[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6F7N9WSP5KV0RW9CGHCWSHP":3,"skill-same:01M6F7N9WSP5KV0RW9CGHCWSHP":72},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6F7N9WSP5KV0RW9CGHCWSHP","langchain-performance-tuning",null,"Optimize LangChain application performance and latency.\nUse when reducing response times, optimizing throughput,\nor improving the efficiency of LangChain pipelines.\nTrigger with phrases like \"langchain performance\", \"langchain optimization\",\n\"langchain latency\", \"langchain slow\", \"speed up langchain\".","Dicklesworthstone\u002Fpi_agent_rust","Dicklesworthstone","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F35050222?v=4","01M6CG26AR942CSVMN1M5E3DSE","Jeff Emanuel","01M6CG26EPP71PSHW1VDS71121",1991,"MIT","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Flangchain-pack\u002Fskills\u002Flangchain-performance-tuning\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"tuning","langchain","langchain performance tuning","performance tuning","performance","optimize","when","with","throughput","trigger","io","latency","speed","efficiency","pipelines","up","use","edit","write","read","Optimization","2026-11-10 10:12:30",false,"---\nname: langchain-performance-tuning\ndescription: |\n  Optimize LangChain application performance and latency.\n  Use when reducing response times, optimizing throughput,\n  or improving the efficiency of LangChain pipelines.\n  Trigger with phrases like \"langchain performance\", \"langchain optimization\",\n  \"langchain latency\", \"langchain slow\", \"speed up langchain\".\nallowed-tools: Read, Write, Edit\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\n---\n\n# LangChain Performance Tuning\n\n## Overview\nOptimize LangChain applications for lower latency, higher throughput, and efficient resource utilization.\n\n## Prerequisites\n- Working LangChain application\n- Performance baseline measurements\n- Profiling tools available\n\n## Instructions\n\n### Step 1: Measure Baseline Performance\n```python\nimport time\nfrom functools import wraps\nfrom typing import Callable\nimport statistics\n\ndef benchmark(func: Callable, iterations: int = 10):\n    \"\"\"Benchmark a function's performance.\"\"\"\n    times = []\n    for _ in range(iterations):\n        start = time.perf_counter()\n        func()\n        elapsed = time.perf_counter() - start\n        times.append(elapsed)\n\n    return {\n        \"mean\": statistics.mean(times),\n        \"median\": statistics.median(times),\n        \"stdev\": statistics.stdev(times) if len(times) > 1 else 0,\n        \"min\": min(times),\n        \"max\": max(times),\n    }\n\n# Usage\nfrom langchain_openai import ChatOpenAI\n\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\n\ndef test_call():\n    llm.invoke(\"Hello!\")\n\nresults = benchmark(test_call, iterations=5)\nprint(f\"Mean latency: {results['mean']:.3f}s\")\n```\n\n### Step 2: Enable Response Caching\n```python\nfrom langchain_core.globals import set_llm_cache\nfrom langchain_community.cache import InMemoryCache, SQLiteCache, RedisCache\n\n# Option 1: In-memory cache (single process)\nset_llm_cache(InMemoryCache())\n\n# Option 2: SQLite cache (persistent, single node)\nset_llm_cache(SQLiteCache(database_path=\".langchain_cache.db\"))\n\n# Option 3: Redis cache (distributed, production)\nimport redis\nredis_client = redis.Redis.from_url(\"redis:\u002F\u002Flocalhost:6379\")\nset_llm_cache(RedisCache(redis_client))\n\n# Cache hit = ~0ms latency vs ~500-2000ms for API call\n```\n\n### Step 3: Optimize Batch Processing\n```python\nimport asyncio\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.prompts import ChatPromptTemplate\n\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\nprompt = ChatPromptTemplate.from_template(\"{input}\")\nchain = prompt | llm\n\n# Sequential (slow)\ndef process_sequential(inputs: list) -> list:\n    return [chain.invoke({\"input\": inp}) for inp in inputs]\n\n# Batch (faster - automatic batching)\ndef process_batch(inputs: list) -> list:\n    batch_inputs = [{\"input\": inp} for inp in inputs]\n    return chain.batch(batch_inputs, config={\"max_concurrency\": 10})\n\n# Async (fastest - true parallelism)\nasync def process_async(inputs: list) -> list:\n    batch_inputs = [{\"input\": inp} for inp in inputs]\n    return await chain.abatch(batch_inputs, config={\"max_concurrency\": 20})\n\n# Benchmark: 10 items\n# Sequential: ~10s (1s each)\n# Batch: ~2s (parallel API calls)\n# Async: ~1.5s (optimal parallelism)\n```\n\n### Step 4: Use Streaming for Perceived Performance\n```python\nfrom langchain_openai import ChatOpenAI\n\n# Non-streaming: User waits for full response\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\nresponse = llm.invoke(\"Tell me a story\")  # Wait 2-3 seconds\n\n# Streaming: First token in ~200ms\nllm_stream = ChatOpenAI(model=\"gpt-4o-mini\", streaming=True)\nfor chunk in llm_stream.stream(\"Tell me a story\"):\n    print(chunk.content, end=\"\", flush=True)\n```\n\n### Step 5: Optimize Prompt Length\n```python\nimport tiktoken\n\ndef count_tokens(text: str, model: str = \"gpt-4o-mini\") -> int:\n    \"\"\"Count tokens in text.\"\"\"\n    encoding = tiktoken.encoding_for_model(model)\n    return len(encoding.encode(text))\n\ndef optimize_prompt(prompt: str, max_tokens: int = 1000) -> str:\n    \"\"\"Truncate prompt to fit token limit.\"\"\"\n    encoding = tiktoken.encoding_for_model(\"gpt-4o-mini\")\n    tokens = encoding.encode(prompt)\n    if len(tokens) \u003C= max_tokens:\n        return prompt\n    return encoding.decode(tokens[:max_tokens])\n\n# Example: Long context optimization\nsystem_prompt = \"You are a helpful assistant.\"  # ~5 tokens\nuser_context = \"Here is the document: \" + long_document  # Could be 10000+ tokens\n\n# Optimize by summarizing or chunking context\n```\n\n### Step 6: Connection Pooling\n```python\nimport httpx\nfrom langchain_openai import ChatOpenAI\n\n# Configure connection pooling for high throughput\ntransport = httpx.HTTPTransport(\n    retries=3,\n    limits=httpx.Limits(\n        max_connections=100,\n        max_keepalive_connections=20\n    )\n)\n\n# Use shared client across requests\nhttp_client = httpx.Client(transport=transport, timeout=30.0)\n\n# Note: OpenAI SDK handles this internally, but for custom integrations:\nllm = ChatOpenAI(\n    model=\"gpt-4o-mini\",\n    http_client=http_client  # Reuse connections\n)\n```\n\n### Step 7: Model Selection Optimization\n```python\n# Match model to task complexity\n\n# Fast + Cheap: Simple tasks\nllm_fast = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n\n# Powerful + Slower: Complex reasoning\nllm_powerful = ChatOpenAI(model=\"gpt-4o\", temperature=0)\n\n# Router pattern: Choose model based on task\nfrom langchain_core.runnables import RunnableBranch\n\ndef classify_complexity(input_dict: dict) -> str:\n    \"\"\"Classify input complexity.\"\"\"\n    text = input_dict.get(\"input\", \"\")\n    # Simple heuristic - replace with classifier\n    return \"complex\" if len(text) > 500 else \"simple\"\n\nrouter = RunnableBranch(\n    (lambda x: classify_complexity(x) == \"simple\", prompt | llm_fast),\n    prompt | llm_powerful  # Default to powerful\n)\n```\n\n## Performance Metrics\n| Optimization | Latency Improvement | Cost Impact |\n|--------------|---------------------|-------------|\n| Caching | 90-99% on cache hit | Major reduction |\n| Batching | 50-80% for bulk | Neutral |\n| Streaming | Perceived 80%+ | Neutral |\n| Shorter prompts | 10-30% | Cost reduction |\n| Connection pooling | 5-10% | Neutral |\n| Model routing | 20-50% | Cost reduction |\n\n## Output\n- Performance benchmarking setup\n- Caching implementation\n- Optimized batch processing\n- Streaming for perceived performance\n\n## Resources\n- [LangChain Caching](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fhow_to\u002Fllm_caching\u002F)\n- [OpenAI Latency Guide](https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fguides\u002Flatency-optimization)\n- [tiktoken](https:\u002F\u002Fgithub.com\u002Fopenai\u002Ftiktoken)\n\n## Next Steps\nUse `langchain-cost-tuning` to optimize API costs alongside performance.\n","# LangChain Performance Tuning\n\n## Overview\nOptimize LangChain applications for lower latency, higher throughput, and efficient resource utilization.\n\n## Prerequisites\n- Working LangChain application\n- Performance baseline measurements\n- Profiling tools available\n\n## Instructions\n\n### Step 1: Measure Baseline Performance\n```python\nimport time\nfrom functools import wraps\nfrom typing import Callable\nimport statistics\n\ndef benchmark(func: Callable, iterations: int = 10):\n    \"\"\"Benchmark a function's performance.\"\"\"\n    times = []\n    for _ in range(iterations):\n        start = time.perf_counter()\n        func()\n        elapsed = time.perf_counter() - start\n        times.append(elapsed)\n\n    return {\n        \"mean\": statistics.mean(times),\n        \"median\": statistics.median(times),\n        \"stdev\": statistics.stdev(times) if len(times) > 1 else 0,\n        \"min\": min(times),\n        \"max\": max(times),\n    }\n\n# Usage\nfrom langchain_openai import ChatOpenAI\n\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\n\ndef test_call():\n    llm.invoke(\"Hello!\")\n\nresults = benchmark(test_call, iterations=5)\nprint(f\"Mean latency: {results['mean']:.3f}s\")\n```\n\n### Step 2: Enable Response Caching\n```python\nfrom langchain_core.globals import set_llm_cache\nfrom langchain_community.cache import InMemoryCache, SQLiteCache, RedisCache\n\n# Option 1: In-memory cache (single process)\nset_llm_cache(InMemoryCache())\n\n# Option 2: SQLite cache (persistent, single node)\nset_llm_cache(SQLiteCache(database_path=\".langchain_cache.db\"))\n\n# Option 3: Redis cache (distributed, production)\nimport redis\nredis_client = redis.Redis.from_url(\"redis:\u002F\u002Flocalhost:6379\")\nset_llm_cache(RedisCache(redis_client))\n\n# Cache hit = ~0ms latency vs ~500-2000ms for API call\n```\n\n### Step 3: Optimize Batch Processing\n```python\nimport asyncio\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.prompts import ChatPromptTemplate\n\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\nprompt = ChatPromptTemplate.from_template(\"{input}\")\nchain = prompt | llm\n\n# Sequential (slow)\ndef process_sequential(inputs: list) -> list:\n    return [chain.invoke({\"input\": inp}) for inp in inputs]\n\n# Batch (faster - automatic batching)\ndef process_batch(inputs: list) -> list:\n    batch_inputs = [{\"input\": inp} for inp in inputs]\n    return chain.batch(batch_inputs, config={\"max_concurrency\": 10})\n\n# Async (fastest - true parallelism)\nasync def process_async(inputs: list) -> list:\n    batch_inputs = [{\"input\": inp} for inp in inputs]\n    return await chain.abatch(batch_inputs, config={\"max_concurrency\": 20})\n\n# Benchmark: 10 items\n# Sequential: ~10s (1s each)\n# Batch: ~2s (parallel API calls)\n# Async: ~1.5s (optimal parallelism)\n```\n\n### Step 4: Use Streaming for Perceived Performance\n```python\nfrom langchain_openai import ChatOpenAI\n\n# Non-streaming: User waits for full response\nllm = ChatOpenAI(model=\"gpt-4o-mini\")\nresponse = llm.invoke(\"Tell me a story\")  # Wait 2-3 seconds\n\n# Streaming: First token in ~200ms\nllm_stream = ChatOpenAI(model=\"gpt-4o-mini\", streaming=True)\nfor chunk in llm_stream.stream(\"Tell me a story\"):\n    print(chunk.content, end=\"\", flush=True)\n```\n\n### Step 5: Optimize Prompt Length\n```python\nimport tiktoken\n\ndef count_tokens(text: str, model: str = \"gpt-4o-mini\") -> int:\n    \"\"\"Count tokens in text.\"\"\"\n    encoding = tiktoken.encoding_for_model(model)\n    return len(encoding.encode(text))\n\ndef optimize_prompt(prompt: str, max_tokens: int = 1000) -> str:\n    \"\"\"Truncate prompt to fit token limit.\"\"\"\n    encoding = tiktoken.encoding_for_model(\"gpt-4o-mini\")\n    tokens = encoding.encode(prompt)\n    if len(tokens) \u003C= max_tokens:\n        return prompt\n    return encoding.decode(tokens[:max_tokens])\n\n# Example: Long context optimization\nsystem_prompt = \"You are a helpful assistant.\"  # ~5 tokens\nuser_context = \"Here is the document: \" + long_document  # Could be 10000+ tokens\n\n# Optimize by summarizing or chunking context\n```\n\n### Step 6: Connection Pooling\n```python\nimport httpx\nfrom langchain_openai import ChatOpenAI\n\n# Configure connection pooling for high throughput\ntransport = httpx.HTTPTransport(\n    retries=3,\n    limits=httpx.Limits(\n        max_connections=100,\n        max_keepalive_connections=20\n    )\n)\n\n# Use shared client across requests\nhttp_client = httpx.Client(transport=transport, timeout=30.0)\n\n# Note: OpenAI SDK handles this internally, but for custom integrations:\nllm = ChatOpenAI(\n    model=\"gpt-4o-mini\",\n    http_client=http_client  # Reuse connections\n)\n```\n\n### Step 7: Model Selection Optimization\n```python\n# Match model to task complexity\n\n# Fast + Cheap: Simple tasks\nllm_fast = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)\n\n# Powerful + Slower: Complex reasoning\nllm_powerful = ChatOpenAI(model=\"gpt-4o\", temperature=0)\n\n# Router pattern: Choose model based on task\nfrom langchain_core.runnables import RunnableBranch\n\ndef classify_complexity(input_dict: dict) -> str:\n    \"\"\"Classify input complexity.\"\"\"\n    text = input_dict.get(\"input\", \"\")\n    # Simple heuristic - replace with classifier\n    return \"complex\" if len(text) > 500 else \"simple\"\n\nrouter = RunnableBranch(\n    (lambda x: classify_complexity(x) == \"simple\", prompt | llm_fast),\n    prompt | llm_powerful  # Default to powerful\n)\n```\n\n## Performance Metrics\n| Optimization | Latency Improvement | Cost Impact |\n|--------------|---------------------|-------------|\n| Caching | 90-99% on cache hit | Major reduction |\n| Batching | 50-80% for bulk | Neutral |\n| Streaming | Perceived 80%+ | Neutral |\n| Shorter prompts | 10-30% | Cost reduction |\n| Connection pooling | 5-10% | Neutral |\n| Model routing | 20-50% | Cost reduction |\n\n## Output\n- Performance benchmarking setup\n- Caching implementation\n- Optimized batch processing\n- Streaming for perceived performance\n\n## Resources\n- [LangChain Caching](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fhow_to\u002Fllm_caching\u002F)\n- [OpenAI Latency Guide](https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fguides\u002Flatency-optimization)\n- [tiktoken](https:\u002F\u002Fgithub.com\u002Fopenai\u002Ftiktoken)\n\n## Next Steps\nUse `langchain-cost-tuning` to optimize API costs alongside performance.\n",{"name":5,"author":45,"license":15,"version":46,"description":47,"allowed-tools":48},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Optimize LangChain application performance and latency.\nUse when reducing response times, optimizing throughput,\nor improving the efficiency of LangChain pipelines.\nTrigger with phrases like \"langchain performance\", \"langchain optimization\",\n\"langchain latency\", \"langchain slow\", \"speed up langchain\".\n","Read, Write, Edit","main","90b50ed0778745a80fd5bfb13b1843d45b9e82f7","tests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Flangchain-pack\u002Fskills\u002Flangchain-performance-tuning",234,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust","https:\u002F\u002Fgithub.com\u002FDicklesworthstone","https:\u002F\u002Fwww.jeffreyemanuel.com\u002F","Building in NY","2026-11-13 11:50:27",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add Dicklesworthstone\u002Fpi_agent_rust --skill langchain-performance-tuning",{"tool":64,"command":65},"bunx","bunx skills add Dicklesworthstone\u002Fpi_agent_rust --skill langchain-performance-tuning",{"tool":67,"command":68},"pnpm","pnpm dlx skills add Dicklesworthstone\u002Fpi_agent_rust --skill langchain-performance-tuning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Flangchain-pack\u002Fskills\u002Flangchain-performance-tuning\u002FSKILL.md",true,[],[73,113,137,163,190,212],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":86,"publishedAt":40},"01M6FEGPPK0ZTKCCM0R3E3KS33","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[81],{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",[87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,35,105,106,107,108,109,110,111,112],"web artifacts builder","web","artifacts","artifacts builder","builder","frontend","css","components","react","component","routing","state management","state","shadcn","file","ui","Tools","Tailwind","html","single-file","simple","ui components","multi","for","jsx","suite",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":124,"publishedAt":40},"01M6FEE9VTK1W4GY21AKREJXRG","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[120,123],{"categoryNo":121,"categoryName":122,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":82,"categoryName":83,"taxonomyType":84,"taxonomyTypeDesc":85},[125,126,127,92,128,129,88,130,131,132,102,133,134,135,136,26,110],"testing","webapp testing","webapp","screenshots","playwright","debugging","toolkit","browser","logs","applications","behavior","local",{"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":141,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":40},"01M6FE20F7ZTQBFWKF4MPJ2SBX","neuropixels-analysis","Neuropixels neural recording analysis. Load SpikeGLX\u002FOpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen\u002FIBL curation, AI-assisted visual analysis, for Neuropixels 1.0\u002F2.0 extracellular electrophysiology. Use when working with neural recordings, spike sorting, extracellular electrophysiology, or when the user mentions Neuropixels, SpikeGLX, Open Ephys, Kilosort, quality metrics, or unit curation.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fscientific\u002Fneuropixels-analysis\u002FSKILL.md",[],[145,146,147,148,149,150,151,152,35,153,154,155,156,157,158,159,26,160,161,162,110,25],"analysis","neuropixels analysis","spike","metrics","data","open","quality","user","recordings","Neural","motion","visual","quality metrics","unit","sorting","curation","recording","load",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":167,"sourceHtmlUrl":168,"categories":169,"keywords":173,"publishedAt":40},"01M6FDP0PDK6F1GGX395C7625Z","skill-creator","Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fskill-creator\u002FSKILL.md",[170],{"categoryNo":171,"categoryName":172,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000023","Skill与智能体开发",[174,175,176,177,178,179,180,181,182,183,184,185,186,187,26,110,188,25,189],"skill creator","creator","workflows","create","update","capabilities","knowledge","tool","integrations","specialized","guide","new skill","existing skill","users","Existing","new",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":194,"sourceHtmlUrl":195,"categories":196,"keywords":198,"publishedAt":40},"01M6FDM8Y7VK7NYG9SM7QPA3PW","notebooklm","Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fnotebooklm\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fnotebooklm\u002FSKILL.md",[197],{"categoryNo":171,"categoryName":172,"taxonomyType":84,"taxonomyTypeDesc":85},[192,199,200,201,202,203,204,132,205,206,35,207,208,209,210,110,211],"google","browser automation","gemini","automation","auth","code","library","management","only","document","query","Citation","source",{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":77,"licenseFileUrl":216,"sourceHtmlUrl":217,"categories":218,"keywords":225,"publishedAt":40},"01M6FDHPXE10J3XGTCH5HBHS1M","slack-gif-creator","Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like \"make me a GIF of X doing Y for Slack.\"","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fenterprise-communication\u002Fslack-gif-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fenterprise-communication\u002Fslack-gif-creator\u002FSKILL.md",[219,222],{"categoryNo":220,"categoryName":221,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000005","邮件与沟通",{"categoryNo":223,"categoryName":224,"taxonomyType":84,"taxonomyTypeDesc":85},"01JBSEEDCAT000000000000016","图像与多媒体",[226,227,228,175,229,103,230,231,180,35,232,187,233,234,235,110,236,25],"slack gif creator","slack","gif","validation","constraints","Animation","me","make","Utilities","concepts","request"]