[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6H6C65SHQDEMJAJQZF2VKFK":3,"skill-same:01M6H6C65SHQDEMJAJQZF2VKFK":66},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":6,"updatedAt":51,"install":52,"resources":65},"01M6H6C65SHQDEMJAJQZF2VKFK","domain-ml",null,"Use when building ML\u002FAI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning, training, prediction, ndarray, tch-rs, burn, candle, 机器学习, 人工智能, 模型推理","0xharryriddle\u002Fcodex-field-kit","0xharryriddle","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F100945007?v=4","01M6H686JV0QKZYP2RWG6B2B8T","harryriddle","01M6H686PVZ8JGKWEG7B3GM5PD",3,"MIT","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Farchive\u002Fupstream\u002Fchasebuild-agent-skills\u002Frust\u002Fskills\u002Fdomain-ml\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"ml","domain","domain ml","machine","inference","neural network","apps","false","burn","deep","Neural","use","model","learning","network","tensor","training","deep learning","machine learning","rust","2026-11-10 10:12:30",false,"---\nname: domain-ml\ndescription: \"Use when building ML\u002FAI apps in Rust. Keywords: machine learning, ML, AI, tensor, model, inference, neural network, deep learning, training, prediction, ndarray, tch-rs, burn, candle, 机器学习, 人工智能, 模型推理\"\nuser-invocable: false\n---\n\n# Machine Learning Domain\n\n> **Layer 3: Domain Constraints**\n\n## Domain Constraints → Design Implications\n\n| Domain Rule | Design Constraint | Rust Implication |\n|-------------|-------------------|------------------|\n| Large data | Efficient memory | Zero-copy, streaming |\n| GPU acceleration | CUDA\u002FMetal support | candle, tch-rs |\n| Model portability | Standard formats | ONNX |\n| Batch processing | Throughput over latency | Batched inference |\n| Numerical precision | Float handling | ndarray, careful f32\u002Ff64 |\n| Reproducibility | Deterministic | Seeded random, versioning |\n\n---\n\n## Critical Constraints\n\n### Memory Efficiency\n\n```\nRULE: Avoid copying large tensors\nWHY: Memory bandwidth is bottleneck\nRUST: References, views, in-place ops\n```\n\n### GPU Utilization\n\n```\nRULE: Batch operations for GPU efficiency\nWHY: GPU overhead per kernel launch\nRUST: Batch sizes, async data loading\n```\n\n### Model Portability\n\n```\nRULE: Use standard model formats\nWHY: Train in Python, deploy in Rust\nRUST: ONNX via tract or candle\n```\n\n---\n\n## Trace Down ↓\n\nFrom constraints to design (Layer 2):\n\n```\n\"Need efficient data pipelines\"\n    ↓ m10-performance: Streaming, batching\n    ↓ polars: Lazy evaluation\n\n\"Need GPU inference\"\n    ↓ m07-concurrency: Async data loading\n    ↓ candle\u002Ftch-rs: CUDA backend\n\n\"Need model loading\"\n    ↓ m12-lifecycle: Lazy init, caching\n    ↓ tract: ONNX runtime\n```\n\n---\n\n## Use Case → Framework\n\n| Use Case | Recommended | Why |\n|----------|-------------|-----|\n| Inference only | tract (ONNX) | Lightweight, portable |\n| Training + inference | candle, burn | Pure Rust, GPU |\n| PyTorch models | tch-rs | Direct bindings |\n| Data pipelines | polars | Fast, lazy eval |\n\n## Key Crates\n\n| Purpose | Crate |\n|---------|-------|\n| Tensors | ndarray |\n| ONNX inference | tract |\n| ML framework | candle, burn |\n| PyTorch bindings | tch-rs |\n| Data processing | polars |\n| Embeddings | fastembed |\n\n## Design Patterns\n\n| Pattern | Purpose | Implementation |\n|---------|---------|----------------|\n| Model loading | Once, reuse | `OnceLock\u003CModel>` |\n| Batching | Throughput | Collect then process |\n| Streaming | Large data | Iterator-based |\n| GPU async | Parallelism | Data loading parallel to compute |\n\n## Code Pattern: Inference Server\n\n```rust\nuse std::sync::OnceLock;\nuse tract_onnx::prelude::*;\n\nstatic MODEL: OnceLock\u003CSimplePlan\u003CTypedFact, Box\u003Cdyn TypedOp>, Graph\u003CTypedFact, Box\u003Cdyn TypedOp>>>> = OnceLock::new();\n\nfn get_model() -> &'static SimplePlan\u003C...> {\n    MODEL.get_or_init(|| {\n        tract_onnx::onnx()\n            .model_for_path(\"model.onnx\")\n            .unwrap()\n            .into_optimized()\n            .unwrap()\n            .into_runnable()\n            .unwrap()\n    })\n}\n\nasync fn predict(input: Vec\u003Cf32>) -> anyhow::Result\u003CVec\u003Cf32>> {\n    let model = get_model();\n    let input = tract_ndarray::arr1(&input).into_shape((1, input.len()))?;\n    let result = model.run(tvec!(input.into()))?;\n    Ok(result[0].to_array_view::\u003Cf32>()?.iter().copied().collect())\n}\n```\n\n## Code Pattern: Batched Inference\n\n```rust\nasync fn batch_predict(inputs: Vec\u003CVec\u003Cf32>>, batch_size: usize) -> Vec\u003CVec\u003Cf32>> {\n    let mut results = Vec::with_capacity(inputs.len());\n\n    for batch in inputs.chunks(batch_size) {\n        \u002F\u002F Stack inputs into batch tensor\n        let batch_tensor = stack_inputs(batch);\n\n        \u002F\u002F Run inference on batch\n        let batch_output = model.run(batch_tensor).await;\n\n        \u002F\u002F Unstack results\n        results.extend(unstack_outputs(batch_output));\n    }\n\n    results\n}\n```\n\n---\n\n## Common Mistakes\n\n| Mistake | Domain Violation | Fix |\n|---------|-----------------|-----|\n| Clone tensors | Memory waste | Use views |\n| Single inference | GPU underutilized | Batch processing |\n| Load model per request | Slow | Singleton pattern |\n| Sync data loading | GPU idle | Async pipeline |\n\n---\n\n## Trace to Layer 1\n\n| Constraint | Layer 2 Pattern | Layer 1 Implementation |\n|------------|-----------------|------------------------|\n| Memory efficiency | Zero-copy | ndarray views |\n| Model singleton | Lazy init | OnceLock\u003CModel> |\n| Batch processing | Chunked iteration | chunks() + parallel |\n| GPU async | Concurrent loading | tokio::spawn + GPU |\n\n---\n\n## Related Skills\n\n| When | See |\n|------|-----|\n| Performance | m10-performance |\n| Lazy initialization | m12-lifecycle |\n| Async patterns | m07-concurrency |\n| Memory efficiency | m01-ownership |\n","# Machine Learning Domain\n\n> **Layer 3: Domain Constraints**\n\n## Domain Constraints → Design Implications\n\n| Domain Rule | Design Constraint | Rust Implication |\n|-------------|-------------------|------------------|\n| Large data | Efficient memory | Zero-copy, streaming |\n| GPU acceleration | CUDA\u002FMetal support | candle, tch-rs |\n| Model portability | Standard formats | ONNX |\n| Batch processing | Throughput over latency | Batched inference |\n| Numerical precision | Float handling | ndarray, careful f32\u002Ff64 |\n| Reproducibility | Deterministic | Seeded random, versioning |\n\n---\n\n## Critical Constraints\n\n### Memory Efficiency\n\n```\nRULE: Avoid copying large tensors\nWHY: Memory bandwidth is bottleneck\nRUST: References, views, in-place ops\n```\n\n### GPU Utilization\n\n```\nRULE: Batch operations for GPU efficiency\nWHY: GPU overhead per kernel launch\nRUST: Batch sizes, async data loading\n```\n\n### Model Portability\n\n```\nRULE: Use standard model formats\nWHY: Train in Python, deploy in Rust\nRUST: ONNX via tract or candle\n```\n\n---\n\n## Trace Down ↓\n\nFrom constraints to design (Layer 2):\n\n```\n\"Need efficient data pipelines\"\n    ↓ m10-performance: Streaming, batching\n    ↓ polars: Lazy evaluation\n\n\"Need GPU inference\"\n    ↓ m07-concurrency: Async data loading\n    ↓ candle\u002Ftch-rs: CUDA backend\n\n\"Need model loading\"\n    ↓ m12-lifecycle: Lazy init, caching\n    ↓ tract: ONNX runtime\n```\n\n---\n\n## Use Case → Framework\n\n| Use Case | Recommended | Why |\n|----------|-------------|-----|\n| Inference only | tract (ONNX) | Lightweight, portable |\n| Training + inference | candle, burn | Pure Rust, GPU |\n| PyTorch models | tch-rs | Direct bindings |\n| Data pipelines | polars | Fast, lazy eval |\n\n## Key Crates\n\n| Purpose | Crate |\n|---------|-------|\n| Tensors | ndarray |\n| ONNX inference | tract |\n| ML framework | candle, burn |\n| PyTorch bindings | tch-rs |\n| Data processing | polars |\n| Embeddings | fastembed |\n\n## Design Patterns\n\n| Pattern | Purpose | Implementation |\n|---------|---------|----------------|\n| Model loading | Once, reuse | `OnceLock\u003CModel>` |\n| Batching | Throughput | Collect then process |\n| Streaming | Large data | Iterator-based |\n| GPU async | Parallelism | Data loading parallel to compute |\n\n## Code Pattern: Inference Server\n\n```rust\nuse std::sync::OnceLock;\nuse tract_onnx::prelude::*;\n\nstatic MODEL: OnceLock\u003CSimplePlan\u003CTypedFact, Box\u003Cdyn TypedOp>, Graph\u003CTypedFact, Box\u003Cdyn TypedOp>>>> = OnceLock::new();\n\nfn get_model() -> &'static SimplePlan\u003C...> {\n    MODEL.get_or_init(|| {\n        tract_onnx::onnx()\n            .model_for_path(\"model.onnx\")\n            .unwrap()\n            .into_optimized()\n            .unwrap()\n            .into_runnable()\n            .unwrap()\n    })\n}\n\nasync fn predict(input: Vec\u003Cf32>) -> anyhow::Result\u003CVec\u003Cf32>> {\n    let model = get_model();\n    let input = tract_ndarray::arr1(&input).into_shape((1, input.len()))?;\n    let result = model.run(tvec!(input.into()))?;\n    Ok(result[0].to_array_view::\u003Cf32>()?.iter().copied().collect())\n}\n```\n\n## Code Pattern: Batched Inference\n\n```rust\nasync fn batch_predict(inputs: Vec\u003CVec\u003Cf32>>, batch_size: usize) -> Vec\u003CVec\u003Cf32>> {\n    let mut results = Vec::with_capacity(inputs.len());\n\n    for batch in inputs.chunks(batch_size) {\n        \u002F\u002F Stack inputs into batch tensor\n        let batch_tensor = stack_inputs(batch);\n\n        \u002F\u002F Run inference on batch\n        let batch_output = model.run(batch_tensor).await;\n\n        \u002F\u002F Unstack results\n        results.extend(unstack_outputs(batch_output));\n    }\n\n    results\n}\n```\n\n---\n\n## Common Mistakes\n\n| Mistake | Domain Violation | Fix |\n|---------|-----------------|-----|\n| Clone tensors | Memory waste | Use views |\n| Single inference | GPU underutilized | Batch processing |\n| Load model per request | Slow | Singleton pattern |\n| Sync data loading | GPU idle | Async pipeline |\n\n---\n\n## Trace to Layer 1\n\n| Constraint | Layer 2 Pattern | Layer 1 Implementation |\n|------------|-----------------|------------------------|\n| Memory efficiency | Zero-copy | ndarray views |\n| Model singleton | Lazy init | OnceLock\u003CModel> |\n| Batch processing | Chunked iteration | chunks() + parallel |\n| GPU async | Concurrent loading | tokio::spawn + GPU |\n\n---\n\n## Related Skills\n\n| When | See |\n|------|-----|\n| Performance | m10-performance |\n| Lazy initialization | m12-lifecycle |\n| Async patterns | m07-concurrency |\n| Memory efficiency | m01-ownership |\n",{"name":5,"description":7,"user-invocable":40},"main","6c13f6f4ac5a3bc1e6b78cd2bb1704f122c4a73e","archive\u002Fupstream\u002Fchasebuild-agent-skills\u002Frust\u002Fskills\u002Fdomain-ml",0,"https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit","https:\u002F\u002Fgithub.com\u002F0xharryriddle","https:\u002F\u002Fharryriddle.vercel.app","2026-04-11 11:49:51",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add 0xharryriddle\u002Fcodex-field-kit --skill domain-ml",{"tool":58,"command":59},"bunx","bunx skills add 0xharryriddle\u002Fcodex-field-kit --skill domain-ml",{"tool":61,"command":62},"pnpm","pnpm dlx skills add 0xharryriddle\u002Fcodex-field-kit --skill domain-ml","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Farchive\u002Fupstream\u002Fchasebuild-agent-skills\u002Frust\u002Fskills\u002Fdomain-ml\u002FSKILL.md",true,[],[67,99,118,128,153,180],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":78,"publishedAt":39},"01M6H7ZKE6MR33HC84QZ1TA6MV","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-react-best-practices\u002FSKILL.md",[73],{"categoryNo":74,"categoryName":75,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",[79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98],"react best practices","react","vercel react best practices","best practices","vercel","tasks","data fetching","triggers","pages","next","performance optimization","refactoring","Next.js","Optimization","code","guidelines","react components","components","performance","writing",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":39},"01M6H7ZGC2WK8SEKYHWDNTMDA9","swarm-planner","[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fswarm-planner\u002FSKILL.md",[],[106,107,108,109,110,111,112,113,114,115,116,117],"swarm","swarm planner","planner","parallel","multi-agent","only","execution","plans","dependency","for","multi","implementation",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":39},"01M6H7ZD93853RZCYQWH1D38TM","super-swarm-spark","Only to be triggered by explicit super-swarm-spark commands.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fsuper-swarm-spark\u002FSKILL.md",[],[125,106,126,111,127],"super swarm spark","spark","commands",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":39},"01M6H7Z987QBY49JCCPT953EAZ","role-creator","Create and install Codex custom agent roles in ~\u002F.codex\u002Fconfig.toml, generate role config files, enforce supported keys, and guide users through required role inputs (model, reasoning effort, developer_instructions).","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Frole-creator\u002FSKILL.md",[],[135,136,137,138,139,140,141,142,143,144,145,31,146,147,148,149,150,151,152],"role","creator","role creator","keys","users","roles","toml","enforce","install","guide","instructions","developer","reasoning","generate","create","config","codex","files",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":162,"publishedAt":39},"01M6H7Z5TRPMDQ7YSZQXPN1G60","read-github","Read and search GitHub repository documentation via gitmcp.io MCP service.\n\n**WHEN TO USE:**\n- User provides a GitHub URL\n- User mentions a specific repo in owner\u002Frepo format\n- User asks \"what does this repo do?\", \"read the docs for X repo\", or similar\n- User wants to search code or docs within a repo","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fread-github\u002FSKILL.md",[159],{"categoryNo":160,"categoryName":161,"taxonomyType":76,"taxonomyTypeDesc":77},"01JBSEEDCAT000000000000023","Skill与智能体开发",[163,164,165,93,166,167,168,169,115,170,171,172,173,174,175,30,176,177,178,179],"github","read github","read","documentation","docs","MCP","search","when to use","URL","via","io","service","do","user","repo","format","repository",{"skillNo":181,"name":108,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":185,"publishedAt":39},"01M6H7Z215CTKYJ4Y1X6EQWN6M","Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: \"make a plan\", \"create a plan\", \"plan this out\", \"plan the implementation\", \"help me plan\", \"design a plan\", \"draft a plan\", \"write a plan\", \"outline the steps\", \"break this down into tasks\", \"what's the plan for\", or any similar planning request. Also triggers on explicit \"\u002Fplanner\" or \"\u002Fplan\" commands.","https:\u002F\u002Fgithub.com\u002F0xharryriddle\u002Fcodex-field-kit\u002Fblob\u002Fmain\u002Fskills\u002Fplanner\u002FSKILL.md",[],[108,186,115,187,188,189,86,113,127,190,191,30,192,193,194,195,196,149,84,197],"outline","atomic","with","sprints","draft","me","write","phased implementation","plan","help","planning","design"]