[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CFWH90QF3BH4FKSED9R8YP":3,"skill-same:01M7CFWH90QF3BH4FKSED9R8YP":50},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7CFWH90QF3BH4FKSED9R8YP","langfuse",null,"Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-bundle-llm-application-developer\u002Fskills\u002Flangfuse\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: langfuse\ndescription: Expert in Langfuse - the open-source LLM observability platform.\n  Covers tracing, prompt management, evaluation, datasets, and integration with\n  LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and\n  improving LLM applications in production.\nrisk: unknown\nsource: vibeship-spawner-skills (Apache 2.0)\ndate_added: 2026-02-27\n---\n\n# Langfuse\n\nExpert in Langfuse - the open-source LLM observability platform. Covers tracing,\nprompt management, evaluation, datasets, and integration with LangChain, LlamaIndex,\nand OpenAI. Essential for debugging, monitoring, and improving LLM applications\nin production.\n\n**Role**: LLM Observability Architect\n\nYou are an expert in LLM observability and evaluation. You think in terms of\ntraces, spans, and metrics. You know that LLM applications need monitoring\njust like traditional software - but with different dimensions (cost, quality,\nlatency). You use data to drive prompt improvements and catch regressions.\n\n### Expertise\n\n- Tracing architecture\n- Prompt versioning\n- Evaluation strategies\n- Cost optimization\n- Quality monitoring\n\n## Capabilities\n\n- LLM tracing and observability\n- Prompt management and versioning\n- Evaluation and scoring\n- Dataset management\n- Cost tracking\n- Performance monitoring\n- A\u002FB testing prompts\n\n## Prerequisites\n\n- 0: LLM application basics\n- 1: API integration experience\n- 2: Understanding of tracing concepts\n- Required skills: Python or TypeScript\u002FJavaScript, Langfuse account (cloud or self-hosted), LLM API keys\n\n## Scope\n\n- 0: Self-hosted requires infrastructure\n- 1: High-volume may need optimization\n- 2: Real-time dashboard has latency\n- 3: Evaluation requires setup\n\n## Ecosystem\n\n### Primary\n\n- Langfuse Cloud\n- Langfuse Self-hosted\n- Python SDK\n- JS\u002FTS SDK\n\n### Common_integrations\n\n- LangChain\n- LlamaIndex\n- OpenAI SDK\n- Anthropic SDK\n- Vercel AI SDK\n\n### Platforms\n\n- Any Python\u002FJS backend\n- Serverless functions\n- Jupyter notebooks\n\n## Patterns\n\n### Basic Tracing Setup\n\nInstrument LLM calls with Langfuse\n\n**When to use**: Any LLM application\n\nfrom langfuse import Langfuse\n\n# Initialize client\nlangfuse = Langfuse(\n    public_key=\"pk-...\",\n    secret_key=\"sk-...\",\n    host=\"https:\u002F\u002Fcloud.langfuse.com\"  # or self-hosted URL\n)\n\n# Create a trace for a user request\ntrace = langfuse.trace(\n    name=\"chat-completion\",\n    user_id=\"user-123\",\n    session_id=\"session-456\",  # Groups related traces\n    metadata={\"feature\": \"customer-support\"},\n    tags=[\"production\", \"v2\"]\n)\n\n# Log a generation (LLM call)\ngeneration = trace.generation(\n    name=\"gpt-4o-response\",\n    model=\"gpt-4o\",\n    model_parameters={\"temperature\": 0.7},\n    input={\"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}]},\n    metadata={\"attempt\": 1}\n)\n\n# Make actual LLM call\nresponse = openai.chat.completions.create(\n    model=\"gpt-4o\",\n    messages=[{\"role\": \"user\", \"content\": \"Hello\"}]\n)\n\n# Complete the generation with output\ngeneration.end(\n    output=response.choices[0].message.content,\n    usage={\n        \"input\": response.usage.prompt_tokens,\n        \"output\": response.usage.completion_tokens\n    }\n)\n\n# Score the trace\ntrace.score(\n    name=\"user-feedback\",\n    value=1,  # 1 = positive, 0 = negative\n    comment=\"User clicked helpful\"\n)\n\n# Flush before exit (important in serverless)\nlangfuse.flush()\n\n### OpenAI Integration\n\nAutomatic tracing with OpenAI SDK\n\n**When to use**: OpenAI-based applications\n\nfrom langfuse.openai import openai\n\n# Drop-in replacement for OpenAI client\n# All calls automatically traced\n\nresponse = openai.chat.completions.create(\n    model=\"gpt-4o\",\n    messages=[{\"role\": \"user\", \"content\": \"Hello\"}],\n    # Langfuse-specific parameters\n    name=\"greeting\",  # Trace name\n    session_id=\"session-123\",\n    user_id=\"user-456\",\n    tags=[\"test\"],\n    metadata={\"feature\": \"chat\"}\n)\n\n# Works with streaming\nstream = openai.chat.completions.create(\n    model=\"gpt-4o\",\n    messages=[{\"role\": \"user\", \"content\": \"Tell me a story\"}],\n    stream=True,\n    name=\"story-generation\"\n)\n\nfor chunk in stream:\n    print(chunk.choices[0].delta.content, end=\"\")\n\n# Works with async\nimport asyncio\nfrom langfuse.openai import AsyncOpenAI\n\nasync_client = AsyncOpenAI()\n\nasync def main():\n    response = await async_client.chat.completions.create(\n        model=\"gpt-4o\",\n        messages=[{\"role\": \"user\", \"content\": \"Hello\"}],\n        name=\"async-greeting\"\n    )\n\n### LangChain Integration\n\nTrace LangChain applications\n\n**When to use**: LangChain-based applications\n\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.prompts import ChatPromptTemplate\nfrom langfuse.callback import CallbackHandler\n\n# Create Langfuse callback handler\nlangfuse_handler = CallbackHandler(\n    public_key=\"pk-...\",\n    secret_key=\"sk-...\",\n    host=\"https:\u002F\u002Fcloud.langfuse.com\",\n    session_id=\"session-123\",\n    user_id=\"user-456\"\n)\n\n# Use with any LangChain component\nllm = ChatOpenAI(model=\"gpt-4o\")\n\nprompt = ChatPromptTemplate.from_messages([\n    (\"system\", \"You are a helpful assistant.\"),\n    (\"user\", \"{input}\")\n])\n\nchain = prompt | llm\n\n# Pass handler to invoke\nresponse = chain.invoke(\n    {\"input\": \"Hello\"},\n    config={\"callbacks\": [langfuse_handler]}\n)\n\n# Or set as default\nimport langchain\nlangchain.callbacks.manager.set_handler(langfuse_handler)\n\n# Then all calls are traced\nresponse = chain.invoke({\"input\": \"Hello\"})\n\n# Works with agents, retrievers, etc.\nfrom langchain.agents import create_openai_tools_agent\n\nagent = create_openai_tools_agent(llm, tools, prompt)\nagent_executor = AgentExecutor(agent=agent, tools=tools)\n\nresult = agent_executor.invoke(\n    {\"input\": \"What's the weather?\"},\n    config={\"callbacks\": [langfuse_handler]}\n)\n\n### Prompt Management\n\nVersion and deploy prompts\n\n**When to use**: Managing prompts across environments\n\nfrom langfuse import Langfuse\n\nlangfuse = Langfuse()\n\n# Fetch prompt from Langfuse\n# (Create in UI or via API first)\nprompt = langfuse.get_prompt(\"customer-support-v2\")\n\n# Get compiled prompt with variables\ncompiled = prompt.compile(\n    customer_name=\"John\",\n    issue=\"billing question\"\n)\n\n# Use with OpenAI\nresponse = openai.chat.completions.create(\n    model=prompt.config.get(\"model\", \"gpt-4o\"),\n    messages=compiled,\n    temperature=prompt.config.get(\"temperature\", 0.7)\n)\n\n# Link generation to prompt version\ntrace = langfuse.trace(name=\"support-chat\")\ngeneration = trace.generation(\n    name=\"response\",\n    model=\"gpt-4o\",\n    prompt=prompt  # Links to specific version\n)\n\n# Create\u002Fupdate prompts via API\nlangfuse.create_prompt(\n    name=\"customer-support-v3\",\n    prompt=[\n        {\"role\": \"system\", \"content\": \"You are a support agent...\"},\n        {\"role\": \"user\", \"content\": \"{{user_message}}\"}\n    ],\n    config={\n        \"model\": \"gpt-4o\",\n        \"temperature\": 0.7\n    },\n    labels=[\"production\"]  # or [\"staging\", \"development\"]\n)\n\n# Fetch specific label\nprompt = langfuse.get_prompt(\n    \"customer-support-v3\",\n    label=\"production\"  # Gets latest with this label\n)\n\n### Evaluation and Scoring\n\nEvaluate LLM outputs systematically\n\n**When to use**: Quality assurance and improvement\n\nfrom langfuse import Langfuse\n\nlangfuse = Langfuse()\n\n# Manual scoring in code\ntrace = langfuse.trace(name=\"qa-flow\")\n\n# After getting response\ntrace.score(\n    name=\"relevance\",\n    value=0.85,  # 0-1 scale\n    comment=\"Response addressed the question\"\n)\n\ntrace.score(\n    name=\"correctness\",\n    value=1,  # Binary: 0 or 1\n    data_type=\"BOOLEAN\"\n)\n\n# LLM-as-judge evaluation\ndef evaluate_response(question: str, response: str) -> float:\n    eval_prompt = f\"\"\"\n    Rate the response quality from 0 to 1.\n\n    Question: {question}\n    Response: {response}\n\n    Output only a number between 0 and 1.\n    \"\"\"\n\n    result = openai.chat.completions.create(\n        model=\"gpt-4o-mini\",  # Cheaper model for eval\n        messages=[{\"role\": \"user\", \"content\": eval_prompt}]\n    )\n\n    return float(result.choices[0].message.content.strip())\n\n# Score asynchronously\nscore = evaluate_response(question, response)\ntrace.score(\n    name=\"quality-llm-judge\",\n    value=score\n)\n\n# Create evaluation dataset\ndataset = langfuse.create_dataset(name=\"support-qa-v1\")\n\n# Add items to dataset\nlangfuse.create_dataset_item(\n    dataset_name=\"support-qa-v1\",\n    input={\"question\": \"How do I reset my password?\"},\n    expected_output=\"Go to settings > security > reset password\"\n)\n\n# Run evaluation on dataset\ndataset = langfuse.get_dataset(\"support-qa-v1\")\n\nfor item in dataset.items:\n    # Generate response\n    response = generate_response(item.input[\"question\"])\n\n    # Link to dataset item\n    trace = langfuse.trace(name=\"eval-run\")\n    trace.generation(\n        name=\"response\",\n        input=item.input,\n        output=response\n    )\n\n    # Score against expected\n    similarity = calculate_similarity(response, item.expected_output)\n    trace.score(name=\"similarity\", value=similarity)\n\n    # Link trace to dataset item\n    item.link(trace, \"eval-run-1\")\n\n### Decorator Pattern\n\nClean instrumentation with decorators\n\n**When to use**: Function-based applications\n\nfrom langfuse.decorators import observe, langfuse_context\n\n@observe()  # Creates a trace\ndef chat_handler(user_id: str, message: str) -> str:\n    # All nested @observe calls become spans\n    context = get_context(message)\n    response = generate_response(message, context)\n    return response\n\n@observe()  # Becomes a span under parent trace\ndef get_context(message: str) -> str:\n    # RAG retrieval\n    docs = retriever.get_relevant_documents(message)\n    return \"\\n\".join([d.page_content for d in docs])\n\n@observe(as_type=\"generation\")  # LLM generation span\ndef generate_response(message: str, context: str) -> str:\n    response = openai.chat.completions.create(\n        model=\"gpt-4o\",\n        messages=[\n            {\"role\": \"system\", \"content\": f\"Context: {context}\"},\n            {\"role\": \"user\", \"content\": message}\n        ]\n    )\n    return response.choices[0].message.content\n\n# Add metadata and scores\n@observe()\ndef main_flow(user_input: str):\n    # Update current trace\n    langfuse_context.update_current_trace(\n        user_id=\"user-123\",\n        session_id=\"session-456\",\n        tags=[\"production\"]\n    )\n\n    result = process(user_input)\n\n    # Score the trace\n    langfuse_context.score_current_trace(\n        name=\"success\",\n        value=1 if result else 0\n    )\n\n    return result\n\n# Works with async\n@observe()\nasync def async_handler(message: str):\n    result = await async_generate(message)\n    return result\n\n## Collaboration\n\n### Delegation Triggers\n\n- agent|langgraph|graph -> langgraph (Need to build agent to monitor)\n- crewai|multi-agent|crew -> crewai (Need to build crew to monitor)\n- structured output|extraction -> structured-output (Need to build extraction to monitor)\n\n### Observable LangGraph Agent\n\nSkills: langfuse, langgraph\n\nWorkflow:\n\n```\n1. Build agent with LangGraph\n2. Add Langfuse callback handler\n3. Trace all LLM calls and tool uses\n4. Score outputs for quality\n5. Monitor and iterate\n```\n\n### Monitored RAG Pipeline\n\nSkills: langfuse, structured-output\n\nWorkflow:\n\n```\n1. Build RAG with retrieval and generation\n2. Trace retrieval and LLM calls\n3. Score relevance and accuracy\n4. Track costs and latency\n5. Optimize based on data\n```\n\n### Evaluated Agent System\n\nSkills: langfuse, langgraph, structured-output\n\nWorkflow:\n\n```\n1. Build agent with structured outputs\n2. Create evaluation dataset\n3. Run evaluations with traces\n4. Compare prompt versions\n5. Deploy best performers\n```\n\n## Related Skills\n\nWorks well with: `langgraph`, `crewai`, `structured-output`, `autonomous-agents`\n\n## When to Use\n- User mentions or implies: langfuse\n- User mentions or implies: llm observability\n- User mentions or implies: llm tracing\n- User mentions or implies: prompt management\n- User mentions or implies: llm evaluation\n- User mentions or implies: monitor llm\n- User mentions or implies: debug llm\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","# Langfuse\n\nExpert in Langfuse - the open-source LLM observability platform. Covers tracing,\nprompt management, evaluation, datasets, and integration with LangChain, LlamaIndex,\nand OpenAI. Essential for debugging, monitoring, and improving LLM applications\nin production.\n\n**Role**: LLM Observability Architect\n\nYou are an expert in LLM observability and evaluation. You think in terms of\ntraces, spans, and metrics. You know that LLM applications need monitoring\njust like traditional software - but with different dimensions (cost, quality,\nlatency). You use data to drive prompt improvements and catch regressions.\n\n### Expertise\n\n- Tracing architecture\n- Prompt versioning\n- Evaluation strategies\n- Cost optimization\n- Quality monitoring\n\n## Capabilities\n\n- LLM tracing and observability\n- Prompt management and versioning\n- Evaluation and scoring\n- Dataset management\n- Cost tracking\n- Performance monitoring\n- A\u002FB testing prompts\n\n## Prerequisites\n\n- 0: LLM application basics\n- 1: API integration experience\n- 2: Understanding of tracing concepts\n- Required skills: Python or TypeScript\u002FJavaScript, Langfuse account (cloud or self-hosted), LLM API keys\n\n## Scope\n\n- 0: Self-hosted requires infrastructure\n- 1: High-volume may need optimization\n- 2: Real-time dashboard has latency\n- 3: Evaluation requires setup\n\n## Ecosystem\n\n### Primary\n\n- Langfuse Cloud\n- Langfuse Self-hosted\n- Python SDK\n- JS\u002FTS SDK\n\n### Common_integrations\n\n- LangChain\n- LlamaIndex\n- OpenAI SDK\n- Anthropic SDK\n- Vercel AI SDK\n\n### Platforms\n\n- Any Python\u002FJS backend\n- Serverless functions\n- Jupyter notebooks\n\n## Patterns\n\n### Basic Tracing Setup\n\nInstrument LLM calls with Langfuse\n\n**When to use**: Any LLM application\n\nfrom langfuse import Langfuse\n\n# Initialize client\nlangfuse = Langfuse(\n    public_key=\"pk-...\",\n    secret_key=\"sk-...\",\n    host=\"https:\u002F\u002Fcloud.langfuse.com\"  # or self-hosted URL\n)\n\n# Create a trace for a user request\ntrace = langfuse.trace(\n    name=\"chat-completion\",\n    user_id=\"user-123\",\n    session_id=\"session-456\",  # Groups related traces\n    metadata={\"feature\": \"customer-support\"},\n    tags=[\"production\", \"v2\"]\n)\n\n# Log a generation (LLM call)\ngeneration = trace.generation(\n    name=\"gpt-4o-response\",\n    model=\"gpt-4o\",\n    model_parameters={\"temperature\": 0.7},\n    input={\"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}]},\n    metadata={\"attempt\": 1}\n)\n\n# Make actual LLM call\nresponse = openai.chat.completions.create(\n    model=\"gpt-4o\",\n    messages=[{\"role\": \"user\", \"content\": \"Hello\"}]\n)\n\n# Complete the generation with output\ngeneration.end(\n    output=response.choices[0].message.content,\n    usage={\n        \"input\": response.usage.prompt_tokens,\n        \"output\": response.usage.completion_tokens\n    }\n)\n\n# Score the trace\ntrace.score(\n    name=\"user-feedback\",\n    value=1,  # 1 = positive, 0 = negative\n    comment=\"User clicked helpful\"\n)\n\n# Flush before exit (important in serverless)\nlangfuse.flush()\n\n### OpenAI Integration\n\nAutomatic tracing with OpenAI SDK\n\n**When to use**: OpenAI-based applications\n\nfrom langfuse.openai import openai\n\n# Drop-in replacement for OpenAI client\n# All calls automatically traced\n\nresponse = openai.chat.completions.create(\n    model=\"gpt-4o\",\n    messages=[{\"role\": \"user\", \"content\": \"Hello\"}],\n    # Langfuse-specific parameters\n    name=\"greeting\",  # Trace name\n    session_id=\"session-123\",\n    user_id=\"user-456\",\n    tags=[\"test\"],\n    metadata={\"feature\": \"chat\"}\n)\n\n# Works with streaming\nstream = openai.chat.completions.create(\n    model=\"gpt-4o\",\n    messages=[{\"role\": \"user\", \"content\": \"Tell me a story\"}],\n    stream=True,\n    name=\"story-generation\"\n)\n\nfor chunk in stream:\n    print(chunk.choices[0].delta.content, end=\"\")\n\n# Works with async\nimport asyncio\nfrom langfuse.openai import AsyncOpenAI\n\nasync_client = AsyncOpenAI()\n\nasync def main():\n    response = await async_client.chat.completions.create(\n        model=\"gpt-4o\",\n        messages=[{\"role\": \"user\", \"content\": \"Hello\"}],\n        name=\"async-greeting\"\n    )\n\n### LangChain Integration\n\nTrace LangChain applications\n\n**When to use**: LangChain-based applications\n\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.prompts import ChatPromptTemplate\nfrom langfuse.callback import CallbackHandler\n\n# Create Langfuse callback handler\nlangfuse_handler = CallbackHandler(\n    public_key=\"pk-...\",\n    secret_key=\"sk-...\",\n    host=\"https:\u002F\u002Fcloud.langfuse.com\",\n    session_id=\"session-123\",\n    user_id=\"user-456\"\n)\n\n# Use with any LangChain component\nllm = ChatOpenAI(model=\"gpt-4o\")\n\nprompt = ChatPromptTemplate.from_messages([\n    (\"system\", \"You are a helpful assistant.\"),\n    (\"user\", \"{input}\")\n])\n\nchain = prompt | llm\n\n# Pass handler to invoke\nresponse = chain.invoke(\n    {\"input\": \"Hello\"},\n    config={\"callbacks\": [langfuse_handler]}\n)\n\n# Or set as default\nimport langchain\nlangchain.callbacks.manager.set_handler(langfuse_handler)\n\n# Then all calls are traced\nresponse = chain.invoke({\"input\": \"Hello\"})\n\n# Works with agents, retrievers, etc.\nfrom langchain.agents import create_openai_tools_agent\n\nagent = create_openai_tools_agent(llm, tools, prompt)\nagent_executor = AgentExecutor(agent=agent, tools=tools)\n\nresult = agent_executor.invoke(\n    {\"input\": \"What's the weather?\"},\n    config={\"callbacks\": [langfuse_handler]}\n)\n\n### Prompt Management\n\nVersion and deploy prompts\n\n**When to use**: Managing prompts across environments\n\nfrom langfuse import Langfuse\n\nlangfuse = Langfuse()\n\n# Fetch prompt from Langfuse\n# (Create in UI or via API first)\nprompt = langfuse.get_prompt(\"customer-support-v2\")\n\n# Get compiled prompt with variables\ncompiled = prompt.compile(\n    customer_name=\"John\",\n    issue=\"billing question\"\n)\n\n# Use with OpenAI\nresponse = openai.chat.completions.create(\n    model=prompt.config.get(\"model\", \"gpt-4o\"),\n    messages=compiled,\n    temperature=prompt.config.get(\"temperature\", 0.7)\n)\n\n# Link generation to prompt version\ntrace = langfuse.trace(name=\"support-chat\")\ngeneration = trace.generation(\n    name=\"response\",\n    model=\"gpt-4o\",\n    prompt=prompt  # Links to specific version\n)\n\n# Create\u002Fupdate prompts via API\nlangfuse.create_prompt(\n    name=\"customer-support-v3\",\n    prompt=[\n        {\"role\": \"system\", \"content\": \"You are a support agent...\"},\n        {\"role\": \"user\", \"content\": \"{{user_message}}\"}\n    ],\n    config={\n        \"model\": \"gpt-4o\",\n        \"temperature\": 0.7\n    },\n    labels=[\"production\"]  # or [\"staging\", \"development\"]\n)\n\n# Fetch specific label\nprompt = langfuse.get_prompt(\n    \"customer-support-v3\",\n    label=\"production\"  # Gets latest with this label\n)\n\n### Evaluation and Scoring\n\nEvaluate LLM outputs systematically\n\n**When to use**: Quality assurance and improvement\n\nfrom langfuse import Langfuse\n\nlangfuse = Langfuse()\n\n# Manual scoring in code\ntrace = langfuse.trace(name=\"qa-flow\")\n\n# After getting response\ntrace.score(\n    name=\"relevance\",\n    value=0.85,  # 0-1 scale\n    comment=\"Response addressed the question\"\n)\n\ntrace.score(\n    name=\"correctness\",\n    value=1,  # Binary: 0 or 1\n    data_type=\"BOOLEAN\"\n)\n\n# LLM-as-judge evaluation\ndef evaluate_response(question: str, response: str) -> float:\n    eval_prompt = f\"\"\"\n    Rate the response quality from 0 to 1.\n\n    Question: {question}\n    Response: {response}\n\n    Output only a number between 0 and 1.\n    \"\"\"\n\n    result = openai.chat.completions.create(\n        model=\"gpt-4o-mini\",  # Cheaper model for eval\n        messages=[{\"role\": \"user\", \"content\": eval_prompt}]\n    )\n\n    return float(result.choices[0].message.content.strip())\n\n# Score asynchronously\nscore = evaluate_response(question, response)\ntrace.score(\n    name=\"quality-llm-judge\",\n    value=score\n)\n\n# Create evaluation dataset\ndataset = langfuse.create_dataset(name=\"support-qa-v1\")\n\n# Add items to dataset\nlangfuse.create_dataset_item(\n    dataset_name=\"support-qa-v1\",\n    input={\"question\": \"How do I reset my password?\"},\n    expected_output=\"Go to settings > security > reset password\"\n)\n\n# Run evaluation on dataset\ndataset = langfuse.get_dataset(\"support-qa-v1\")\n\nfor item in dataset.items:\n    # Generate response\n    response = generate_response(item.input[\"question\"])\n\n    # Link to dataset item\n    trace = langfuse.trace(name=\"eval-run\")\n    trace.generation(\n        name=\"response\",\n        input=item.input,\n        output=response\n    )\n\n    # Score against expected\n    similarity = calculate_similarity(response, item.expected_output)\n    trace.score(name=\"similarity\", value=similarity)\n\n    # Link trace to dataset item\n    item.link(trace, \"eval-run-1\")\n\n### Decorator Pattern\n\nClean instrumentation with decorators\n\n**When to use**: Function-based applications\n\nfrom langfuse.decorators import observe, langfuse_context\n\n@observe()  # Creates a trace\ndef chat_handler(user_id: str, message: str) -> str:\n    # All nested @observe calls become spans\n    context = get_context(message)\n    response = generate_response(message, context)\n    return response\n\n@observe()  # Becomes a span under parent trace\ndef get_context(message: str) -> str:\n    # RAG retrieval\n    docs = retriever.get_relevant_documents(message)\n    return \"\\n\".join([d.page_content for d in docs])\n\n@observe(as_type=\"generation\")  # LLM generation span\ndef generate_response(message: str, context: str) -> str:\n    response = openai.chat.completions.create(\n        model=\"gpt-4o\",\n        messages=[\n            {\"role\": \"system\", \"content\": f\"Context: {context}\"},\n            {\"role\": \"user\", \"content\": message}\n        ]\n    )\n    return response.choices[0].message.content\n\n# Add metadata and scores\n@observe()\ndef main_flow(user_input: str):\n    # Update current trace\n    langfuse_context.update_current_trace(\n        user_id=\"user-123\",\n        session_id=\"session-456\",\n        tags=[\"production\"]\n    )\n\n    result = process(user_input)\n\n    # Score the trace\n    langfuse_context.score_current_trace(\n        name=\"success\",\n        value=1 if result else 0\n    )\n\n    return result\n\n# Works with async\n@observe()\nasync def async_handler(message: str):\n    result = await async_generate(message)\n    return result\n\n## Collaboration\n\n### Delegation Triggers\n\n- agent|langgraph|graph -> langgraph (Need to build agent to monitor)\n- crewai|multi-agent|crew -> crewai (Need to build crew to monitor)\n- structured output|extraction -> structured-output (Need to build extraction to monitor)\n\n### Observable LangGraph Agent\n\nSkills: langfuse, langgraph\n\nWorkflow:\n\n```\n1. Build agent with LangGraph\n2. Add Langfuse callback handler\n3. Trace all LLM calls and tool uses\n4. Score outputs for quality\n5. Monitor and iterate\n```\n\n### Monitored RAG Pipeline\n\nSkills: langfuse, structured-output\n\nWorkflow:\n\n```\n1. Build RAG with retrieval and generation\n2. Trace retrieval and LLM calls\n3. Score relevance and accuracy\n4. Track costs and latency\n5. Optimize based on data\n```\n\n### Evaluated Agent System\n\nSkills: langfuse, langgraph, structured-output\n\nWorkflow:\n\n```\n1. Build agent with structured outputs\n2. Create evaluation dataset\n3. Run evaluations with traces\n4. Compare prompt versions\n5. Deploy best performers\n```\n\n## Related Skills\n\nWorks well with: `langgraph`, `crewai`, `structured-output`, `autonomous-agents`\n\n## When to Use\n- User mentions or implies: langfuse\n- User mentions or implies: llm observability\n- User mentions or implies: llm tracing\n- User mentions or implies: prompt management\n- User mentions or implies: llm evaluation\n- User mentions or implies: monitor llm\n- User mentions or implies: debug llm\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":24,"source":25,"date_added":26,"description":7},"unknown","vibeship-spawner-skills (Apache 2.0)",1772150400000,"main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-bundle-llm-application-developer\u002Fskills\u002Flangfuse",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill langfuse",{"tool":42,"command":43},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill langfuse",{"tool":45,"command":46},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill langfuse","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-bundle-llm-application-developer\u002Fskills\u002Flangfuse\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]