[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6F7NJ8MV8JCQM6FQJPR4HPH":3,"skill-same:01M6F7NJ8MV8JCQM6FQJPR4HPH":79},{"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":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":56,"commitSha":57,"skillDirectory":58,"forksCount":59,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":63,"updatedAt":64,"install":65,"resources":78},"01M6F7NJ8MV8JCQM6FQJPR4HPH","langchain-rate-limits",null,"Implement LangChain rate limiting and backoff strategies.\nUse when handling API quotas, implementing retry logic,\nor optimizing request throughput for LLM providers.\nTrigger with phrases like \"langchain rate limit\", \"langchain throttling\",\n\"langchain backoff\", \"langchain retry\", \"API quota\".","Dicklesworthstone\u002Fpi_agent_rust","Dicklesworthstone","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F35050222?v=4","01M6CG26AR942CSVMN1M5E3DSE","Jeff Emanuel","01M6CG26EPP71PSHW1VDS71121",1992,"MIT","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Flangchain-pack\u002Fskills\u002Flangchain-rate-limits\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"limits","langchain","rate","langchain rate limits","trigger","when","request","rate limit","for","implementing","limit","backoff","retry","with","throughput","implement","io","rate limiting","logic","strategies","quota","use","edit","write","read","api","throttling","Providers","2026-11-10 10:12:30",false,"---\nname: langchain-rate-limits\ndescription: |\n  Implement LangChain rate limiting and backoff strategies.\n  Use when handling API quotas, implementing retry logic,\n  or optimizing request throughput for LLM providers.\n  Trigger with phrases like \"langchain rate limit\", \"langchain throttling\",\n  \"langchain backoff\", \"langchain retry\", \"API quota\".\nallowed-tools: Read, Write, Edit\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\n---\n\n# LangChain Rate Limits\n\n## Overview\nImplement robust rate limiting and retry strategies for LangChain applications to handle API quotas gracefully.\n\n## Prerequisites\n- LangChain installed with LLM provider\n- Understanding of provider rate limits\n- tenacity package for advanced retry logic\n\n## Instructions\n\n### Step 1: Understand Provider Limits\n```python\n# Common rate limits by provider:\nRATE_LIMITS = {\n    \"openai\": {\n        \"gpt-4o\": {\"rpm\": 10000, \"tpm\": 800000},\n        \"gpt-4o-mini\": {\"rpm\": 10000, \"tpm\": 4000000},\n    },\n    \"anthropic\": {\n        \"claude-3-5-sonnet\": {\"rpm\": 4000, \"tpm\": 400000},\n    },\n    \"google\": {\n        \"gemini-1.5-pro\": {\"rpm\": 360, \"tpm\": 4000000},\n    }\n}\n# rpm = requests per minute, tpm = tokens per minute\n```\n\n### Step 2: Built-in Retry Configuration\n```python\nfrom langchain_openai import ChatOpenAI\n\n# LangChain has built-in retry with exponential backoff\nllm = ChatOpenAI(\n    model=\"gpt-4o-mini\",\n    max_retries=3,  # Number of retries\n    request_timeout=30,  # Timeout per request\n)\n```\n\n### Step 3: Advanced Retry with Tenacity\n```python\nfrom tenacity import (\n    retry,\n    stop_after_attempt,\n    wait_exponential,\n    retry_if_exception_type\n)\nfrom openai import RateLimitError, APIError\n\n@retry(\n    stop=stop_after_attempt(5),\n    wait=wait_exponential(multiplier=1, min=4, max=60),\n    retry=retry_if_exception_type((RateLimitError, APIError))\n)\ndef call_with_retry(chain, input_data):\n    \"\"\"Call chain with exponential backoff.\"\"\"\n    return chain.invoke(input_data)\n\n# Usage\nresult = call_with_retry(chain, {\"input\": \"Hello\"})\n```\n\n### Step 4: Rate Limiter Wrapper\n```python\nimport asyncio\nimport time\nfrom collections import deque\nfrom threading import Lock\n\nclass RateLimiter:\n    \"\"\"Token bucket rate limiter for API calls.\"\"\"\n\n    def __init__(self, requests_per_minute: int = 60):\n        self.rpm = requests_per_minute\n        self.interval = 60.0 \u002F requests_per_minute\n        self.timestamps = deque()\n        self.lock = Lock()\n\n    def acquire(self):\n        \"\"\"Block until request can be made.\"\"\"\n        with self.lock:\n            now = time.time()\n            # Remove timestamps older than 1 minute\n            while self.timestamps and now - self.timestamps[0] > 60:\n                self.timestamps.popleft()\n\n            if len(self.timestamps) >= self.rpm:\n                sleep_time = 60 - (now - self.timestamps[0])\n                if sleep_time > 0:\n                    time.sleep(sleep_time)\n\n            self.timestamps.append(time.time())\n\n# Usage with LangChain\nrate_limiter = RateLimiter(requests_per_minute=100)\n\ndef rate_limited_call(chain, input_data):\n    rate_limiter.acquire()\n    return chain.invoke(input_data)\n```\n\n### Step 5: Async Rate Limiting\n```python\nimport asyncio\nfrom asyncio import Semaphore\n\nclass AsyncRateLimiter:\n    \"\"\"Async rate limiter with semaphore.\"\"\"\n\n    def __init__(self, max_concurrent: int = 10):\n        self.semaphore = Semaphore(max_concurrent)\n\n    async def call(self, chain, input_data):\n        async with self.semaphore:\n            return await chain.ainvoke(input_data)\n\n# Batch processing with rate limiting\nasync def process_batch(chain, inputs: list, max_concurrent: int = 5):\n    limiter = AsyncRateLimiter(max_concurrent)\n    tasks = [limiter.call(chain, inp) for inp in inputs]\n    return await asyncio.gather(*tasks, return_exceptions=True)\n```\n\n## Output\n- Configured retry logic with exponential backoff\n- Rate limiter class for request throttling\n- Async batch processing with concurrency control\n- Graceful handling of rate limit errors\n\n## Examples\n\n### Handling Rate Limits in Production\n```python\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.runnables import RunnableConfig\n\nllm = ChatOpenAI(\n    model=\"gpt-4o-mini\",\n    max_retries=5,\n)\n\n# Use batch with max_concurrency\ninputs = [{\"input\": f\"Query {i}\"} for i in range(100)]\n\nresults = chain.batch(\n    inputs,\n    config=RunnableConfig(max_concurrency=10)  # Limit concurrent calls\n)\n```\n\n### Fallback on Rate Limit\n```python\nfrom langchain_openai import ChatOpenAI\nfrom langchain_anthropic import ChatAnthropic\n\nprimary = ChatOpenAI(model=\"gpt-4o-mini\", max_retries=2)\nfallback = ChatAnthropic(model=\"claude-3-5-sonnet-20241022\")\n\n# Automatically switch to fallback on rate limit\nrobust_llm = primary.with_fallbacks([fallback])\n```\n\n## Error Handling\n| Error | Cause | Solution |\n|-------|-------|----------|\n| RateLimitError | Exceeded quota | Implement backoff, reduce concurrency |\n| Timeout | Request too slow | Increase timeout, check network |\n| 429 Too Many Requests | API throttled | Wait and retry with backoff |\n| Quota Exceeded | Monthly limit hit | Upgrade plan or switch provider |\n\n## Resources\n- [OpenAI Rate Limits](https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fguides\u002Frate-limits)\n- [Anthropic Rate Limits](https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fapi\u002Frate-limits)\n- [tenacity Documentation](https:\u002F\u002Ftenacity.readthedocs.io\u002F)\n\n## Next Steps\nProceed to `langchain-security-basics` for security best practices.\n","# LangChain Rate Limits\n\n## Overview\nImplement robust rate limiting and retry strategies for LangChain applications to handle API quotas gracefully.\n\n## Prerequisites\n- LangChain installed with LLM provider\n- Understanding of provider rate limits\n- tenacity package for advanced retry logic\n\n## Instructions\n\n### Step 1: Understand Provider Limits\n```python\n# Common rate limits by provider:\nRATE_LIMITS = {\n    \"openai\": {\n        \"gpt-4o\": {\"rpm\": 10000, \"tpm\": 800000},\n        \"gpt-4o-mini\": {\"rpm\": 10000, \"tpm\": 4000000},\n    },\n    \"anthropic\": {\n        \"claude-3-5-sonnet\": {\"rpm\": 4000, \"tpm\": 400000},\n    },\n    \"google\": {\n        \"gemini-1.5-pro\": {\"rpm\": 360, \"tpm\": 4000000},\n    }\n}\n# rpm = requests per minute, tpm = tokens per minute\n```\n\n### Step 2: Built-in Retry Configuration\n```python\nfrom langchain_openai import ChatOpenAI\n\n# LangChain has built-in retry with exponential backoff\nllm = ChatOpenAI(\n    model=\"gpt-4o-mini\",\n    max_retries=3,  # Number of retries\n    request_timeout=30,  # Timeout per request\n)\n```\n\n### Step 3: Advanced Retry with Tenacity\n```python\nfrom tenacity import (\n    retry,\n    stop_after_attempt,\n    wait_exponential,\n    retry_if_exception_type\n)\nfrom openai import RateLimitError, APIError\n\n@retry(\n    stop=stop_after_attempt(5),\n    wait=wait_exponential(multiplier=1, min=4, max=60),\n    retry=retry_if_exception_type((RateLimitError, APIError))\n)\ndef call_with_retry(chain, input_data):\n    \"\"\"Call chain with exponential backoff.\"\"\"\n    return chain.invoke(input_data)\n\n# Usage\nresult = call_with_retry(chain, {\"input\": \"Hello\"})\n```\n\n### Step 4: Rate Limiter Wrapper\n```python\nimport asyncio\nimport time\nfrom collections import deque\nfrom threading import Lock\n\nclass RateLimiter:\n    \"\"\"Token bucket rate limiter for API calls.\"\"\"\n\n    def __init__(self, requests_per_minute: int = 60):\n        self.rpm = requests_per_minute\n        self.interval = 60.0 \u002F requests_per_minute\n        self.timestamps = deque()\n        self.lock = Lock()\n\n    def acquire(self):\n        \"\"\"Block until request can be made.\"\"\"\n        with self.lock:\n            now = time.time()\n            # Remove timestamps older than 1 minute\n            while self.timestamps and now - self.timestamps[0] > 60:\n                self.timestamps.popleft()\n\n            if len(self.timestamps) >= self.rpm:\n                sleep_time = 60 - (now - self.timestamps[0])\n                if sleep_time > 0:\n                    time.sleep(sleep_time)\n\n            self.timestamps.append(time.time())\n\n# Usage with LangChain\nrate_limiter = RateLimiter(requests_per_minute=100)\n\ndef rate_limited_call(chain, input_data):\n    rate_limiter.acquire()\n    return chain.invoke(input_data)\n```\n\n### Step 5: Async Rate Limiting\n```python\nimport asyncio\nfrom asyncio import Semaphore\n\nclass AsyncRateLimiter:\n    \"\"\"Async rate limiter with semaphore.\"\"\"\n\n    def __init__(self, max_concurrent: int = 10):\n        self.semaphore = Semaphore(max_concurrent)\n\n    async def call(self, chain, input_data):\n        async with self.semaphore:\n            return await chain.ainvoke(input_data)\n\n# Batch processing with rate limiting\nasync def process_batch(chain, inputs: list, max_concurrent: int = 5):\n    limiter = AsyncRateLimiter(max_concurrent)\n    tasks = [limiter.call(chain, inp) for inp in inputs]\n    return await asyncio.gather(*tasks, return_exceptions=True)\n```\n\n## Output\n- Configured retry logic with exponential backoff\n- Rate limiter class for request throttling\n- Async batch processing with concurrency control\n- Graceful handling of rate limit errors\n\n## Examples\n\n### Handling Rate Limits in Production\n```python\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.runnables import RunnableConfig\n\nllm = ChatOpenAI(\n    model=\"gpt-4o-mini\",\n    max_retries=5,\n)\n\n# Use batch with max_concurrency\ninputs = [{\"input\": f\"Query {i}\"} for i in range(100)]\n\nresults = chain.batch(\n    inputs,\n    config=RunnableConfig(max_concurrency=10)  # Limit concurrent calls\n)\n```\n\n### Fallback on Rate Limit\n```python\nfrom langchain_openai import ChatOpenAI\nfrom langchain_anthropic import ChatAnthropic\n\nprimary = ChatOpenAI(model=\"gpt-4o-mini\", max_retries=2)\nfallback = ChatAnthropic(model=\"claude-3-5-sonnet-20241022\")\n\n# Automatically switch to fallback on rate limit\nrobust_llm = primary.with_fallbacks([fallback])\n```\n\n## Error Handling\n| Error | Cause | Solution |\n|-------|-------|----------|\n| RateLimitError | Exceeded quota | Implement backoff, reduce concurrency |\n| Timeout | Request too slow | Increase timeout, check network |\n| 429 Too Many Requests | API throttled | Wait and retry with backoff |\n| Quota Exceeded | Monthly limit hit | Upgrade plan or switch provider |\n\n## Resources\n- [OpenAI Rate Limits](https:\u002F\u002Fplatform.openai.com\u002Fdocs\u002Fguides\u002Frate-limits)\n- [Anthropic Rate Limits](https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fapi\u002Frate-limits)\n- [tenacity Documentation](https:\u002F\u002Ftenacity.readthedocs.io\u002F)\n\n## Next Steps\nProceed to `langchain-security-basics` for security best practices.\n",{"name":5,"author":52,"license":15,"version":53,"description":54,"allowed-tools":55},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Implement LangChain rate limiting and backoff strategies.\nUse when handling API quotas, implementing retry logic,\nor optimizing request throughput for LLM providers.\nTrigger with phrases like \"langchain rate limit\", \"langchain throttling\",\n\"langchain backoff\", \"langchain retry\", \"API quota\".\n","Read, Write, Edit","main","90b50ed0778745a80fd5bfb13b1843d45b9e82f7","tests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Flangchain-pack\u002Fskills\u002Flangchain-rate-limits",233,"https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust","https:\u002F\u002Fgithub.com\u002FDicklesworthstone","https:\u002F\u002Fwww.jeffreyemanuel.com\u002F","Building in NY","2026-11-15 01:54:15",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add Dicklesworthstone\u002Fpi_agent_rust --skill langchain-rate-limits",{"tool":71,"command":72},"bunx","bunx skills add Dicklesworthstone\u002Fpi_agent_rust --skill langchain-rate-limits",{"tool":74,"command":75},"pnpm","pnpm dlx skills add Dicklesworthstone\u002Fpi_agent_rust --skill langchain-rate-limits","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-rate-limits\u002FSKILL.md",true,[],[80,119,143,169,196,218],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":93,"publishedAt":47},"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",[88],{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",[94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,40,112,113,114,115,116,27,117,118],"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","jsx","suite",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":123,"sourceHtmlUrl":124,"categories":125,"keywords":130,"publishedAt":47},"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",[126,129],{"categoryNo":127,"categoryName":128,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[131,132,133,99,134,135,95,136,137,138,109,139,140,141,142,32,27],"testing","webapp testing","webapp","screenshots","playwright","debugging","toolkit","browser","logs","applications","behavior","local",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":147,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":47},"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",[],[151,152,153,154,155,156,157,158,40,159,160,161,162,163,164,165,32,166,167,168,27,24],"analysis","neuropixels analysis","spike","metrics","data","open","quality","user","recordings","Neural","motion","visual","quality metrics","unit","sorting","curation","recording","load",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":173,"sourceHtmlUrl":174,"categories":175,"keywords":179,"publishedAt":47},"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",[176],{"categoryNo":177,"categoryName":178,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000023","Skill与智能体开发",[180,181,182,183,184,185,186,187,188,189,190,191,192,193,32,27,194,24,195],"skill creator","creator","workflows","create","update","capabilities","knowledge","tool","integrations","specialized","guide","new skill","existing skill","users","Existing","new",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":200,"sourceHtmlUrl":201,"categories":202,"keywords":204,"publishedAt":47},"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",[203],{"categoryNo":177,"categoryName":178,"taxonomyType":91,"taxonomyTypeDesc":92},[198,205,206,207,208,209,210,138,211,212,40,213,214,215,216,27,217],"google","browser automation","gemini","automation","auth","code","library","management","only","document","query","Citation","source",{"skillNo":219,"name":220,"nameZh":6,"description":221,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":84,"licenseFileUrl":222,"sourceHtmlUrl":223,"categories":224,"keywords":231,"publishedAt":47},"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",[225,228],{"categoryNo":226,"categoryName":227,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000005","邮件与沟通",{"categoryNo":229,"categoryName":230,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000016","图像与多媒体",[232,233,234,181,235,110,236,237,186,40,238,193,239,240,241,27,25,24],"slack gif creator","slack","gif","validation","constraints","Animation","me","make","Utilities","concepts"]