[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6F7PKBA2MKM27KTFB8EW32Y":3,"skill-same:01M6F7PKBA2MKM27KTFB8EW32Y":81},{"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":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":6,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":80},"01M6F7PKBA2MKM27KTFB8EW32Y","langfuse-core-workflow-a",null,"Execute Langfuse primary workflow: Tracing LLM calls and spans.\nUse when implementing LLM tracing, building traced AI features,\nor adding observability to existing LLM applications.\nTrigger with phrases like \"langfuse tracing\", \"trace LLM calls\",\n\"add langfuse to openai\", \"langfuse spans\", \"track llm requests\".","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\u002Flangfuse-pack\u002Fskills\u002Flangfuse-core-workflow-a\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"core","workflow","langfuse","langfuse core workflow a","when","track","features","implementing","with","LLM Applications","add","trigger","io","use","execute","edit","write","read","grep","Bash","applications","tracing","observability","npm","openai","2026-11-10 10:12:30",false,"---\nname: langfuse-core-workflow-a\ndescription: |\n  Execute Langfuse primary workflow: Tracing LLM calls and spans.\n  Use when implementing LLM tracing, building traced AI features,\n  or adding observability to existing LLM applications.\n  Trigger with phrases like \"langfuse tracing\", \"trace LLM calls\",\n  \"add langfuse to openai\", \"langfuse spans\", \"track llm requests\".\nallowed-tools: Read, Write, Edit, Bash(npm:*), Grep\nversion: 1.0.0\nlicense: MIT\nauthor: Jeremy Longshore \u003Cjeremy@intentsolutions.io>\n---\n\n# Langfuse Core Workflow A: Tracing LLM Calls\n\n## Overview\nPrimary workflow for Langfuse: end-to-end tracing of LLM calls, chains, and agents.\n\n## Prerequisites\n- Completed `langfuse-install-auth` setup\n- Understanding of Langfuse trace hierarchy\n- LLM provider SDK (OpenAI, Anthropic, etc.)\n\n## Instructions\n\n### Step 1: Set Up Automatic OpenAI Tracing\n\n```typescript\nimport { observeOpenAI } from \"langfuse\";\nimport OpenAI from \"openai\";\n\n\u002F\u002F Wrap OpenAI client for automatic tracing\nconst openai = observeOpenAI(new OpenAI());\n\n\u002F\u002F All calls are now automatically traced\nconst response = await openai.chat.completions.create({\n  model: \"gpt-4\",\n  messages: [\n    { role: \"system\", content: \"You are a helpful assistant.\" },\n    { role: \"user\", content: \"What is Langfuse?\" },\n  ],\n});\n```\n\n### Step 2: Manual Tracing for Complex Flows\n\n```typescript\nimport { Langfuse } from \"langfuse\";\n\nconst langfuse = new Langfuse();\n\nasync function ragPipeline(query: string) {\n  \u002F\u002F Create top-level trace\n  const trace = langfuse.trace({\n    name: \"rag-pipeline\",\n    input: { query },\n    metadata: { pipeline: \"rag-v1\" },\n  });\n\n  \u002F\u002F Span: Query embedding\n  const embedSpan = trace.span({\n    name: \"embed-query\",\n    input: { text: query },\n  });\n\n  const queryEmbedding = await embedText(query);\n\n  embedSpan.end({\n    output: { dimensions: queryEmbedding.length },\n    metadata: { model: \"text-embedding-ada-002\" },\n  });\n\n  \u002F\u002F Span: Vector search\n  const searchSpan = trace.span({\n    name: \"vector-search\",\n    input: { embedding: \"vector[1536]\" },\n  });\n\n  const documents = await searchVectorDB(queryEmbedding);\n\n  searchSpan.end({\n    output: {\n      documentCount: documents.length,\n      topScore: documents[0]?.score,\n    },\n  });\n\n  \u002F\u002F Generation: LLM call with context\n  const generation = trace.generation({\n    name: \"generate-answer\",\n    model: \"gpt-4\",\n    modelParameters: { temperature: 0.7, maxTokens: 500 },\n    input: {\n      query,\n      context: documents.map((d) => d.content),\n    },\n  });\n\n  const answer = await generateAnswer(query, documents);\n\n  generation.end({\n    output: answer.content,\n    usage: {\n      promptTokens: answer.usage.prompt_tokens,\n      completionTokens: answer.usage.completion_tokens,\n      totalTokens: answer.usage.total_tokens,\n    },\n  });\n\n  \u002F\u002F Update trace with final output\n  trace.update({\n    output: { answer: answer.content },\n  });\n\n  return answer.content;\n}\n```\n\n### Step 3: Trace Streaming Responses\n\n```typescript\nasync function streamingChat(messages: ChatMessage[]) {\n  const trace = langfuse.trace({\n    name: \"streaming-chat\",\n    input: { messages },\n  });\n\n  const generation = trace.generation({\n    name: \"stream-response\",\n    model: \"gpt-4\",\n    input: messages,\n  });\n\n  const stream = await openai.chat.completions.create({\n    model: \"gpt-4\",\n    messages,\n    stream: true,\n  });\n\n  let fullContent = \"\";\n  let usage = { promptTokens: 0, completionTokens: 0 };\n\n  for await (const chunk of stream) {\n    const content = chunk.choices[0]?.delta?.content || \"\";\n    fullContent += content;\n\n    \u002F\u002F Track usage from final chunk\n    if (chunk.usage) {\n      usage = {\n        promptTokens: chunk.usage.prompt_tokens,\n        completionTokens: chunk.usage.completion_tokens,\n      };\n    }\n\n    yield content;\n  }\n\n  \u002F\u002F End generation after stream completes\n  generation.end({\n    output: fullContent,\n    usage,\n  });\n\n  trace.update({ output: { response: fullContent } });\n}\n```\n\n### Step 4: Link Traces to Parent Operations\n\n```typescript\n\u002F\u002F API endpoint that creates parent trace\nasync function handleChatRequest(req: Request) {\n  const trace = langfuse.trace({\n    name: \"api\u002Fchat\",\n    userId: req.userId,\n    sessionId: req.sessionId,\n    input: req.body,\n  });\n\n  \u002F\u002F Pass trace to child operations\n  const response = await processChat(trace, req.body.message);\n\n  return response;\n}\n\n\u002F\u002F Child function receives parent trace\nasync function processChat(\n  parentTrace: ReturnType\u003Ctypeof langfuse.trace>,\n  message: string\n) {\n  \u002F\u002F Create child span under parent trace\n  const span = parentTrace.span({\n    name: \"process-chat\",\n    input: { message },\n  });\n\n  \u002F\u002F OpenAI call linked to parent\n  const response = await openai.chat.completions.create(\n    {\n      model: \"gpt-4\",\n      messages: [{ role: \"user\", content: message }],\n    },\n    { langfuseParent: span } \u002F\u002F Link generation to span\n  );\n\n  span.end({ output: response.choices[0].message });\n  return response.choices[0].message.content;\n}\n```\n\n## Output\n- Automatic OpenAI tracing with zero code changes\n- Manual tracing for RAG and complex pipelines\n- Streaming response tracking\n- Linked parent-child trace hierarchy\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Missing generations | Wrapper not applied | Use `observeOpenAI()` wrapper |\n| Orphaned spans | Missing `.end()` call | Always end spans in finally block |\n| No token usage | Stream without usage | Use `stream_options: {include_usage: true}` |\n| Broken hierarchy | Missing parent link | Pass `langfuseParent` option |\n\n## Examples\n\n### Anthropic Claude Tracing\n```typescript\nimport Anthropic from \"@anthropic-ai\u002Fsdk\";\nimport { Langfuse } from \"langfuse\";\n\nconst anthropic = new Anthropic();\nconst langfuse = new Langfuse();\n\nasync function callClaude(prompt: string) {\n  const trace = langfuse.trace({ name: \"claude-call\", input: { prompt } });\n\n  const generation = trace.generation({\n    name: \"claude-response\",\n    model: \"claude-3-sonnet-20240229\",\n    input: [{ role: \"user\", content: prompt }],\n  });\n\n  const response = await anthropic.messages.create({\n    model: \"claude-3-sonnet-20240229\",\n    max_tokens: 1024,\n    messages: [{ role: \"user\", content: prompt }],\n  });\n\n  generation.end({\n    output: response.content[0].text,\n    usage: {\n      promptTokens: response.usage.input_tokens,\n      completionTokens: response.usage.output_tokens,\n    },\n  });\n\n  return response.content[0].text;\n}\n```\n\n### LangChain Integration\n```python\nfrom langchain.callbacks import LangfuseCallbackHandler\nfrom langchain.chat_models import ChatOpenAI\nfrom langchain.schema import HumanMessage\n\n# Create callback handler\nlangfuse_handler = LangfuseCallbackHandler()\n\n# Pass to LLM\nllm = ChatOpenAI(callbacks=[langfuse_handler])\n\n# All LangChain operations are now traced\nresponse = llm([HumanMessage(content=\"Hello!\")])\n```\n\n### Tool\u002FFunction Calling Tracing\n```typescript\nasync function tracedToolCall(trace: Trace, toolName: string, args: any) {\n  const span = trace.span({\n    name: `tool\u002F${toolName}`,\n    input: args,\n    metadata: { type: \"tool-call\" },\n  });\n\n  try {\n    const result = await executeTool(toolName, args);\n    span.end({ output: result });\n    return result;\n  } catch (error) {\n    span.end({\n      level: \"ERROR\",\n      statusMessage: String(error),\n    });\n    throw error;\n  }\n}\n```\n\n## Resources\n- [Langfuse Tracing Guide](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Ftracing)\n- [OpenAI Integration](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Fintegrations\u002Fopenai)\n- [LangChain Integration](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Fintegrations\u002Flangchain)\n- [Streaming Guide](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Ftracing-features\u002Fsessions)\n\n## Next Steps\nFor evaluation and scoring workflows, see `langfuse-core-workflow-b`.\n","# Langfuse Core Workflow A: Tracing LLM Calls\n\n## Overview\nPrimary workflow for Langfuse: end-to-end tracing of LLM calls, chains, and agents.\n\n## Prerequisites\n- Completed `langfuse-install-auth` setup\n- Understanding of Langfuse trace hierarchy\n- LLM provider SDK (OpenAI, Anthropic, etc.)\n\n## Instructions\n\n### Step 1: Set Up Automatic OpenAI Tracing\n\n```typescript\nimport { observeOpenAI } from \"langfuse\";\nimport OpenAI from \"openai\";\n\n\u002F\u002F Wrap OpenAI client for automatic tracing\nconst openai = observeOpenAI(new OpenAI());\n\n\u002F\u002F All calls are now automatically traced\nconst response = await openai.chat.completions.create({\n  model: \"gpt-4\",\n  messages: [\n    { role: \"system\", content: \"You are a helpful assistant.\" },\n    { role: \"user\", content: \"What is Langfuse?\" },\n  ],\n});\n```\n\n### Step 2: Manual Tracing for Complex Flows\n\n```typescript\nimport { Langfuse } from \"langfuse\";\n\nconst langfuse = new Langfuse();\n\nasync function ragPipeline(query: string) {\n  \u002F\u002F Create top-level trace\n  const trace = langfuse.trace({\n    name: \"rag-pipeline\",\n    input: { query },\n    metadata: { pipeline: \"rag-v1\" },\n  });\n\n  \u002F\u002F Span: Query embedding\n  const embedSpan = trace.span({\n    name: \"embed-query\",\n    input: { text: query },\n  });\n\n  const queryEmbedding = await embedText(query);\n\n  embedSpan.end({\n    output: { dimensions: queryEmbedding.length },\n    metadata: { model: \"text-embedding-ada-002\" },\n  });\n\n  \u002F\u002F Span: Vector search\n  const searchSpan = trace.span({\n    name: \"vector-search\",\n    input: { embedding: \"vector[1536]\" },\n  });\n\n  const documents = await searchVectorDB(queryEmbedding);\n\n  searchSpan.end({\n    output: {\n      documentCount: documents.length,\n      topScore: documents[0]?.score,\n    },\n  });\n\n  \u002F\u002F Generation: LLM call with context\n  const generation = trace.generation({\n    name: \"generate-answer\",\n    model: \"gpt-4\",\n    modelParameters: { temperature: 0.7, maxTokens: 500 },\n    input: {\n      query,\n      context: documents.map((d) => d.content),\n    },\n  });\n\n  const answer = await generateAnswer(query, documents);\n\n  generation.end({\n    output: answer.content,\n    usage: {\n      promptTokens: answer.usage.prompt_tokens,\n      completionTokens: answer.usage.completion_tokens,\n      totalTokens: answer.usage.total_tokens,\n    },\n  });\n\n  \u002F\u002F Update trace with final output\n  trace.update({\n    output: { answer: answer.content },\n  });\n\n  return answer.content;\n}\n```\n\n### Step 3: Trace Streaming Responses\n\n```typescript\nasync function streamingChat(messages: ChatMessage[]) {\n  const trace = langfuse.trace({\n    name: \"streaming-chat\",\n    input: { messages },\n  });\n\n  const generation = trace.generation({\n    name: \"stream-response\",\n    model: \"gpt-4\",\n    input: messages,\n  });\n\n  const stream = await openai.chat.completions.create({\n    model: \"gpt-4\",\n    messages,\n    stream: true,\n  });\n\n  let fullContent = \"\";\n  let usage = { promptTokens: 0, completionTokens: 0 };\n\n  for await (const chunk of stream) {\n    const content = chunk.choices[0]?.delta?.content || \"\";\n    fullContent += content;\n\n    \u002F\u002F Track usage from final chunk\n    if (chunk.usage) {\n      usage = {\n        promptTokens: chunk.usage.prompt_tokens,\n        completionTokens: chunk.usage.completion_tokens,\n      };\n    }\n\n    yield content;\n  }\n\n  \u002F\u002F End generation after stream completes\n  generation.end({\n    output: fullContent,\n    usage,\n  });\n\n  trace.update({ output: { response: fullContent } });\n}\n```\n\n### Step 4: Link Traces to Parent Operations\n\n```typescript\n\u002F\u002F API endpoint that creates parent trace\nasync function handleChatRequest(req: Request) {\n  const trace = langfuse.trace({\n    name: \"api\u002Fchat\",\n    userId: req.userId,\n    sessionId: req.sessionId,\n    input: req.body,\n  });\n\n  \u002F\u002F Pass trace to child operations\n  const response = await processChat(trace, req.body.message);\n\n  return response;\n}\n\n\u002F\u002F Child function receives parent trace\nasync function processChat(\n  parentTrace: ReturnType\u003Ctypeof langfuse.trace>,\n  message: string\n) {\n  \u002F\u002F Create child span under parent trace\n  const span = parentTrace.span({\n    name: \"process-chat\",\n    input: { message },\n  });\n\n  \u002F\u002F OpenAI call linked to parent\n  const response = await openai.chat.completions.create(\n    {\n      model: \"gpt-4\",\n      messages: [{ role: \"user\", content: message }],\n    },\n    { langfuseParent: span } \u002F\u002F Link generation to span\n  );\n\n  span.end({ output: response.choices[0].message });\n  return response.choices[0].message.content;\n}\n```\n\n## Output\n- Automatic OpenAI tracing with zero code changes\n- Manual tracing for RAG and complex pipelines\n- Streaming response tracking\n- Linked parent-child trace hierarchy\n\n## Error Handling\n| Issue | Cause | Solution |\n|-------|-------|----------|\n| Missing generations | Wrapper not applied | Use `observeOpenAI()` wrapper |\n| Orphaned spans | Missing `.end()` call | Always end spans in finally block |\n| No token usage | Stream without usage | Use `stream_options: {include_usage: true}` |\n| Broken hierarchy | Missing parent link | Pass `langfuseParent` option |\n\n## Examples\n\n### Anthropic Claude Tracing\n```typescript\nimport Anthropic from \"@anthropic-ai\u002Fsdk\";\nimport { Langfuse } from \"langfuse\";\n\nconst anthropic = new Anthropic();\nconst langfuse = new Langfuse();\n\nasync function callClaude(prompt: string) {\n  const trace = langfuse.trace({ name: \"claude-call\", input: { prompt } });\n\n  const generation = trace.generation({\n    name: \"claude-response\",\n    model: \"claude-3-sonnet-20240229\",\n    input: [{ role: \"user\", content: prompt }],\n  });\n\n  const response = await anthropic.messages.create({\n    model: \"claude-3-sonnet-20240229\",\n    max_tokens: 1024,\n    messages: [{ role: \"user\", content: prompt }],\n  });\n\n  generation.end({\n    output: response.content[0].text,\n    usage: {\n      promptTokens: response.usage.input_tokens,\n      completionTokens: response.usage.output_tokens,\n    },\n  });\n\n  return response.content[0].text;\n}\n```\n\n### LangChain Integration\n```python\nfrom langchain.callbacks import LangfuseCallbackHandler\nfrom langchain.chat_models import ChatOpenAI\nfrom langchain.schema import HumanMessage\n\n# Create callback handler\nlangfuse_handler = LangfuseCallbackHandler()\n\n# Pass to LLM\nllm = ChatOpenAI(callbacks=[langfuse_handler])\n\n# All LangChain operations are now traced\nresponse = llm([HumanMessage(content=\"Hello!\")])\n```\n\n### Tool\u002FFunction Calling Tracing\n```typescript\nasync function tracedToolCall(trace: Trace, toolName: string, args: any) {\n  const span = trace.span({\n    name: `tool\u002F${toolName}`,\n    input: args,\n    metadata: { type: \"tool-call\" },\n  });\n\n  try {\n    const result = await executeTool(toolName, args);\n    span.end({ output: result });\n    return result;\n  } catch (error) {\n    span.end({\n      level: \"ERROR\",\n      statusMessage: String(error),\n    });\n    throw error;\n  }\n}\n```\n\n## Resources\n- [Langfuse Tracing Guide](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Ftracing)\n- [OpenAI Integration](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Fintegrations\u002Fopenai)\n- [LangChain Integration](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Fintegrations\u002Flangchain)\n- [Streaming Guide](https:\u002F\u002Flangfuse.com\u002Fdocs\u002Ftracing-features\u002Fsessions)\n\n## Next Steps\nFor evaluation and scoring workflows, see `langfuse-core-workflow-b`.\n",{"name":5,"author":54,"license":15,"version":55,"description":56,"allowed-tools":57},"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Execute Langfuse primary workflow: Tracing LLM calls and spans.\nUse when implementing LLM tracing, building traced AI features,\nor adding observability to existing LLM applications.\nTrigger with phrases like \"langfuse tracing\", \"trace LLM calls\",\n\"add langfuse to openai\", \"langfuse spans\", \"track llm requests\".\n","Read, Write, Edit, Bash(npm:*), Grep","main","90b50ed0778745a80fd5bfb13b1843d45b9e82f7","tests\u002Fext_conformance\u002Fartifacts\u002Fplugins-community\u002Fplugins\u002Fsaas-packs\u002Flangfuse-pack\u002Fskills\u002Flangfuse-core-workflow-a",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":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add Dicklesworthstone\u002Fpi_agent_rust --skill langfuse-core-workflow-a",{"tool":73,"command":74},"bunx","bunx skills add Dicklesworthstone\u002Fpi_agent_rust --skill langfuse-core-workflow-a",{"tool":76,"command":77},"pnpm","pnpm dlx skills add Dicklesworthstone\u002Fpi_agent_rust --skill langfuse-core-workflow-a","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\u002Flangfuse-pack\u002Fskills\u002Flangfuse-core-workflow-a\u002FSKILL.md",true,[],[82,113,148,170,196,221],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":93,"publishedAt":112},"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",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,32,110,111],"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":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":123,"publishedAt":49},"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",[120],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[124,125,100,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,37,105,141,142,143,144,145,146,147],"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":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":86,"licenseFileUrl":152,"sourceHtmlUrl":153,"categories":154,"keywords":159,"publishedAt":49},"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",[155,158],{"categoryNo":156,"categoryName":157,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},[160,161,162,128,163,164,125,165,98,166,138,167,44,168,169,32,145],"testing","webapp testing","webapp","screenshots","playwright","debugging","browser","logs","behavior","local",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":174,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":49},"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",[],[178,179,180,181,182,183,184,185,37,186,187,188,189,190,191,192,32,193,194,195,145,28],"analysis","neuropixels analysis","spike","metrics","data","open","quality","user","recordings","Neural","motion","visual","quality metrics","unit","sorting","curation","recording","load",{"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":86,"licenseFileUrl":200,"sourceHtmlUrl":201,"categories":202,"keywords":204,"publishedAt":49},"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",[203],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[205,206,207,208,209,210,211,212,213,214,215,216,217,218,32,145,219,28,220],"skill creator","creator","workflows","create","update","capabilities","knowledge","tool","integrations","specialized","guide","new skill","existing skill","users","Existing","new",{"skillNo":222,"name":223,"nameZh":6,"description":224,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":225,"sourceHtmlUrl":226,"categories":227,"keywords":229,"publishedAt":49},"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",[228],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[223,230,231,232,233,234,235,166,236,237,37,238,239,240,241,145,242],"google","browser automation","gemini","automation","auth","code","library","management","only","document","query","Citation","source"]