-llama-guide",null,"Build with Meta's Code Llama — open code models for generation, infilling, and long-context code tasks.","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-code-llama-guide\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: code-llama-guide\ndescription: Build with Meta's Code Llama — open code models for generation, infilling, and long-context code tasks.\ncategory: ai-research\n---\n\n## Overview\n\nCode Llama (Meta) is the code-specialized derivative of Llama — open-weight\nmodels for code generation, completion, infilling, and instruction-following\ncode assistance, in sizes from 7B to 70B (plus a long-context variant). As a\nLlama derivative, it inherits the ecosystem advantages: every provider hosts\nit, tooling targets it, and deployment is frictionless.\n\nFor builders, Code Llama is the default open code model — the safe choice with\nmaximum support. It may not top every code benchmark against newer specialized\nmodels (DeepSeek Coder, Qwen-Coder), but its combination of solid quality,\nbroad availability, and the Llama fine-tuning ecosystem makes it the baseline\nagainst which open code models are judged.\n\nThe practical stance: start open-code evaluations with Code Llama as the\nbaseline; adopt alternatives when they beat it on your tasks.\n\n## When to use\n\n- Default open code model when you want maximum ecosystem support.\n- Code completion and infilling (FIM support).\n- Long-context code tasks (the long-context variant for repo-scale work).\n- Code assistants and chat-based programming help (instruction-tuned).\n- Fine-tuning code models (the Llama code ecosystem is mature).\n- Python-heavy workloads (plus strong multi-language coverage).\n\n## Core concepts\n\n- **Size range (7B–70B)**: ladder from fast completion models to capable\n  reasoning models. Match size to task: 7B\u002F13B for completion, larger for\n  complex generation.\n- **Variants**: base (completion), Python-specialized, and instruct\n  (chat\u002Fassistant). Choose per use case — don't use instruct for pure\n  completion or base for chat.\n- **Fill-in-the-middle**: infilling support for IDE completion. Test on your\n  code patterns.\n- **Long-context variant**: extended context for repository-level tasks.\n  Validate on real repos.\n- **Llama ecosystem**: providers, quantization, fine-tuning tools — the\n  operational advantages of the standard.\n- **Instruction tuning**: the instruct variants for assistant behavior;\n  evaluate multi-turn code dialogue quality.\n- **Multi-language**: strong across popular languages; per-language testing\n  on your stack.\n- **License**: the Llama community license terms — read for your scale and\n  use case.\n\n## Practical workflow\n\n1. **Set Code Llama as the baseline.** Benchmark it first on your code tasks;\n   alternatives must beat it to displace it.\n2. **Match variant to use case.** Completion → base\u002FFIM; assistant → instruct;\n   repo tasks → long-context variant. Test each on its intended job.\n3. **Ladder-test sizes.** 7B vs. 13B vs. 34B vs. 70B on your tasks. Completion\n   often works at small sizes; complex generation needs larger.\n4. **Test your languages.** Your stack's languages, your frameworks, your\n   idioms — not just Python benchmarks.\n5. **Evaluate infilling.** For IDE use: prefix\u002Fsuffix completion on your\n   codebase.\n6. **Check the license.** Community license terms for your deployment scale.\n7. **Monitor in production.** Acceptance rates for completion; task success\n   for generation. Offline benchmarks don't capture the full picture.\n\nChecklist for Code Llama in production:\n- Baselined against alternatives; displacement justified by measurement.\n- Correct variant per use case.\n- Size right-sized via ladder testing.\n- Your languages tested on your code.\n- License confirmed; production quality monitored.\n\n## Common pitfalls\n\n- **Baseline skipped.** Adopting a newer code model without checking whether\n  it actually beats Code Llama on your tasks.\n- **Variant mismatch.** Instruct model for completion (worse + slower) or\n  base model for chat (unhelpful). Match variant to job.\n- **Oversizing.** 70B for simple completion. Right-size per task.\n- **Python-only evals.** Assuming multi-language quality from Python scores.\n  Test your languages.\n- **FIM untested.** Completion deployment without infilling evaluation.\n- **Long-context assumed.** The variant exists; your repo tasks still need\n  testing.\n- **License blindness.** Not reading the community license terms.\n- **No production metrics.** Offline benchmarks without acceptance-rate\n  tracking in the real tool.\n","## Overview\n\nCode Llama (Meta) is the code-specialized derivative of Llama — open-weight\nmodels for code generation, completion, infilling, and instruction-following\ncode assistance, in sizes from 7B to 70B (plus a long-context variant). As a\nLlama derivative, it inherits the ecosystem advantages: every provider hosts\nit, tooling targets it, and deployment is frictionless.\n\nFor builders, Code Llama is the default open code model — the safe choice with\nmaximum support. It may not top every code benchmark against newer specialized\nmodels (DeepSeek Coder, Qwen-Coder), but its combination of solid quality,\nbroad availability, and the Llama fine-tuning ecosystem makes it the baseline\nagainst which open code models are judged.\n\nThe practical stance: start open-code evaluations with Code Llama as the\nbaseline; adopt alternatives when they beat it on your tasks.\n\n## When to use\n\n- Default open code model when you want maximum ecosystem support.\n- Code completion and infilling (FIM support).\n- Long-context code tasks (the long-context variant for repo-scale work).\n- Code assistants and chat-based programming help (instruction-tuned).\n- Fine-tuning code models (the Llama code ecosystem is mature).\n- Python-heavy workloads (plus strong multi-language coverage).\n\n## Core concepts\n\n- **Size range (7B–70B)**: ladder from fast completion models to capable\n  reasoning models. Match size to task: 7B\u002F13B for completion, larger for\n  complex generation.\n- **Variants**: base (completion), Python-specialized, and instruct\n  (chat\u002Fassistant). Choose per use case — don't use instruct for pure\n  completion or base for chat.\n- **Fill-in-the-middle**: infilling support for IDE completion. Test on your\n  code patterns.\n- **Long-context variant**: extended context for repository-level tasks.\n  Validate on real repos.\n- **Llama ecosystem**: providers, quantization, fine-tuning tools — the\n  operational advantages of the standard.\n- **Instruction tuning**: the instruct variants for assistant behavior;\n  evaluate multi-turn code dialogue quality.\n- **Multi-language**: strong across popular languages; per-language testing\n  on your stack.\n- **License**: the Llama community license terms — read for your scale and\n  use case.\n\n## Practical workflow\n\n1. **Set Code Llama as the baseline.** Benchmark it first on your code tasks;\n   alternatives must beat it to displace it.\n2. **Match variant to use case.** Completion → base\u002FFIM; assistant → instruct;\n   repo tasks → long-context variant. Test each on its intended job.\n3. **Ladder-test sizes.** 7B vs. 13B vs. 34B vs. 70B on your tasks. Completion\n   often works at small sizes; complex generation needs larger.\n4. **Test your languages.** Your stack's languages, your frameworks, your\n   idioms — not just Python benchmarks.\n5. **Evaluate infilling.** For IDE use: prefix\u002Fsuffix completion on your\n   codebase.\n6. **Check the license.** Community license terms for your deployment scale.\n7. **Monitor in production.** Acceptance rates for completion; task success\n   for generation. Offline benchmarks don't capture the full picture.\n\nChecklist for Code Llama in production:\n- Baselined against alternatives; displacement justified by measurement.\n- Correct variant per use case.\n- Size right-sized via ladder testing.\n- Your languages tested on your code.\n- License confirmed; production quality monitored.\n\n## Common pitfalls\n\n- **Baseline skipped.** Adopting a newer code model without checking whether\n  it actually beats Code Llama on your tasks.\n- **Variant mismatch.** Instruct model for completion (worse + slower) or\n  base model for chat (unhelpful). Match variant to job.\n- **Oversizing.** 70B for simple completion. Right-size per task.\n- **Python-only evals.** Assuming multi-language quality from Python scores.\n  Test your languages.\n- **FIM untested.** Completion deployment without infilling evaluation.\n- **Long-context assumed.** The variant exists; your repo tasks still need\n  testing.\n- **License blindness.** Not reading the community license terms.\n- **No production metrics.** Offline benchmarks without acceptance-rate\n  tracking in the real tool.\n",{"name":5,"category":24,"description":7},"ai-research","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-code-llama-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 code-llama-guide",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill code-llama-guide",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill code-llama-guide","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-code-llama-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",[],[]]