[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6F7KRZJ3GHCKJNF2Z52XAEW":3,"skill-same:01M6F7KRZJ3GHCKJNF2Z52XAEW":80},{"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":23,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":6,"ownerHtmlUrl":62,"ownerBlogUrl":63,"ownerDescription":64,"updatedAt":65,"install":66,"resources":79},"01M6F7KRZJ3GHCKJNF2Z52XAEW","langchain-cost-tuning",null,"Optimize LangChain API costs and token usage.\nUse when reducing LLM API expenses, implementing cost controls,\nor optimizing token consumption in production.\nTrigger with phrases like \"langchain cost\", \"langchain tokens\",\n\"reduce langchain cost\", \"langchain billing\", \"langchain budget\".","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-cost-tuning\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000040","财务","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"tuning","langchain","langchain cost tuning","cost","when","Production","reduce","implementing","usage","expenses","with","billing","controls","trigger","io","tokens","token","optimize","use","edit","write","read","api","Budget","2026-11-10 10:12:30",false,"---\nname: langchain-cost-tuning\ndescription: |\n  Optimize LangChain API costs and token usage.\n  Use when reducing LLM API expenses, implementing cost controls,\n  or optimizing token consumption in production.\n  Trigger with phrases like \"langchain cost\", \"langchain tokens\",\n  \"reduce langchain cost\", \"langchain billing\", \"langchain budget\".\nallowed-tools: Read, Write, Edit\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\n---\n\n# LangChain Cost Tuning\n\n## Overview\nStrategies for reducing LLM API costs while maintaining quality in LangChain applications.\n\n## Prerequisites\n- LangChain application in production\n- Access to API usage dashboard\n- Understanding of token pricing\n\n## Instructions\n\n### Step 1: Understand Token Pricing\n```python\n# Current approximate pricing (check provider for current rates)\nPRICING = {\n    \"openai\": {\n        \"gpt-4o\": {\"input\": 0.005, \"output\": 0.015},      # per 1K tokens\n        \"gpt-4o-mini\": {\"input\": 0.00015, \"output\": 0.0006},\n        \"gpt-3.5-turbo\": {\"input\": 0.0005, \"output\": 0.0015},\n    },\n    \"anthropic\": {\n        \"claude-3-5-sonnet\": {\"input\": 0.003, \"output\": 0.015},\n        \"claude-3-haiku\": {\"input\": 0.00025, \"output\": 0.00125},\n    },\n    \"google\": {\n        \"gemini-1.5-pro\": {\"input\": 0.00125, \"output\": 0.005},\n        \"gemini-1.5-flash\": {\"input\": 0.000075, \"output\": 0.0003},\n    }\n}\n\ndef estimate_cost(\n    input_tokens: int,\n    output_tokens: int,\n    model: str = \"gpt-4o-mini\"\n) -> float:\n    \"\"\"Estimate API cost for a request.\"\"\"\n    provider, model_name = model.split(\"\u002F\") if \"\u002F\" in model else (\"openai\", model)\n    rates = PRICING.get(provider, {}).get(model_name, {\"input\": 0.001, \"output\": 0.002})\n    return (input_tokens \u002F 1000 * rates[\"input\"]) + (output_tokens \u002F 1000 * rates[\"output\"])\n```\n\n### Step 2: Implement Token Counting\n```python\nimport tiktoken\nfrom langchain_core.callbacks import BaseCallbackHandler\n\nclass CostTrackingCallback(BaseCallbackHandler):\n    \"\"\"Track token usage and costs.\"\"\"\n\n    def __init__(self, model: str = \"gpt-4o-mini\"):\n        self.model = model\n        self.total_input_tokens = 0\n        self.total_output_tokens = 0\n        self.requests = 0\n\n    def on_llm_end(self, response, **kwargs) -> None:\n        \"\"\"Track tokens from LLM response.\"\"\"\n        if response.llm_output and \"token_usage\" in response.llm_output:\n            usage = response.llm_output[\"token_usage\"]\n            self.total_input_tokens += usage.get(\"prompt_tokens\", 0)\n            self.total_output_tokens += usage.get(\"completion_tokens\", 0)\n            self.requests += 1\n\n    @property\n    def total_cost(self) -> float:\n        return estimate_cost(\n            self.total_input_tokens,\n            self.total_output_tokens,\n            self.model\n        )\n\n    def report(self) -> dict:\n        return {\n            \"requests\": self.requests,\n            \"input_tokens\": self.total_input_tokens,\n            \"output_tokens\": self.total_output_tokens,\n            \"total_tokens\": self.total_input_tokens + self.total_output_tokens,\n            \"estimated_cost\": f\"${self.total_cost:.4f}\"\n        }\n\n# Usage\ntracker = CostTrackingCallback()\nllm = ChatOpenAI(model=\"gpt-4o-mini\", callbacks=[tracker])\n\n# After operations\nprint(tracker.report())\n```\n\n### Step 3: Optimize Prompt Length\n```python\nimport tiktoken\n\ndef optimize_prompt(\n    text: str,\n    max_tokens: int = 2000,\n    model: str = \"gpt-4o-mini\"\n) -> str:\n    \"\"\"Truncate text to fit within token budget.\"\"\"\n    encoding = tiktoken.encoding_for_model(model)\n    tokens = encoding.encode(text)\n\n    if len(tokens) \u003C= max_tokens:\n        return text\n\n    # Truncate and add indicator\n    truncated = encoding.decode(tokens[:max_tokens - 10])\n    return truncated + \"... [truncated]\"\n\ndef summarize_context(long_text: str, llm) -> str:\n    \"\"\"Summarize long context to reduce tokens.\"\"\"\n    if count_tokens(long_text) \u003C 2000:\n        return long_text\n\n    summary_prompt = ChatPromptTemplate.from_template(\n        \"Summarize this text in 500 words or less, preserving key facts:\\n\\n{text}\"\n    )\n    chain = summary_prompt | llm | StrOutputParser()\n    return chain.invoke({\"text\": long_text})\n```\n\n### Step 4: Model Tiering Strategy\n```python\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.runnables import RunnableBranch\n\n# Define model tiers\nllm_cheap = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)    # $0.15\u002F1M tokens\nllm_medium = ChatOpenAI(model=\"gpt-4o\", temperature=0)         # $5\u002F1M tokens\nllm_powerful = ChatOpenAI(model=\"o1\", temperature=0)           # $15\u002F1M tokens\n\ndef select_model(input_data: dict) -> str:\n    \"\"\"Route to appropriate model based on task.\"\"\"\n    task_type = input_data.get(\"task_type\", \"simple\")\n\n    if task_type in [\"chat\", \"faq\", \"simple\"]:\n        return \"cheap\"\n    elif task_type in [\"analysis\", \"summary\", \"medium\"]:\n        return \"medium\"\n    else:\n        return \"powerful\"\n\nrouter = RunnableBranch(\n    (lambda x: select_model(x) == \"cheap\", prompt | llm_cheap),\n    (lambda x: select_model(x) == \"medium\", prompt | llm_medium),\n    prompt | llm_powerful\n)\n\n# Simple chat: ~$0.0001 per request\n# Complex analysis: ~$0.01 per request\n# Cost reduction: 100x for simple tasks\n```\n\n### Step 5: Implement Caching\n```python\nfrom langchain_core.globals import set_llm_cache\nfrom langchain_community.cache import RedisSemanticCache\nfrom langchain_openai import OpenAIEmbeddings\n\n# Semantic caching - finds similar queries\nembeddings = OpenAIEmbeddings(model=\"text-embedding-3-small\")\nset_llm_cache(RedisSemanticCache(\n    redis_url=\"redis:\u002F\u002Flocalhost:6379\",\n    embedding=embeddings,\n    score_threshold=0.95  # High similarity required\n))\n\n# Example savings:\n# - \"What is Python?\" and \"What's Python?\" -> Same cached response\n# - 100 similar queries -> 1 API call + 99 cache hits\n# - Potential 99% cost reduction for repetitive queries\n```\n\n### Step 6: Set Budget Limits\n```python\nclass BudgetLimitCallback(BaseCallbackHandler):\n    \"\"\"Enforce budget limits.\"\"\"\n\n    def __init__(self, daily_budget: float = 10.0, model: str = \"gpt-4o-mini\"):\n        self.daily_budget = daily_budget\n        self.model = model\n        self.daily_spend = 0.0\n        self.last_reset = datetime.now().date()\n\n    def on_llm_start(self, serialized, prompts, **kwargs) -> None:\n        \"\"\"Check budget before request.\"\"\"\n        today = datetime.now().date()\n        if today != self.last_reset:\n            self.daily_spend = 0.0\n            self.last_reset = today\n\n        if self.daily_spend >= self.daily_budget:\n            raise RuntimeError(f\"Daily budget of ${self.daily_budget} exceeded\")\n\n    def on_llm_end(self, response, **kwargs) -> None:\n        \"\"\"Update spend after request.\"\"\"\n        if response.llm_output and \"token_usage\" in response.llm_output:\n            usage = response.llm_output[\"token_usage\"]\n            cost = estimate_cost(\n                usage.get(\"prompt_tokens\", 0),\n                usage.get(\"completion_tokens\", 0),\n                self.model\n            )\n            self.daily_spend += cost\n\n# Usage\nbudget_callback = BudgetLimitCallback(daily_budget=50.0)\nllm = ChatOpenAI(model=\"gpt-4o-mini\", callbacks=[budget_callback])\n```\n\n## Cost Optimization Summary\n| Strategy | Potential Savings | Implementation Effort |\n|----------|-------------------|----------------------|\n| Model tiering | 50-100x | Medium |\n| Response caching | 50-99% | Low |\n| Prompt optimization | 10-50% | Low |\n| Semantic caching | 30-70% | Medium |\n| Budget limits | Risk mitigation | Low |\n\n## Output\n- Token counting and cost tracking\n- Prompt optimization utilities\n- Model routing for cost efficiency\n- Budget enforcement callbacks\n\n## Resources\n- [OpenAI Pricing](https:\u002F\u002Fopenai.com\u002Fpricing)\n- [Anthropic Pricing](https:\u002F\u002Fwww.anthropic.com\u002Fpricing)\n- [tiktoken](https:\u002F\u002Fgithub.com\u002Fopenai\u002Ftiktoken)\n\n## Next Steps\nUse `langchain-reference-architecture` for scalable production patterns.\n","# LangChain Cost Tuning\n\n## Overview\nStrategies for reducing LLM API costs while maintaining quality in LangChain applications.\n\n## Prerequisites\n- LangChain application in production\n- Access to API usage dashboard\n- Understanding of token pricing\n\n## Instructions\n\n### Step 1: Understand Token Pricing\n```python\n# Current approximate pricing (check provider for current rates)\nPRICING = {\n    \"openai\": {\n        \"gpt-4o\": {\"input\": 0.005, \"output\": 0.015},      # per 1K tokens\n        \"gpt-4o-mini\": {\"input\": 0.00015, \"output\": 0.0006},\n        \"gpt-3.5-turbo\": {\"input\": 0.0005, \"output\": 0.0015},\n    },\n    \"anthropic\": {\n        \"claude-3-5-sonnet\": {\"input\": 0.003, \"output\": 0.015},\n        \"claude-3-haiku\": {\"input\": 0.00025, \"output\": 0.00125},\n    },\n    \"google\": {\n        \"gemini-1.5-pro\": {\"input\": 0.00125, \"output\": 0.005},\n        \"gemini-1.5-flash\": {\"input\": 0.000075, \"output\": 0.0003},\n    }\n}\n\ndef estimate_cost(\n    input_tokens: int,\n    output_tokens: int,\n    model: str = \"gpt-4o-mini\"\n) -> float:\n    \"\"\"Estimate API cost for a request.\"\"\"\n    provider, model_name = model.split(\"\u002F\") if \"\u002F\" in model else (\"openai\", model)\n    rates = PRICING.get(provider, {}).get(model_name, {\"input\": 0.001, \"output\": 0.002})\n    return (input_tokens \u002F 1000 * rates[\"input\"]) + (output_tokens \u002F 1000 * rates[\"output\"])\n```\n\n### Step 2: Implement Token Counting\n```python\nimport tiktoken\nfrom langchain_core.callbacks import BaseCallbackHandler\n\nclass CostTrackingCallback(BaseCallbackHandler):\n    \"\"\"Track token usage and costs.\"\"\"\n\n    def __init__(self, model: str = \"gpt-4o-mini\"):\n        self.model = model\n        self.total_input_tokens = 0\n        self.total_output_tokens = 0\n        self.requests = 0\n\n    def on_llm_end(self, response, **kwargs) -> None:\n        \"\"\"Track tokens from LLM response.\"\"\"\n        if response.llm_output and \"token_usage\" in response.llm_output:\n            usage = response.llm_output[\"token_usage\"]\n            self.total_input_tokens += usage.get(\"prompt_tokens\", 0)\n            self.total_output_tokens += usage.get(\"completion_tokens\", 0)\n            self.requests += 1\n\n    @property\n    def total_cost(self) -> float:\n        return estimate_cost(\n            self.total_input_tokens,\n            self.total_output_tokens,\n            self.model\n        )\n\n    def report(self) -> dict:\n        return {\n            \"requests\": self.requests,\n            \"input_tokens\": self.total_input_tokens,\n            \"output_tokens\": self.total_output_tokens,\n            \"total_tokens\": self.total_input_tokens + self.total_output_tokens,\n            \"estimated_cost\": f\"${self.total_cost:.4f}\"\n        }\n\n# Usage\ntracker = CostTrackingCallback()\nllm = ChatOpenAI(model=\"gpt-4o-mini\", callbacks=[tracker])\n\n# After operations\nprint(tracker.report())\n```\n\n### Step 3: Optimize Prompt Length\n```python\nimport tiktoken\n\ndef optimize_prompt(\n    text: str,\n    max_tokens: int = 2000,\n    model: str = \"gpt-4o-mini\"\n) -> str:\n    \"\"\"Truncate text to fit within token budget.\"\"\"\n    encoding = tiktoken.encoding_for_model(model)\n    tokens = encoding.encode(text)\n\n    if len(tokens) \u003C= max_tokens:\n        return text\n\n    # Truncate and add indicator\n    truncated = encoding.decode(tokens[:max_tokens - 10])\n    return truncated + \"... [truncated]\"\n\ndef summarize_context(long_text: str, llm) -> str:\n    \"\"\"Summarize long context to reduce tokens.\"\"\"\n    if count_tokens(long_text) \u003C 2000:\n        return long_text\n\n    summary_prompt = ChatPromptTemplate.from_template(\n        \"Summarize this text in 500 words or less, preserving key facts:\\n\\n{text}\"\n    )\n    chain = summary_prompt | llm | StrOutputParser()\n    return chain.invoke({\"text\": long_text})\n```\n\n### Step 4: Model Tiering Strategy\n```python\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.runnables import RunnableBranch\n\n# Define model tiers\nllm_cheap = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0)    # $0.15\u002F1M tokens\nllm_medium = ChatOpenAI(model=\"gpt-4o\", temperature=0)         # $5\u002F1M tokens\nllm_powerful = ChatOpenAI(model=\"o1\", temperature=0)           # $15\u002F1M tokens\n\ndef select_model(input_data: dict) -> str:\n    \"\"\"Route to appropriate model based on task.\"\"\"\n    task_type = input_data.get(\"task_type\", \"simple\")\n\n    if task_type in [\"chat\", \"faq\", \"simple\"]:\n        return \"cheap\"\n    elif task_type in [\"analysis\", \"summary\", \"medium\"]:\n        return \"medium\"\n    else:\n        return \"powerful\"\n\nrouter = RunnableBranch(\n    (lambda x: select_model(x) == \"cheap\", prompt | llm_cheap),\n    (lambda x: select_model(x) == \"medium\", prompt | llm_medium),\n    prompt | llm_powerful\n)\n\n# Simple chat: ~$0.0001 per request\n# Complex analysis: ~$0.01 per request\n# Cost reduction: 100x for simple tasks\n```\n\n### Step 5: Implement Caching\n```python\nfrom langchain_core.globals import set_llm_cache\nfrom langchain_community.cache import RedisSemanticCache\nfrom langchain_openai import OpenAIEmbeddings\n\n# Semantic caching - finds similar queries\nembeddings = OpenAIEmbeddings(model=\"text-embedding-3-small\")\nset_llm_cache(RedisSemanticCache(\n    redis_url=\"redis:\u002F\u002Flocalhost:6379\",\n    embedding=embeddings,\n    score_threshold=0.95  # High similarity required\n))\n\n# Example savings:\n# - \"What is Python?\" and \"What's Python?\" -> Same cached response\n# - 100 similar queries -> 1 API call + 99 cache hits\n# - Potential 99% cost reduction for repetitive queries\n```\n\n### Step 6: Set Budget Limits\n```python\nclass BudgetLimitCallback(BaseCallbackHandler):\n    \"\"\"Enforce budget limits.\"\"\"\n\n    def __init__(self, daily_budget: float = 10.0, model: str = \"gpt-4o-mini\"):\n        self.daily_budget = daily_budget\n        self.model = model\n        self.daily_spend = 0.0\n        self.last_reset = datetime.now().date()\n\n    def on_llm_start(self, serialized, prompts, **kwargs) -> None:\n        \"\"\"Check budget before request.\"\"\"\n        today = datetime.now().date()\n        if today != self.last_reset:\n            self.daily_spend = 0.0\n            self.last_reset = today\n\n        if self.daily_spend >= self.daily_budget:\n            raise RuntimeError(f\"Daily budget of ${self.daily_budget} exceeded\")\n\n    def on_llm_end(self, response, **kwargs) -> None:\n        \"\"\"Update spend after request.\"\"\"\n        if response.llm_output and \"token_usage\" in response.llm_output:\n            usage = response.llm_output[\"token_usage\"]\n            cost = estimate_cost(\n                usage.get(\"prompt_tokens\", 0),\n                usage.get(\"completion_tokens\", 0),\n                self.model\n            )\n            self.daily_spend += cost\n\n# Usage\nbudget_callback = BudgetLimitCallback(daily_budget=50.0)\nllm = ChatOpenAI(model=\"gpt-4o-mini\", callbacks=[budget_callback])\n```\n\n## Cost Optimization Summary\n| Strategy | Potential Savings | Implementation Effort |\n|----------|-------------------|----------------------|\n| Model tiering | 50-100x | Medium |\n| Response caching | 50-99% | Low |\n| Prompt optimization | 10-50% | Low |\n| Semantic caching | 30-70% | Medium |\n| Budget limits | Risk mitigation | Low |\n\n## Output\n- Token counting and cost tracking\n- Prompt optimization utilities\n- Model routing for cost efficiency\n- Budget enforcement callbacks\n\n## Resources\n- [OpenAI Pricing](https:\u002F\u002Fopenai.com\u002Fpricing)\n- [Anthropic Pricing](https:\u002F\u002Fwww.anthropic.com\u002Fpricing)\n- [tiktoken](https:\u002F\u002Fgithub.com\u002Fopenai\u002Ftiktoken)\n\n## Next Steps\nUse `langchain-reference-architecture` for scalable production patterns.\n",{"name":5,"author":53,"license":15,"version":54,"description":55,"allowed-tools":56},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Optimize LangChain API costs and token usage.\nUse when reducing LLM API expenses, implementing cost controls,\nor optimizing token consumption in production.\nTrigger with phrases like \"langchain cost\", \"langchain tokens\",\n\"reduce langchain cost\", \"langchain billing\", \"langchain budget\".\n","Read, Write, Edit","main","90b50ed0778745a80fd5bfb13b1843d45b9e82f7","tests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Flangchain-pack\u002Fskills\u002Flangchain-cost-tuning",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":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add Dicklesworthstone\u002Fpi_agent_rust --skill langchain-cost-tuning",{"tool":72,"command":73},"bunx","bunx skills add Dicklesworthstone\u002Fpi_agent_rust --skill langchain-cost-tuning",{"tool":75,"command":76},"pnpm","pnpm dlx skills add Dicklesworthstone\u002Fpi_agent_rust --skill langchain-cost-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-cost-tuning\u002FSKILL.md",true,[],[81,114,149,172,198,225],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":86,"sourceHtmlUrl":87,"categories":88,"keywords":94,"publishedAt":113},"01M6FCR7G5A005P364Z6ZWCJDP","theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors\u002Ffonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcreative-design\u002Ftheme-factory\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FDicklesworthstone\u002Fpi_agent_rust\u002Fblob\u002Fmain\u002Ftests\u002Fext_conformance\u002Fartifacts\u002Ftemplates-davila7\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fcreative-design\u002Ftheme-factory\u002FSKILL.md",[89],{"categoryNo":90,"categoryName":91,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",[95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,34,111,112],"theme factory","factory","theme","docs","toolkit","generate","artifacts","SET","fly","slides","landing","html","styling","artifact","pages","themes","you","fonts","2026-11-11 15:11:14",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":124,"publishedAt":48},"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.","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",[121],{"categoryNo":122,"categoryName":123,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000009","前端开发",[125,126,101,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,42,106,142,143,144,145,146,147,148],"web artifacts builder","web","artifacts builder","builder","frontend","css","components","react","component","routing","state management","state","shadcn","file","ui","Tools","Tailwind","single-file","simple","ui components","multi","for","jsx","suite",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":153,"sourceHtmlUrl":154,"categories":155,"keywords":160,"publishedAt":48},"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",[156,159],{"categoryNo":157,"categoryName":158,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":122,"categoryName":123,"taxonomyType":92,"taxonomyTypeDesc":93},[161,162,163,129,164,165,126,166,99,167,139,168,169,170,171,34,146],"testing","webapp testing","webapp","screenshots","playwright","debugging","browser","logs","applications","behavior","local",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":176,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":48},"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",[],[180,181,182,183,184,185,186,187,42,188,189,190,191,192,193,194,34,195,196,197,146,28],"analysis","neuropixels analysis","spike","metrics","data","open","quality","user","recordings","Neural","motion","visual","quality metrics","unit","sorting","curation","recording","load",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":85,"licenseFileUrl":202,"sourceHtmlUrl":203,"categories":204,"keywords":208,"publishedAt":48},"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",[205],{"categoryNo":206,"categoryName":207,"taxonomyType":92,"taxonomyTypeDesc":93},"01JBSEEDCAT000000000000023","Skill与智能体开发",[209,210,211,212,213,214,215,216,217,218,219,220,221,222,34,146,223,28,224],"skill creator","creator","workflows","create","update","capabilities","knowledge","tool","integrations","specialized","guide","new skill","existing skill","users","Existing","new",{"skillNo":226,"name":227,"nameZh":6,"description":228,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":229,"sourceHtmlUrl":230,"categories":231,"keywords":233,"publishedAt":48},"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",[232],{"categoryNo":206,"categoryName":207,"taxonomyType":92,"taxonomyTypeDesc":93},[227,234,235,236,237,238,239,167,240,241,42,242,243,244,245,146,246],"google","browser automation","gemini","automation","auth","code","library","management","only","document","query","Citation","source"]