[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EVM4QJAAX0ZPKAJ5DZ3ZQP":3,"skill-same:01M7EVM4QJAAX0ZPKAJ5DZ3ZQP":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},"01M7EVM4QJAAX0ZPKAJ5DZ3ZQP","qwen-coder",null,"Build with Qwen's code models — strong open code generation, completion, and agentic coding capabilities.","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-qwen-coder\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: qwen-coder\ndescription: Build with Qwen's code models — strong open code generation, completion, and agentic coding capabilities.\ncategory: ai-research\n---\n\n## Overview\n\nQwen-Coder (Qwen2.5-Coder and successors) is Alibaba's code-specialized open\nmodel family — among the strongest open code models available, with particular\nstrength in agentic coding workflows (the models are tuned for tool use and\nmulti-step coding tasks). Available across sizes, Qwen-Coder competes at the\ntop of open code benchmarks alongside DeepSeek Coder.\n\nFor builders, Qwen-Coder's distinctive note is agentic coding: these models\nare designed not just for single-shot generation but for the iterative,\ntool-using loops of modern coding agents. If you're building coding agents on\nopen models, Qwen-Coder belongs at the top of your evaluation list.\n\nThe practical stance: for open code models, the frontrunners are DeepSeek\nCoder and Qwen-Coder — benchmark both on your tasks, including agentic\nworkflows.\n\n## When to use\n\n- Agentic coding workflows: tool-using coding agents on open models.\n- Open code generation at high quality.\n- Code completion and infilling.\n- Multi-language code tasks.\n- Fine-tuning open code models.\n- Cost-efficient code inference at scale.\n\n## Core concepts\n\n- **Agentic tuning**: optimized for multi-step tool-using coding workflows —\n  not just generation. Evaluate in agent loops, not just single-shot\n  benchmarks.\n- **Size range**: from small completion models to large reasoning models.\n  Ladder-test per task.\n- **Code benchmarks leadership**: top-tier open code performance. Verify on\n  your tasks — leadership is general, your needs are specific.\n- **Multi-language**: strong across languages; test yours.\n- **Fill-in-the-middle**: completion support; test on your patterns.\n- **Long context**: repo-scale understanding; validate on real repositories.\n- **Open weights**: self-hostable, fine-tunable; check licensing per release.\n- **Qwen ecosystem**: the broader Qwen tooling and provider support.\n\n## Practical workflow\n\n1. **Benchmark single-shot generation.** Your code tasks: Qwen-Coder vs.\n   DeepSeek Coder vs. Code Llama. Your languages, your difficulty.\n2. **Evaluate agentic workflows.** This is the differentiator — run\n   Qwen-Coder in your agent loop (file tools, test execution) and measure\n   task completion, not just code quality.\n3. **Test tool use specifically.** Function calling accuracy with your coding\n   tools — agentic coding lives or dies here.\n4. **Ladder-test sizes.** Completion vs. generation vs. agentic reasoning may\n   want different sizes.\n5. **Test your languages and repos.** Real codebases, real tasks.\n6. **Check licensing.** Per-release terms.\n7. **Monitor agentic metrics.** Task completion rates, tool-use accuracy, and\n   iteration counts in production — not just offline benchmarks.\n\nChecklist for Qwen-Coder in production:\n- Benchmarked against DeepSeek Coder and Code Llama on your tasks.\n- Agentic workflow performance measured (task completion, not just code).\n- Tool-use accuracy validated with your tools.\n- Sizes right-sized per task type.\n- License verified; agentic metrics monitored.\n\n## Common pitfalls\n\n- **Single-shot-only evals.** Missing the agentic differentiation by testing\n  only one-shot generation. Test in agent loops.\n- **Tool-use untested.** Assuming function calling works with your tools.\n  Measure it.\n- **Peer comparison skipped.** Not benchmarking against DeepSeek Coder.\n  The frontrunner comparison is mandatory.\n- **Language assumptions.** Strong multilingual claims need per-language\n  verification on your stack.\n- **Wrong size per task.** One size for completion, generation, and agentic\n  reasoning. Right-size each.\n- **Repo context untested.** Long windows without real-repository validation.\n- **License unchecked.** Per-release verification.\n- **Offline-only metrics.** Production agentic coding needs completion-rate\n  and tool-accuracy monitoring, not just benchmark scores.\n","## Overview\n\nQwen-Coder (Qwen2.5-Coder and successors) is Alibaba's code-specialized open\nmodel family — among the strongest open code models available, with particular\nstrength in agentic coding workflows (the models are tuned for tool use and\nmulti-step coding tasks). Available across sizes, Qwen-Coder competes at the\ntop of open code benchmarks alongside DeepSeek Coder.\n\nFor builders, Qwen-Coder's distinctive note is agentic coding: these models\nare designed not just for single-shot generation but for the iterative,\ntool-using loops of modern coding agents. If you're building coding agents on\nopen models, Qwen-Coder belongs at the top of your evaluation list.\n\nThe practical stance: for open code models, the frontrunners are DeepSeek\nCoder and Qwen-Coder — benchmark both on your tasks, including agentic\nworkflows.\n\n## When to use\n\n- Agentic coding workflows: tool-using coding agents on open models.\n- Open code generation at high quality.\n- Code completion and infilling.\n- Multi-language code tasks.\n- Fine-tuning open code models.\n- Cost-efficient code inference at scale.\n\n## Core concepts\n\n- **Agentic tuning**: optimized for multi-step tool-using coding workflows —\n  not just generation. Evaluate in agent loops, not just single-shot\n  benchmarks.\n- **Size range**: from small completion models to large reasoning models.\n  Ladder-test per task.\n- **Code benchmarks leadership**: top-tier open code performance. Verify on\n  your tasks — leadership is general, your needs are specific.\n- **Multi-language**: strong across languages; test yours.\n- **Fill-in-the-middle**: completion support; test on your patterns.\n- **Long context**: repo-scale understanding; validate on real repositories.\n- **Open weights**: self-hostable, fine-tunable; check licensing per release.\n- **Qwen ecosystem**: the broader Qwen tooling and provider support.\n\n## Practical workflow\n\n1. **Benchmark single-shot generation.** Your code tasks: Qwen-Coder vs.\n   DeepSeek Coder vs. Code Llama. Your languages, your difficulty.\n2. **Evaluate agentic workflows.** This is the differentiator — run\n   Qwen-Coder in your agent loop (file tools, test execution) and measure\n   task completion, not just code quality.\n3. **Test tool use specifically.** Function calling accuracy with your coding\n   tools — agentic coding lives or dies here.\n4. **Ladder-test sizes.** Completion vs. generation vs. agentic reasoning may\n   want different sizes.\n5. **Test your languages and repos.** Real codebases, real tasks.\n6. **Check licensing.** Per-release terms.\n7. **Monitor agentic metrics.** Task completion rates, tool-use accuracy, and\n   iteration counts in production — not just offline benchmarks.\n\nChecklist for Qwen-Coder in production:\n- Benchmarked against DeepSeek Coder and Code Llama on your tasks.\n- Agentic workflow performance measured (task completion, not just code).\n- Tool-use accuracy validated with your tools.\n- Sizes right-sized per task type.\n- License verified; agentic metrics monitored.\n\n## Common pitfalls\n\n- **Single-shot-only evals.** Missing the agentic differentiation by testing\n  only one-shot generation. Test in agent loops.\n- **Tool-use untested.** Assuming function calling works with your tools.\n  Measure it.\n- **Peer comparison skipped.** Not benchmarking against DeepSeek Coder.\n  The frontrunner comparison is mandatory.\n- **Language assumptions.** Strong multilingual claims need per-language\n  verification on your stack.\n- **Wrong size per task.** One size for completion, generation, and agentic\n  reasoning. Right-size each.\n- **Repo context untested.** Long windows without real-repository validation.\n- **License unchecked.** Per-release verification.\n- **Offline-only metrics.** Production agentic coding needs completion-rate\n  and tool-accuracy monitoring, not just benchmark scores.\n",{"name":5,"category":24,"description":7},"ai-research","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-qwen-coder",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 qwen-coder",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill qwen-coder",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill qwen-coder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-qwen-coder\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",[],[]]