[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PRHRD659FPZRKYJFP8AGPJ":3,"skill-same:01M6PRHRD659FPZRKYJFP8AGPJ":86},{"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":47,"commitSha":48,"skillDirectory":49,"forksCount":14,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6PRHRD659FPZRKYJFP8AGPJ","redis-vector-search",null,"Redis vector search guidance covering HNSW vs FLAT algorithm choice, vector index configuration (dims, distance metric, datatype), filtered hybrid search combining vector similarity with TAG or NUMERIC filters, and the RAG retrieval pattern with RedisVL. Use when defining a VECTOR field in FT.CREATE, integrating embeddings (OpenAI, Cohere, sentence-transformers), tuning HNSW parameters (M, EF_CONSTRUCTION, EF_RUNTIME), building a retrieval-augmented generation pipeline, or filtering vector results by attribute.","headmktlucca-ui\u002Fneuroads-lp","headmktlucca-ui","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F247379838?v=4","01M6PDVAV6M1W96D1SR1PDF8CS","NeuroAds","01M6PDVAZ4P281GNDKD45CYTF5",0,"MIT","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fredis-vector-search\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"search","redis vector search","Vector Search","vector","redis","generation","create","filtered","hybrid","cohere","with","Hybrid Search","similarity","runtime","filters","use","filtering","results","choice","pipeline","2026-11-10 10:12:30",false,"---\nname: redis-vector-search\ndescription: Redis vector search guidance covering HNSW vs FLAT algorithm choice, vector index configuration (dims, distance metric, datatype), filtered hybrid search combining vector similarity with TAG or NUMERIC filters, and the RAG retrieval pattern with RedisVL. Use when defining a VECTOR field in FT.CREATE, integrating embeddings (OpenAI, Cohere, sentence-transformers), tuning HNSW parameters (M, EF_CONSTRUCTION, EF_RUNTIME), building a retrieval-augmented generation pipeline, or filtering vector results by attribute.\nlicense: MIT\nmetadata:\n  author: Redis, Inc.\n  version: \"0.1.0\"\n---\n\n# Redis Vector Search\n\nGuidance for storing and searching embeddings in Redis. Covers index configuration, algorithm selection, hybrid filtering, and the RAG retrieval pattern with RedisVL.\n\n## When to apply\n\n- Defining a `VECTOR` field in `FT.CREATE` (raw RQE) or a RedisVL `IndexSchema`.\n- Choosing HNSW vs FLAT and tuning HNSW parameters.\n- Adding category, date, or tenant filters to a vector query.\n- Building a retrieval-augmented generation (RAG) pipeline on top of Redis.\n\nThis skill builds on the `redis-query-engine` skill — vector fields live inside RQE indexes and share the same `FT.CREATE` \u002F `FT.SEARCH` machinery.\n\n## 1. Configure the vector index properly\n\nThree settings must match the embedding model:\n\n- **`DIM`** — the model's output dimensionality (e.g. 1536 for OpenAI `text-embedding-3-small`). A mismatch produces silent garbage.\n- **`DISTANCE_METRIC`** — `COSINE` for normalized text embeddings (the common case), `IP` for unnormalized inner-product, `L2` for raw Euclidean.\n- **`TYPE` \u002F `datatype`** — usually `FLOAT32`. Use `FLOAT16` or quantized variants only when memory cost is a hard constraint.\n\nRaw RQE:\n\n```\nFT.CREATE idx:docs ON HASH PREFIX 1 doc:\n    SCHEMA\n        content TEXT\n        embedding VECTOR HNSW 6\n            TYPE FLOAT32\n            DIM 1536\n            DISTANCE_METRIC COSINE\n```\n\nRedisVL:\n\n```python\nschema = IndexSchema.from_dict({\n    \"index\": {\"name\": \"idx:docs\", \"prefix\": \"doc:\"},\n    \"fields\": [\n        {\"name\": \"content\", \"type\": \"text\"},\n        {\"name\": \"embedding\", \"type\": \"vector\", \"attrs\": {\n            \"dims\": 1536, \"algorithm\": \"HNSW\",\n            \"datatype\": \"FLOAT32\", \"distance_metric\": \"COSINE\",\n        }},\n    ]\n})\n```\n\nSee [references\u002Findex-creation.md](references\u002Findex-creation.md) for redis-py and RedisVL variants.\n\n## 2. HNSW vs FLAT\n\n| Algorithm | Speed | Accuracy | Memory | Best for |\n|---|---|---|---|---|\n| **HNSW** | Fast (approximate) | ~95%+ recall (tunable) | Higher | Large datasets (>10k vectors), latency-sensitive |\n| **FLAT** | Slow (exact) | 100% | Lower | Small datasets (\u003C10k), accuracy-critical |\n\nDefault to **HNSW** for any production-scale workload. Tuning levers:\n\n- `M` — connections per node (16–64). Higher = better recall, more memory.\n- `EF_CONSTRUCTION` — build-time graph quality (100–500). Higher = better index, slower build.\n- `EF_RUNTIME` — query-time candidate-list size. Higher = better recall, slower queries.\n\nUse **FLAT** when the corpus is small and you need exact results (e.g. semantic dedup over a few thousand items).\n\nSee [references\u002Falgorithm-choice.md](references\u002Falgorithm-choice.md).\n\n## 3. Hybrid search — filter before vector\n\nApply attribute filters (TAG \u002F NUMERIC) so the engine narrows the search space *before* the vector comparison. Don't fetch a wide result set and then filter client-side — that's slower and less accurate.\n\n```python\nfrom redisvl.query import VectorQuery\nfrom redisvl.query.filter import Num, Tag\n\nfilters = (Tag(\"category\") == \"technology\") & (Num(\"date\") >= 2024)\n\nquery = VectorQuery(\n    vector=query_embedding,\n    vector_field_name=\"embedding\",\n    return_fields=[\"content\", \"category\", \"date\"],\n    num_results=10,\n    filter_expression=filters,\n)\nresults = index.query(query)\n```\n\nFor **text + vector fusion** (BM25-weighted text scoring combined with vector similarity), use `HybridQuery` on Redis ≥ 8.4 with redis-py ≥ 7.1, or `AggregateHybridQuery` on older Redis. That's a different \"hybrid\" from filtered vector search above.\n\nSee [references\u002Fhybrid-search.md](references\u002Fhybrid-search.md).\n\n## 4. RAG pattern\n\nStandard pipeline: embed the user query → vector search Redis → pass top-K context to the LLM.\n\n```python\n# Index documents with embeddings\nrecords = [{\"content\": doc.content,\n            \"embedding\": embed_model.encode(doc.content).tolist(),\n            \"source\": doc.source}\n           for doc in documents]\nindex.load(records)\n\n# Retrieve relevant context for a user question\nq_emb = embed_model.encode(user_question)\nresults = index.query(VectorQuery(\n    vector=q_emb,\n    vector_field_name=\"embedding\",\n    return_fields=[\"content\", \"source\"],\n    num_results=5,\n))\n\n# Generate with retrieved context\ncontext = \"\\n\".join(r[\"content\"] for r in results)\nresponse = llm.generate(f\"Context: {context}\\n\\nQuestion: {user_question}\")\n```\n\nPractical tips:\n\n- **Match metric to model.** Most modern text embedding models pair best with `COSINE`.\n- **Chunk long documents** before indexing — retrieval over 200–500-token chunks usually beats indexing whole pages.\n- **Batch inserts** with `index.load([...])` instead of one call per record.\n- **Pre-filter with attributes** (tenant, recency, document type) before the vector search.\n\nSee [references\u002Frag-pattern.md](references\u002Frag-pattern.md).\n\n## References\n\n- [Redis: Vectors](https:\u002F\u002Fredis.io\u002Fdocs\u002Flatest\u002Fdevelop\u002Fai\u002Fsearch-and-query\u002Fvectors\u002F)\n- [Redis: RAG quickstart](https:\u002F\u002Fredis.io\u002Fdocs\u002Flatest\u002Fdevelop\u002Fget-started\u002Frag\u002F)\n- [RedisVL documentation](https:\u002F\u002Fdocs.redisvl.com\u002Fen\u002Flatest\u002F)\n","# Redis Vector Search\n\nGuidance for storing and searching embeddings in Redis. Covers index configuration, algorithm selection, hybrid filtering, and the RAG retrieval pattern with RedisVL.\n\n## When to apply\n\n- Defining a `VECTOR` field in `FT.CREATE` (raw RQE) or a RedisVL `IndexSchema`.\n- Choosing HNSW vs FLAT and tuning HNSW parameters.\n- Adding category, date, or tenant filters to a vector query.\n- Building a retrieval-augmented generation (RAG) pipeline on top of Redis.\n\nThis skill builds on the `redis-query-engine` skill — vector fields live inside RQE indexes and share the same `FT.CREATE` \u002F `FT.SEARCH` machinery.\n\n## 1. Configure the vector index properly\n\nThree settings must match the embedding model:\n\n- **`DIM`** — the model's output dimensionality (e.g. 1536 for OpenAI `text-embedding-3-small`). A mismatch produces silent garbage.\n- **`DISTANCE_METRIC`** — `COSINE` for normalized text embeddings (the common case), `IP` for unnormalized inner-product, `L2` for raw Euclidean.\n- **`TYPE` \u002F `datatype`** — usually `FLOAT32`. Use `FLOAT16` or quantized variants only when memory cost is a hard constraint.\n\nRaw RQE:\n\n```\nFT.CREATE idx:docs ON HASH PREFIX 1 doc:\n    SCHEMA\n        content TEXT\n        embedding VECTOR HNSW 6\n            TYPE FLOAT32\n            DIM 1536\n            DISTANCE_METRIC COSINE\n```\n\nRedisVL:\n\n```python\nschema = IndexSchema.from_dict({\n    \"index\": {\"name\": \"idx:docs\", \"prefix\": \"doc:\"},\n    \"fields\": [\n        {\"name\": \"content\", \"type\": \"text\"},\n        {\"name\": \"embedding\", \"type\": \"vector\", \"attrs\": {\n            \"dims\": 1536, \"algorithm\": \"HNSW\",\n            \"datatype\": \"FLOAT32\", \"distance_metric\": \"COSINE\",\n        }},\n    ]\n})\n```\n\nSee [references\u002Findex-creation.md](references\u002Findex-creation.md) for redis-py and RedisVL variants.\n\n## 2. HNSW vs FLAT\n\n| Algorithm | Speed | Accuracy | Memory | Best for |\n|---|---|---|---|---|\n| **HNSW** | Fast (approximate) | ~95%+ recall (tunable) | Higher | Large datasets (>10k vectors), latency-sensitive |\n| **FLAT** | Slow (exact) | 100% | Lower | Small datasets (\u003C10k), accuracy-critical |\n\nDefault to **HNSW** for any production-scale workload. Tuning levers:\n\n- `M` — connections per node (16–64). Higher = better recall, more memory.\n- `EF_CONSTRUCTION` — build-time graph quality (100–500). Higher = better index, slower build.\n- `EF_RUNTIME` — query-time candidate-list size. Higher = better recall, slower queries.\n\nUse **FLAT** when the corpus is small and you need exact results (e.g. semantic dedup over a few thousand items).\n\nSee [references\u002Falgorithm-choice.md](references\u002Falgorithm-choice.md).\n\n## 3. Hybrid search — filter before vector\n\nApply attribute filters (TAG \u002F NUMERIC) so the engine narrows the search space *before* the vector comparison. Don't fetch a wide result set and then filter client-side — that's slower and less accurate.\n\n```python\nfrom redisvl.query import VectorQuery\nfrom redisvl.query.filter import Num, Tag\n\nfilters = (Tag(\"category\") == \"technology\") & (Num(\"date\") >= 2024)\n\nquery = VectorQuery(\n    vector=query_embedding,\n    vector_field_name=\"embedding\",\n    return_fields=[\"content\", \"category\", \"date\"],\n    num_results=10,\n    filter_expression=filters,\n)\nresults = index.query(query)\n```\n\nFor **text + vector fusion** (BM25-weighted text scoring combined with vector similarity), use `HybridQuery` on Redis ≥ 8.4 with redis-py ≥ 7.1, or `AggregateHybridQuery` on older Redis. That's a different \"hybrid\" from filtered vector search above.\n\nSee [references\u002Fhybrid-search.md](references\u002Fhybrid-search.md).\n\n## 4. RAG pattern\n\nStandard pipeline: embed the user query → vector search Redis → pass top-K context to the LLM.\n\n```python\n# Index documents with embeddings\nrecords = [{\"content\": doc.content,\n            \"embedding\": embed_model.encode(doc.content).tolist(),\n            \"source\": doc.source}\n           for doc in documents]\nindex.load(records)\n\n# Retrieve relevant context for a user question\nq_emb = embed_model.encode(user_question)\nresults = index.query(VectorQuery(\n    vector=q_emb,\n    vector_field_name=\"embedding\",\n    return_fields=[\"content\", \"source\"],\n    num_results=5,\n))\n\n# Generate with retrieved context\ncontext = \"\\n\".join(r[\"content\"] for r in results)\nresponse = llm.generate(f\"Context: {context}\\n\\nQuestion: {user_question}\")\n```\n\nPractical tips:\n\n- **Match metric to model.** Most modern text embedding models pair best with `COSINE`.\n- **Chunk long documents** before indexing — retrieval over 200–500-token chunks usually beats indexing whole pages.\n- **Batch inserts** with `index.load([...])` instead of one call per record.\n- **Pre-filter with attributes** (tenant, recency, document type) before the vector search.\n\nSee [references\u002Frag-pattern.md](references\u002Frag-pattern.md).\n\n## References\n\n- [Redis: Vectors](https:\u002F\u002Fredis.io\u002Fdocs\u002Flatest\u002Fdevelop\u002Fai\u002Fsearch-and-query\u002Fvectors\u002F)\n- [Redis: RAG quickstart](https:\u002F\u002Fredis.io\u002Fdocs\u002Flatest\u002Fdevelop\u002Fget-started\u002Frag\u002F)\n- [RedisVL documentation](https:\u002F\u002Fdocs.redisvl.com\u002Fen\u002Flatest\u002F)\n",{"name":5,"license":15,"metadata":44,"description":7},{"author":45,"version":46},"Redis, Inc.","0.1.0","main","7a940b8e5af16c95e5c190a524421d32fc7445a9",".claude\u002Fskills\u002Fredis-vector-search","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui","https:\u002F\u002Fneuroads.com.br","2026-08-12 00:42:44",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add headmktlucca-ui\u002Fneuroads-lp --skill redis-vector-search",{"tool":60,"command":61},"bunx","bunx skills add headmktlucca-ui\u002Fneuroads-lp --skill redis-vector-search",{"tool":63,"command":64},"pnpm","pnpm dlx skills add headmktlucca-ui\u002Fneuroads-lp --skill redis-vector-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fredis-vector-search\u002FSKILL.md",true,[68,74,78,82],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Falgorithm-choice.md","REFERENCE","参考文档",1842,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fredis-vector-search\u002Freferences\u002Falgorithm-choice.md",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fhybrid-search.md",1536,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fredis-vector-search\u002Freferences\u002Fhybrid-search.md",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Findex-creation.md",2028,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fredis-vector-search\u002Freferences\u002Findex-creation.md",{"path":83,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Frag-pattern.md",1370,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fredis-vector-search\u002Freferences\u002Frag-pattern.md",[87,112,137,162,180,215],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":101,"publishedAt":39},"01M6PTDCZTXTGSTX4RFK901YSZ","xunit-skill","Generates xUnit.net tests in C#. Covers Fact\u002FTheory, constructor injection, IClassFixture, and FluentAssertions. Use when user mentions \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal\", \"C# xUnit\". Triggers on: \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal C#\", \"xUnit.net\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxunit-skill\u002FSKILL.md",[93,98],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发",[102,103,104,105,106,34,107,108,109,110,111],"xunit","xunit skill","testing","injection","user","tests","triggers","unit","unit-testing","C#",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":120,"publishedAt":39},"01M6PTCB59ZTG5FTMWGPYEMMBP","xcuitest-skill","Generates XCUITest UI tests for iOS\u002FiPadOS apps in Swift. Apple's native testing framework for reliable, fast UI automation. Supports local simulators and TestMu AI cloud real devices. Use when user mentions \"XCUITest\", \"XCTest\", \"iOS UI test\", \"Swift test\", \"XCUIApplication\". Triggers on: \"XCUITest\", \"XCTest UI\", \"iOS UI test\", \"Swift UI test\", \"XCUIApplication\", \"TestMu\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxcuitest-skill\u002FSKILL.md",[118,119],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},[121,122,104,123,124,125,126,127,34,128,129,130,131,132,107,108,133,134,135,136],"xcuitest","xcuitest skill","automation","test","testing framework","ios","devices","mobile","mobile-testing","ui test","local","apple","apps","native","for","objective",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":147,"publishedAt":39},"01M6PTATMNTY9NF4J7KSR76YK6","world-builder","Create and manage generative game zones for Dorothy's Pokemon-style world. Use this skill when creating, updating, or designing game worlds via MCP tools.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fworld-builder\u002FSKILL.md",[143,146],{"categoryNo":144,"categoryName":145,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},[148,149,150,151,25,152,153,154,34,155,156,157,158,159,160,135,161],"builder","world","world builder","MCP","mcp tools","Tools","game","pokemon","manage","style","via","theme","zone","generative",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":170,"publishedAt":39},"01M6PT9Z92JTSQEHE1QR0NNW5F","webdriverio-skill","Generates WebdriverIO (WDIO) automation tests in JavaScript or TypeScript. Supports local and TestMu AI cloud. Use when user mentions \"WebdriverIO\", \"WDIO\", \"wdio.conf\", \"browser.url\", \"$\", \"$$\". Triggers on: \"WebdriverIO\", \"WDIO\", \"wdio\", \"browser.$\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwebdriverio-skill\u002FSKILL.md",[168,169],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":99,"categoryName":100,"taxonomyType":96,"taxonomyTypeDesc":97},[171,104,172,123,173,174,175,176,106,34,177,131,107,108,178,179],"webdriverio skill","typescript","javascript","browser","cloud","e2e","e2e-testing","URL","conf",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":195,"publishedAt":39},"01M6PT9NVK36ZWCQ69YXK3FR4K","web-design-guidelines","Web platform design and accessibility guidelines. Use when building web interfaces, auditing accessibility, implementing responsive layouts, or reviewing web UI code. Triggers on tasks involving HTML, CSS, web components, WCAG compliance, responsive design, or web performance.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fweb\u002FSKILL.md",[186,189,190],{"categoryNo":187,"categoryName":188,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":144,"categoryName":145,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":191,"categoryName":192,"taxonomyType":193,"taxonomyTypeDesc":194},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,108,214],"design","web","guidelines","web design guidelines","web design","css","performance","components","web components","tasks","code","web performance","ui","platform design","html","responsive design","responsive","platform","implementing",{"skillNo":216,"name":217,"nameZh":6,"description":218,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":219,"categories":220,"keywords":223,"publishedAt":39},"01M6PT9A3JKRE3X34276F2FW5R","watchos-design-guidelines","Apple Human Interface Guidelines for Apple Watch. Use when building watchOS apps, complications, or workout features. Triggers on tasks involving Watch UI, Digital Crown, glanceable interfaces, or wrist-based interactions.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwatchos\u002FSKILL.md",[221,222],{"categoryNo":144,"categoryName":145,"taxonomyType":96,"taxonomyTypeDesc":97},{"categoryNo":191,"categoryName":192,"taxonomyType":193,"taxonomyTypeDesc":194},[196,198,224,205,208,34,225,226,132,213,227,108,133,228,135,229,230],"watchos design guidelines","workout","human","watch","interface","platform-design","features"]