[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EMKS7BQ0K4AXCMNBCXDHJ5":3,"skill-same:01M7EMKS7BQ0K4AXCMNBCXDHJ5":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},"01M7EMKS7BQ0K4AXCMNBCXDHJ5","codestral-guide",null,"Build with Mistral's Codestral code models — efficient open code generation with fill-in-the-middle.","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-codestral-guide\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: codestral-guide\ndescription: Build with Mistral's Codestral code models — efficient open code generation with fill-in-the-middle.\ncategory: ai-research\n---\n\n## Overview\n\nCodestral (Mistral AI) is a code-specialized open model emphasizing efficiency\n— strong code generation and completion at a size that's cheap to serve,\nwith fill-in-the-middle support for IDE-style infilling. It carries Mistral's\nefficiency DNA into code: the pitch is capable code AI without large-model\nserving costs.\n\nFor builders, Codestral fits the efficient-code-model niche: code completion\nin editors, cost-sensitive code generation, and applications where a focused\ncode model beats a generalist on price\u002Fperformance. It also inherits Mistral's\nopen-weights approach — API via La Plateforme or self-hosted.\n\nThe practical stance: evaluate Codestral where serving efficiency matters for\ncode tasks. Benchmark against other efficient code models (small Qwen-Coder,\nsmall DeepSeek Coder, Code Llama small) on your tasks.\n\n## When to use\n\n- Efficient code completion (IDE copilots, editor integrations).\n- Cost-sensitive code generation at scale.\n- Fill-in-the-middle infilling workflows.\n- Multilingual code tasks (Mistral's language strength extends to code\n  contexts).\n- Self-hosting efficient code models.\n- API-based code generation via La Plateforme.\n\n## Core concepts\n\n- **Efficiency focus**: capable code performance at serving-friendly sizes.\n  The value is price\u002Fperformance — verify on your tasks.\n- **Fill-in-the-middle**: infilling for completion. Test on your code\n  patterns.\n- **Mistral efficiency DNA**: the architectural and training efficiency\n  approach applied to code.\n- **Open weights**: self-hostable; check licensing per release.\n- **La Plateforme API**: managed API option — evaluate vs. self-hosting on\n  economics.\n- **Multilingual**: 80+ programming languages claimed — test yours\n  specifically.\n- **Instruction following**: tuned for code assistance interactions.\n- **Size appropriateness**: the model is sized for efficiency; match task\n  difficulty honestly — hard reasoning tasks may need larger models.\n\n## Practical workflow\n\n1. **Benchmark efficiency peers.** Codestral vs. small Qwen-Coder, small\n   DeepSeek Coder, small Code Llama — on your code tasks, measuring quality\n   and serving cost.\n2. **Test completion specifically.** If IDE completion is the use case: FIM\n   quality, latency, and acceptance-relevant metrics on your codebase.\n3. **Test your languages.** Per-language evaluation on your stack's languages.\n4. **Compare API vs. self-host.** La Plateforme pricing against self-hosted\n   serving costs at your volume.\n5. **Check task difficulty fit.** Ensure the model's capacity matches your\n   hardest tasks — efficiency doesn't help if quality falls short.\n6. **Verify licensing.** Per-release terms for your use case.\n7. **Monitor acceptance.** Production code completion lives on acceptance\n   rates — track them.\n\nChecklist for Codestral in production:\n- Benchmarked against efficient code-model peers on your tasks.\n- FIM completion quality validated for IDE use.\n- Your languages tested specifically.\n- API-vs-self-host economics modeled.\n- Task difficulty matched to model capacity; acceptance monitored.\n\n## Common pitfalls\n\n- **Efficiency without quality bar.** Choosing the efficient option before\n  confirming it clears your quality threshold.\n- **Peer comparison skipped.** Not benchmarking against small Qwen-Coder and\n  DeepSeek Coder — the relevant competitors.\n- **FIM untested.** Completion use without infilling evaluation.\n- **Language claims accepted.** \"80+ languages\" needs per-language testing\n  on yours.\n- **Difficulty mismatch.** Efficient models for tasks needing heavy reasoning.\n  Match honestly.\n- **API-vs-self-host not modeled.** Defaulting without economics.\n- **License unchecked.** Per-release verification.\n- **No acceptance tracking.** Offline benchmarks without production\n  acceptance-rate monitoring.\n","## Overview\n\nCodestral (Mistral AI) is a code-specialized open model emphasizing efficiency\n— strong code generation and completion at a size that's cheap to serve,\nwith fill-in-the-middle support for IDE-style infilling. It carries Mistral's\nefficiency DNA into code: the pitch is capable code AI without large-model\nserving costs.\n\nFor builders, Codestral fits the efficient-code-model niche: code completion\nin editors, cost-sensitive code generation, and applications where a focused\ncode model beats a generalist on price\u002Fperformance. It also inherits Mistral's\nopen-weights approach — API via La Plateforme or self-hosted.\n\nThe practical stance: evaluate Codestral where serving efficiency matters for\ncode tasks. Benchmark against other efficient code models (small Qwen-Coder,\nsmall DeepSeek Coder, Code Llama small) on your tasks.\n\n## When to use\n\n- Efficient code completion (IDE copilots, editor integrations).\n- Cost-sensitive code generation at scale.\n- Fill-in-the-middle infilling workflows.\n- Multilingual code tasks (Mistral's language strength extends to code\n  contexts).\n- Self-hosting efficient code models.\n- API-based code generation via La Plateforme.\n\n## Core concepts\n\n- **Efficiency focus**: capable code performance at serving-friendly sizes.\n  The value is price\u002Fperformance — verify on your tasks.\n- **Fill-in-the-middle**: infilling for completion. Test on your code\n  patterns.\n- **Mistral efficiency DNA**: the architectural and training efficiency\n  approach applied to code.\n- **Open weights**: self-hostable; check licensing per release.\n- **La Plateforme API**: managed API option — evaluate vs. self-hosting on\n  economics.\n- **Multilingual**: 80+ programming languages claimed — test yours\n  specifically.\n- **Instruction following**: tuned for code assistance interactions.\n- **Size appropriateness**: the model is sized for efficiency; match task\n  difficulty honestly — hard reasoning tasks may need larger models.\n\n## Practical workflow\n\n1. **Benchmark efficiency peers.** Codestral vs. small Qwen-Coder, small\n   DeepSeek Coder, small Code Llama — on your code tasks, measuring quality\n   and serving cost.\n2. **Test completion specifically.** If IDE completion is the use case: FIM\n   quality, latency, and acceptance-relevant metrics on your codebase.\n3. **Test your languages.** Per-language evaluation on your stack's languages.\n4. **Compare API vs. self-host.** La Plateforme pricing against self-hosted\n   serving costs at your volume.\n5. **Check task difficulty fit.** Ensure the model's capacity matches your\n   hardest tasks — efficiency doesn't help if quality falls short.\n6. **Verify licensing.** Per-release terms for your use case.\n7. **Monitor acceptance.** Production code completion lives on acceptance\n   rates — track them.\n\nChecklist for Codestral in production:\n- Benchmarked against efficient code-model peers on your tasks.\n- FIM completion quality validated for IDE use.\n- Your languages tested specifically.\n- API-vs-self-host economics modeled.\n- Task difficulty matched to model capacity; acceptance monitored.\n\n## Common pitfalls\n\n- **Efficiency without quality bar.** Choosing the efficient option before\n  confirming it clears your quality threshold.\n- **Peer comparison skipped.** Not benchmarking against small Qwen-Coder and\n  DeepSeek Coder — the relevant competitors.\n- **FIM untested.** Completion use without infilling evaluation.\n- **Language claims accepted.** \"80+ languages\" needs per-language testing\n  on yours.\n- **Difficulty mismatch.** Efficient models for tasks needing heavy reasoning.\n  Match honestly.\n- **API-vs-self-host not modeled.** Defaulting without economics.\n- **License unchecked.** Per-release verification.\n- **No acceptance tracking.** Offline benchmarks without production\n  acceptance-rate monitoring.\n",{"name":5,"category":24,"description":7},"ai-research","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-codestral-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 codestral-guide",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill codestral-guide",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill codestral-guide","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-codestral-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",[],[]]