[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ANTA3397660AX829NMEKFX":3,"skill-same:01M7ANTA3397660AX829NMEKFX":78},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":15,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":40,"commitSha":41,"skillDirectory":5,"forksCount":13,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":44,"install":45,"resources":57},"01M7ANTA3397660AX829NMEKFX","openai-agents",null,"Use this skill when building AI applications with OpenAI Agents SDK for JavaScript\u002FTypeScript. The skill covers both text-based agents and realtime voice agents, including multi-agent workflows (handoffs), tools with Zod schemas, input\u002Foutput guardrails, structured outputs, streaming, human-in-the-loop patterns, and framework integrations for Cloudflare Workers, Next.js, and React. It prevents 9+ common errors including Zod schema type errors, MCP tracing failures, infinite loops, tool call failures, and schema mismatches. The skill includes comprehensive templates for all agent types, error handling patterns, and debugging strategies.\n\nKeywords: OpenAI Agents SDK, @openai\u002Fagents, @openai\u002Fagents-realtime, openai agents javascript, openai agents typescript, text agents, voice agents, realtime agents, multi-agent workflows, agent handoffs, agent tools, zod schemas agents, structured outputs agents, agent streaming, agent guardrails, input guardrails, output guardrails, human-in-the-loop, cloudflare workers agents, nextjs openai agents, react openai agents, hono agents, agent debugging, Zod schema type error, MCP tracing failure, agent infinite loop, tool call failures, schema mismatch agents","davidanthonyn\u002Fclaude-skills","davidanthonyn","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F55152980?v=4","01M7AJ4MY8S5C2RJCGX6626J0G","01M7AJ7JE1K98GRPH9Z57Z0R0W",0,"MIT","https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fopenai-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fopenai-agents\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: openai-agents\ndescription: |\n  Use this skill when building AI applications with OpenAI Agents SDK for JavaScript\u002FTypeScript. The skill covers both text-based agents and realtime voice agents, including multi-agent workflows (handoffs), tools with Zod schemas, input\u002Foutput guardrails, structured outputs, streaming, human-in-the-loop patterns, and framework integrations for Cloudflare Workers, Next.js, and React. It prevents 9+ common errors including Zod schema type errors, MCP tracing failures, infinite loops, tool call failures, and schema mismatches. The skill includes comprehensive templates for all agent types, error handling patterns, and debugging strategies.\n\n  Keywords: OpenAI Agents SDK, @openai\u002Fagents, @openai\u002Fagents-realtime, openai agents javascript, openai agents typescript, text agents, voice agents, realtime agents, multi-agent workflows, agent handoffs, agent tools, zod schemas agents, structured outputs agents, agent streaming, agent guardrails, input guardrails, output guardrails, human-in-the-loop, cloudflare workers agents, nextjs openai agents, react openai agents, hono agents, agent debugging, Zod schema type error, MCP tracing failure, agent infinite loop, tool call failures, schema mismatch agents\nlicense: MIT\nmetadata:\n  packages:\n    - \"@openai\u002Fagents@0.2.1\"\n    - \"@openai\u002Fagents-realtime@0.2.1\"\n    - \"zod@^3.24.1\"\n  frameworks: [\"Cloudflare Workers\", \"Next.js\", \"React\", \"Node.js\", \"Hono\"]\n  last_verified: \"2025-10-26\"\n  production_tested: true\n  token_savings: \"~60%\"\n  errors_prevented: 9\n---\n\n# OpenAI Agents SDK Skill\n\nComplete skill for building AI applications with OpenAI Agents SDK (JavaScript\u002FTypeScript), covering text agents, realtime voice agents, multi-agent workflows, and production deployment patterns.\n\n---\n\n## Installation & Setup\n\nInstall required packages:\n\n```bash\nnpm install @openai\u002Fagents zod@3\nnpm install @openai\u002Fagents-realtime  # For voice agents\n```\n\nSet environment variable:\n\n```bash\nexport OPENAI_API_KEY=\"your-api-key\"\n```\n\nSupported runtimes:\n- Node.js 22+\n- Deno\n- Bun\n- Cloudflare Workers (experimental)\n\n---\n\n## Core Concepts\n\n### 1. Agents\nLLMs equipped with instructions and tools:\n\n```typescript\nimport { Agent } from '@openai\u002Fagents';\n\nconst agent = new Agent({\n  name: 'Assistant',\n  instructions: 'You are helpful.',\n  tools: [myTool],\n  model: 'gpt-4o-mini',\n});\n```\n\n### 2. Tools\nFunctions agents can call, with automatic schema generation:\n\n```typescript\nimport { tool } from '@openai\u002Fagents';\nimport { z } from 'zod';\n\nconst weatherTool = tool({\n  name: 'get_weather',\n  description: 'Get weather for a city',\n  parameters: z.object({\n    city: z.string(),\n  }),\n  execute: async ({ city }) => {\n    return `Weather in ${city}: sunny`;\n  },\n});\n```\n\n### 3. Handoffs\nMulti-agent delegation:\n\n```typescript\nconst specialist = new Agent({ \u002F* ... *\u002F });\n\nconst triageAgent = Agent.create({\n  name: 'Triage',\n  instructions: 'Route to specialists',\n  handoffs: [specialist],\n});\n```\n\n### 4. Guardrails\nInput\u002Foutput validation for safety:\n\n```typescript\nconst agent = new Agent({\n  inputGuardrails: [homeworkDetector],\n  outputGuardrails: [piiFilter],\n});\n```\n\n### 5. Structured Outputs\nType-safe responses with Zod:\n\n```typescript\nconst agent = new Agent({\n  outputType: z.object({\n    sentiment: z.enum(['positive', 'negative', 'neutral']),\n    confidence: z.number(),\n  }),\n});\n```\n\n---\n\n## Text Agents\n\n### Basic Usage\n\n```typescript\nimport { run } from '@openai\u002Fagents';\n\nconst result = await run(agent, 'What is 2+2?');\nconsole.log(result.finalOutput);\nconsole.log(result.usage.totalTokens);\n```\n\n### Streaming\n\n```typescript\nconst stream = await run(agent, 'Tell me a story', {\n  stream: true,\n});\n\nfor await (const event of stream) {\n  if (event.type === 'raw_model_stream_event') {\n    const chunk = event.data?.choices?.[0]?.delta?.content || '';\n    process.stdout.write(chunk);\n  }\n}\n```\n\n**Templates**:\n- `templates\u002Ftext-agents\u002Fagent-basic.ts`\n- `templates\u002Ftext-agents\u002Fagent-streaming.ts`\n\n---\n\n## Multi-Agent Handoffs\n\nCreate specialized agents and route between them:\n\n```typescript\nconst billingAgent = new Agent({\n  name: 'Billing',\n  handoffDescription: 'For billing and payment questions',\n  tools: [processRefundTool],\n});\n\nconst techAgent = new Agent({\n  name: 'Technical',\n  handoffDescription: 'For technical issues',\n  tools: [createTicketTool],\n});\n\nconst triageAgent = Agent.create({\n  name: 'Triage',\n  instructions: 'Route customers to the right specialist',\n  handoffs: [billingAgent, techAgent],\n});\n```\n\n**Templates**:\n- `templates\u002Ftext-agents\u002Fagent-handoffs.ts`\n\n**References**:\n- `references\u002Fagent-patterns.md` - LLM vs code orchestration\n\n---\n\n## Guardrails\n\n### Input Guardrails\n\nValidate input before processing:\n\n```typescript\nconst homeworkGuardrail: InputGuardrail = {\n  name: 'Homework Detection',\n  execute: async ({ input, context }) => {\n    const result = await run(guardrailAgent, input);\n    return {\n      tripwireTriggered: result.finalOutput.isHomework,\n      outputInfo: result.finalOutput,\n    };\n  },\n};\n\nconst agent = new Agent({\n  inputGuardrails: [homeworkGuardrail],\n});\n```\n\n### Output Guardrails\n\nFilter responses:\n\n```typescript\nconst piiGuardrail: OutputGuardrail = {\n  name: 'PII Detection',\n  execute: async ({ agentOutput }) => {\n    const phoneRegex = \u002F\\b\\d{3}[-. ]?\\d{3}[-. ]?\\d{4}\\b\u002F;\n    return {\n      tripwireTriggered: phoneRegex.test(agentOutput as string),\n      outputInfo: { detected: 'phone_number' },\n    };\n  },\n};\n```\n\n**Templates**:\n- `templates\u002Ftext-agents\u002Fagent-guardrails-input.ts`\n- `templates\u002Ftext-agents\u002Fagent-guardrails-output.ts`\n\n---\n\n## Human-in-the-Loop\n\nRequire approval for specific actions:\n\n```typescript\nconst refundTool = tool({\n  name: 'process_refund',\n  requiresApproval: true,  \u002F\u002F ← Requires human approval\n  execute: async ({ amount }) => {\n    return `Refunded $${amount}`;\n  },\n});\n\n\u002F\u002F Handle approval requests\nlet result = await runner.run(input);\n\nwhile (result.interruption) {\n  if (result.interruption.type === 'tool_approval') {\n    const approved = await promptUser(result.interruption);\n    result = approved\n      ? await result.state.approve(result.interruption)\n      : await result.state.reject(result.interruption);\n  }\n}\n```\n\n**Templates**:\n- `templates\u002Ftext-agents\u002Fagent-human-approval.ts`\n\n---\n\n## Realtime Voice Agents\n\n### Creating Voice Agents\n\n```typescript\nimport { RealtimeAgent, tool } from '@openai\u002Fagents-realtime';\n\nconst voiceAgent = new RealtimeAgent({\n  name: 'Voice Assistant',\n  instructions: 'Keep responses concise for voice',\n  tools: [weatherTool],\n  voice: 'alloy', \u002F\u002F alloy, echo, fable, onyx, nova, shimmer\n  model: 'gpt-4o-realtime-preview',\n});\n```\n\n### Browser Session (React)\n\n```typescript\nimport { RealtimeSession } from '@openai\u002Fagents-realtime';\n\nconst session = new RealtimeSession(voiceAgent, {\n  apiKey: sessionApiKey, \u002F\u002F From your backend!\n  transport: 'webrtc', \u002F\u002F or 'websocket'\n});\n\nsession.on('connected', () => console.log('Connected'));\nsession.on('audio.transcription.completed', (e) => console.log('User:', e.transcript));\nsession.on('agent.audio.done', (e) => console.log('Agent:', e.transcript));\n\nawait session.connect();\n```\n\n**CRITICAL**: Never send your main OPENAI_API_KEY to the browser! Generate ephemeral session tokens server-side.\n\n### Voice Agent Handoffs\n\nVoice agents support handoffs with constraints:\n- **Cannot change voice** during handoff\n- **Cannot change model** during handoff\n- Conversation history automatically passed\n\n```typescript\nconst specialist = new RealtimeAgent({\n  voice: 'nova', \u002F\u002F Must match parent\n  \u002F* ... *\u002F\n});\n\nconst triageAgent = new RealtimeAgent({\n  voice: 'nova',\n  handoffs: [specialist],\n});\n```\n\n**Templates**:\n- `templates\u002Frealtime-agents\u002Frealtime-agent-basic.ts`\n- `templates\u002Frealtime-agents\u002Frealtime-session-browser.tsx`\n- `templates\u002Frealtime-agents\u002Frealtime-handoffs.ts`\n\n**References**:\n- `references\u002Frealtime-transports.md` - WebRTC vs WebSocket\n\n---\n\n## Framework Integration\n\n### Cloudflare Workers (Experimental)\n\n```typescript\nimport { Agent, run } from '@openai\u002Fagents';\n\nexport default {\n  async fetch(request: Request, env: Env) {\n    const { message } = await request.json();\n\n    process.env.OPENAI_API_KEY = env.OPENAI_API_KEY;\n\n    const agent = new Agent({\n      name: 'Assistant',\n      instructions: 'Be helpful and concise',\n      model: 'gpt-4o-mini',\n    });\n\n    const result = await run(agent, message, {\n      maxTurns: 5,\n    });\n\n    return new Response(JSON.stringify({\n      response: result.finalOutput,\n      tokens: result.usage.totalTokens,\n    }), {\n      headers: { 'Content-Type': 'application\u002Fjson' },\n    });\n  },\n};\n```\n\n**Limitations**:\n- No realtime voice agents\n- CPU time limits (30s max)\n- Memory constraints (128MB)\n\n**Templates**:\n- `templates\u002Fcloudflare-workers\u002Fworker-text-agent.ts`\n- `templates\u002Fcloudflare-workers\u002Fworker-agent-hono.ts`\n\n**References**:\n- `references\u002Fcloudflare-integration.md`\n\n### Next.js App Router\n\n```typescript\n\u002F\u002F app\u002Fapi\u002Fagent\u002Froute.ts\nimport { NextRequest, NextResponse } from 'next\u002Fserver';\nimport { Agent, run } from '@openai\u002Fagents';\n\nexport async function POST(request: NextRequest) {\n  const { message } = await request.json();\n\n  const agent = new Agent({\n    name: 'Assistant',\n    instructions: 'Be helpful',\n  });\n\n  const result = await run(agent, message);\n\n  return NextResponse.json({\n    response: result.finalOutput,\n  });\n}\n```\n\n**Templates**:\n- `templates\u002Fnextjs\u002Fapi-agent-route.ts`\n- `templates\u002Fnextjs\u002Fapi-realtime-route.ts`\n\n---\n\n## Error Handling (9+ Errors Prevented)\n\n### 1. Zod Schema Type Errors\n\n**Error**: Type errors with tool parameters.\n\n**Workaround**: Define schemas inline.\n\n```typescript\n\u002F\u002F ❌ Can cause type errors\nparameters: mySchema\n\n\u002F\u002F ✅ Works reliably\nparameters: z.object({ field: z.string() })\n```\n\n**Source**: [GitHub #188](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fissues\u002F188)\n\n### 2. MCP Tracing Errors\n\n**Error**: \"No existing trace found\" with MCP servers.\n\n**Workaround**:\n```typescript\nimport { initializeTracing } from '@openai\u002Fagents\u002Ftracing';\nawait initializeTracing();\n```\n\n**Source**: [GitHub #580](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fissues\u002F580)\n\n### 3. MaxTurnsExceededError\n\n**Error**: Agent loops infinitely.\n\n**Solution**: Increase maxTurns or improve instructions:\n\n```typescript\nconst result = await run(agent, input, {\n  maxTurns: 20, \u002F\u002F Increase limit\n});\n\n\u002F\u002F Or improve instructions\ninstructions: `After using tools, provide a final answer.\nDo not loop endlessly.`\n```\n\n### 4. ToolCallError\n\n**Error**: Tool execution fails.\n\n**Solution**: Retry with exponential backoff:\n\n```typescript\nfor (let attempt = 1; attempt \u003C= 3; attempt++) {\n  try {\n    return await run(agent, input);\n  } catch (error) {\n    if (error instanceof ToolCallError && attempt \u003C 3) {\n      await sleep(1000 * Math.pow(2, attempt - 1));\n      continue;\n    }\n    throw error;\n  }\n}\n```\n\n### 5. Schema Mismatch\n\n**Error**: Output doesn't match `outputType`.\n\n**Solution**: Use stronger model or add validation instructions:\n\n```typescript\nconst agent = new Agent({\n  model: 'gpt-4o', \u002F\u002F More reliable than gpt-4o-mini\n  instructions: 'CRITICAL: Return JSON matching schema exactly',\n  outputType: mySchema,\n});\n```\n\n**All Errors**: See `references\u002Fcommon-errors.md`\n\n**Template**: `templates\u002Fshared\u002Ferror-handling.ts`\n\n---\n\n## Orchestration Patterns\n\n### LLM-Based\n\nAgent decides routing autonomously:\n\n```typescript\nconst manager = Agent.create({\n  instructions: 'Analyze request and route to appropriate agent',\n  handoffs: [agent1, agent2, agent3],\n});\n```\n\n**Pros**: Adaptive, handles complexity\n**Cons**: Less predictable, higher tokens\n\n### Code-Based\n\nExplicit control flow:\n\n```typescript\nconst summary = await run(summarizerAgent, text);\nconst sentiment = await run(sentimentAgent, summary.finalOutput);\n\nif (sentiment.finalOutput.score \u003C 0.3) {\n  await run(escalationAgent, text);\n}\n```\n\n**Pros**: Predictable, lower cost\n**Cons**: Less flexible\n\n### Parallel\n\nRun multiple agents concurrently:\n\n```typescript\nconst [summary, keywords, entities] = await Promise.all([\n  run(summarizerAgent, text),\n  run(keywordAgent, text),\n  run(entityAgent, text),\n]);\n```\n\n**Template**: `templates\u002Ftext-agents\u002Fagent-parallel.ts`\n\n**References**: `references\u002Fagent-patterns.md`\n\n---\n\n## Debugging & Tracing\n\nEnable verbose logging:\n\n```typescript\nprocess.env.DEBUG = '@openai\u002Fagents:*';\n```\n\nAccess execution details:\n\n```typescript\nconst result = await run(agent, input);\n\nconsole.log('Tokens:', result.usage.totalTokens);\nconsole.log('Turns:', result.history.length);\nconsole.log('Current Agent:', result.currentAgent?.name);\n```\n\n**Template**: `templates\u002Fshared\u002Ftracing-setup.ts`\n\n---\n\n## When to Use This Skill\n\n✅ **Use when**:\n- Building multi-agent workflows\n- Creating voice AI applications\n- Implementing tool-calling patterns\n- Requiring input\u002Foutput validation (guardrails)\n- Needing human approval gates\n- Orchestrating complex AI tasks\n- Deploying to Cloudflare Workers or Next.js\n\n❌ **Don't use when**:\n- Simple OpenAI API calls (use `openai-api` skill instead)\n- Non-OpenAI models exclusively\n- Production voice at massive scale (consider LiveKit Agents)\n\n---\n\n## Production Checklist\n\n- [ ] Set `OPENAI_API_KEY` as environment secret\n- [ ] Implement error handling for all agent calls\n- [ ] Add guardrails for safety-critical applications\n- [ ] Enable tracing for debugging\n- [ ] Set reasonable `maxTurns` to prevent runaway costs\n- [ ] Use `gpt-4o-mini` where possible for cost efficiency\n- [ ] Implement rate limiting\n- [ ] Log token usage for cost monitoring\n- [ ] Test handoff flows thoroughly\n- [ ] Never expose API keys to browsers (use session tokens)\n\n---\n\n## Token Efficiency\n\n**Estimated Savings**: ~60%\n\n| Task | Without Skill | With Skill | Savings |\n|------|---------------|------------|---------|\n| Multi-agent setup | ~12k tokens | ~5k tokens | 58% |\n| Voice agent | ~10k tokens | ~4k tokens | 60% |\n| Error debugging | ~8k tokens | ~3k tokens | 63% |\n| **Average** | **~10k** | **~4k** | **~60%** |\n\n**Errors Prevented**: 9 documented issues = 100% error prevention\n\n---\n\n## Templates Index\n\n**Text Agents** (8):\n1. `agent-basic.ts` - Simple agent with tools\n2. `agent-handoffs.ts` - Multi-agent triage\n3. `agent-structured-output.ts` - Zod schemas\n4. `agent-streaming.ts` - Real-time events\n5. `agent-guardrails-input.ts` - Input validation\n6. `agent-guardrails-output.ts` - Output filtering\n7. `agent-human-approval.ts` - HITL pattern\n8. `agent-parallel.ts` - Concurrent execution\n\n**Realtime Agents** (3):\n9. `realtime-agent-basic.ts` - Voice setup\n10. `realtime-session-browser.tsx` - React client\n11. `realtime-handoffs.ts` - Voice delegation\n\n**Framework Integration** (4):\n12. `worker-text-agent.ts` - Cloudflare Workers\n13. `worker-agent-hono.ts` - Hono framework\n14. `api-agent-route.ts` - Next.js API\n15. `api-realtime-route.ts` - Next.js voice\n\n**Utilities** (2):\n16. `error-handling.ts` - Comprehensive errors\n17. `tracing-setup.ts` - Debugging\n\n---\n\n## References\n\n1. `agent-patterns.md` - Orchestration strategies\n2. `common-errors.md` - 9 errors with workarounds\n3. `realtime-transports.md` - WebRTC vs WebSocket\n4. `cloudflare-integration.md` - Workers limitations\n5. `official-links.md` - Documentation links\n\n---\n\n## Official Resources\n\n- **Docs**: https:\u002F\u002Fopenai.github.io\u002Fopenai-agents-js\u002F\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\n- **npm**: https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@openai\u002Fagents\n- **Issues**: https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fissues\n\n---\n\n**Version**: SDK v0.2.1\n**Last Verified**: 2025-10-26\n**Skill Author**: Jeremy Dawes (Jezweb)\n**Production Tested**: Yes\n","# OpenAI Agents SDK Skill\n\nComplete skill for building AI applications with OpenAI Agents SDK (JavaScript\u002FTypeScript), covering text agents, realtime voice agents, multi-agent workflows, and production deployment patterns.\n\n---\n\n## Installation & Setup\n\nInstall required packages:\n\n```bash\nnpm install @openai\u002Fagents zod@3\nnpm install @openai\u002Fagents-realtime  # For voice agents\n```\n\nSet environment variable:\n\n```bash\nexport OPENAI_API_KEY=\"your-api-key\"\n```\n\nSupported runtimes:\n- Node.js 22+\n- Deno\n- Bun\n- Cloudflare Workers (experimental)\n\n---\n\n## Core Concepts\n\n### 1. Agents\nLLMs equipped with instructions and tools:\n\n```typescript\nimport { Agent } from '@openai\u002Fagents';\n\nconst agent = new Agent({\n  name: 'Assistant',\n  instructions: 'You are helpful.',\n  tools: [myTool],\n  model: 'gpt-4o-mini',\n});\n```\n\n### 2. Tools\nFunctions agents can call, with automatic schema generation:\n\n```typescript\nimport { tool } from '@openai\u002Fagents';\nimport { z } from 'zod';\n\nconst weatherTool = tool({\n  name: 'get_weather',\n  description: 'Get weather for a city',\n  parameters: z.object({\n    city: z.string(),\n  }),\n  execute: async ({ city }) => {\n    return `Weather in ${city}: sunny`;\n  },\n});\n```\n\n### 3. Handoffs\nMulti-agent delegation:\n\n```typescript\nconst specialist = new Agent({ \u002F* ... *\u002F });\n\nconst triageAgent = Agent.create({\n  name: 'Triage',\n  instructions: 'Route to specialists',\n  handoffs: [specialist],\n});\n```\n\n### 4. Guardrails\nInput\u002Foutput validation for safety:\n\n```typescript\nconst agent = new Agent({\n  inputGuardrails: [homeworkDetector],\n  outputGuardrails: [piiFilter],\n});\n```\n\n### 5. Structured Outputs\nType-safe responses with Zod:\n\n```typescript\nconst agent = new Agent({\n  outputType: z.object({\n    sentiment: z.enum(['positive', 'negative', 'neutral']),\n    confidence: z.number(),\n  }),\n});\n```\n\n---\n\n## Text Agents\n\n### Basic Usage\n\n```typescript\nimport { run } from '@openai\u002Fagents';\n\nconst result = await run(agent, 'What is 2+2?');\nconsole.log(result.finalOutput);\nconsole.log(result.usage.totalTokens);\n```\n\n### Streaming\n\n```typescript\nconst stream = await run(agent, 'Tell me a story', {\n  stream: true,\n});\n\nfor await (const event of stream) {\n  if (event.type === 'raw_model_stream_event') {\n    const chunk = event.data?.choices?.[0]?.delta?.content || '';\n    process.stdout.write(chunk);\n  }\n}\n```\n\n**Templates**:\n- `templates\u002Ftext-agents\u002Fagent-basic.ts`\n- `templates\u002Ftext-agents\u002Fagent-streaming.ts`\n\n---\n\n## Multi-Agent Handoffs\n\nCreate specialized agents and route between them:\n\n```typescript\nconst billingAgent = new Agent({\n  name: 'Billing',\n  handoffDescription: 'For billing and payment questions',\n  tools: [processRefundTool],\n});\n\nconst techAgent = new Agent({\n  name: 'Technical',\n  handoffDescription: 'For technical issues',\n  tools: [createTicketTool],\n});\n\nconst triageAgent = Agent.create({\n  name: 'Triage',\n  instructions: 'Route customers to the right specialist',\n  handoffs: [billingAgent, techAgent],\n});\n```\n\n**Templates**:\n- `templates\u002Ftext-agents\u002Fagent-handoffs.ts`\n\n**References**:\n- `references\u002Fagent-patterns.md` - LLM vs code orchestration\n\n---\n\n## Guardrails\n\n### Input Guardrails\n\nValidate input before processing:\n\n```typescript\nconst homeworkGuardrail: InputGuardrail = {\n  name: 'Homework Detection',\n  execute: async ({ input, context }) => {\n    const result = await run(guardrailAgent, input);\n    return {\n      tripwireTriggered: result.finalOutput.isHomework,\n      outputInfo: result.finalOutput,\n    };\n  },\n};\n\nconst agent = new Agent({\n  inputGuardrails: [homeworkGuardrail],\n});\n```\n\n### Output Guardrails\n\nFilter responses:\n\n```typescript\nconst piiGuardrail: OutputGuardrail = {\n  name: 'PII Detection',\n  execute: async ({ agentOutput }) => {\n    const phoneRegex = \u002F\\b\\d{3}[-. ]?\\d{3}[-. ]?\\d{4}\\b\u002F;\n    return {\n      tripwireTriggered: phoneRegex.test(agentOutput as string),\n      outputInfo: { detected: 'phone_number' },\n    };\n  },\n};\n```\n\n**Templates**:\n- `templates\u002Ftext-agents\u002Fagent-guardrails-input.ts`\n- `templates\u002Ftext-agents\u002Fagent-guardrails-output.ts`\n\n---\n\n## Human-in-the-Loop\n\nRequire approval for specific actions:\n\n```typescript\nconst refundTool = tool({\n  name: 'process_refund',\n  requiresApproval: true,  \u002F\u002F ← Requires human approval\n  execute: async ({ amount }) => {\n    return `Refunded $${amount}`;\n  },\n});\n\n\u002F\u002F Handle approval requests\nlet result = await runner.run(input);\n\nwhile (result.interruption) {\n  if (result.interruption.type === 'tool_approval') {\n    const approved = await promptUser(result.interruption);\n    result = approved\n      ? await result.state.approve(result.interruption)\n      : await result.state.reject(result.interruption);\n  }\n}\n```\n\n**Templates**:\n- `templates\u002Ftext-agents\u002Fagent-human-approval.ts`\n\n---\n\n## Realtime Voice Agents\n\n### Creating Voice Agents\n\n```typescript\nimport { RealtimeAgent, tool } from '@openai\u002Fagents-realtime';\n\nconst voiceAgent = new RealtimeAgent({\n  name: 'Voice Assistant',\n  instructions: 'Keep responses concise for voice',\n  tools: [weatherTool],\n  voice: 'alloy', \u002F\u002F alloy, echo, fable, onyx, nova, shimmer\n  model: 'gpt-4o-realtime-preview',\n});\n```\n\n### Browser Session (React)\n\n```typescript\nimport { RealtimeSession } from '@openai\u002Fagents-realtime';\n\nconst session = new RealtimeSession(voiceAgent, {\n  apiKey: sessionApiKey, \u002F\u002F From your backend!\n  transport: 'webrtc', \u002F\u002F or 'websocket'\n});\n\nsession.on('connected', () => console.log('Connected'));\nsession.on('audio.transcription.completed', (e) => console.log('User:', e.transcript));\nsession.on('agent.audio.done', (e) => console.log('Agent:', e.transcript));\n\nawait session.connect();\n```\n\n**CRITICAL**: Never send your main OPENAI_API_KEY to the browser! Generate ephemeral session tokens server-side.\n\n### Voice Agent Handoffs\n\nVoice agents support handoffs with constraints:\n- **Cannot change voice** during handoff\n- **Cannot change model** during handoff\n- Conversation history automatically passed\n\n```typescript\nconst specialist = new RealtimeAgent({\n  voice: 'nova', \u002F\u002F Must match parent\n  \u002F* ... *\u002F\n});\n\nconst triageAgent = new RealtimeAgent({\n  voice: 'nova',\n  handoffs: [specialist],\n});\n```\n\n**Templates**:\n- `templates\u002Frealtime-agents\u002Frealtime-agent-basic.ts`\n- `templates\u002Frealtime-agents\u002Frealtime-session-browser.tsx`\n- `templates\u002Frealtime-agents\u002Frealtime-handoffs.ts`\n\n**References**:\n- `references\u002Frealtime-transports.md` - WebRTC vs WebSocket\n\n---\n\n## Framework Integration\n\n### Cloudflare Workers (Experimental)\n\n```typescript\nimport { Agent, run } from '@openai\u002Fagents';\n\nexport default {\n  async fetch(request: Request, env: Env) {\n    const { message } = await request.json();\n\n    process.env.OPENAI_API_KEY = env.OPENAI_API_KEY;\n\n    const agent = new Agent({\n      name: 'Assistant',\n      instructions: 'Be helpful and concise',\n      model: 'gpt-4o-mini',\n    });\n\n    const result = await run(agent, message, {\n      maxTurns: 5,\n    });\n\n    return new Response(JSON.stringify({\n      response: result.finalOutput,\n      tokens: result.usage.totalTokens,\n    }), {\n      headers: { 'Content-Type': 'application\u002Fjson' },\n    });\n  },\n};\n```\n\n**Limitations**:\n- No realtime voice agents\n- CPU time limits (30s max)\n- Memory constraints (128MB)\n\n**Templates**:\n- `templates\u002Fcloudflare-workers\u002Fworker-text-agent.ts`\n- `templates\u002Fcloudflare-workers\u002Fworker-agent-hono.ts`\n\n**References**:\n- `references\u002Fcloudflare-integration.md`\n\n### Next.js App Router\n\n```typescript\n\u002F\u002F app\u002Fapi\u002Fagent\u002Froute.ts\nimport { NextRequest, NextResponse } from 'next\u002Fserver';\nimport { Agent, run } from '@openai\u002Fagents';\n\nexport async function POST(request: NextRequest) {\n  const { message } = await request.json();\n\n  const agent = new Agent({\n    name: 'Assistant',\n    instructions: 'Be helpful',\n  });\n\n  const result = await run(agent, message);\n\n  return NextResponse.json({\n    response: result.finalOutput,\n  });\n}\n```\n\n**Templates**:\n- `templates\u002Fnextjs\u002Fapi-agent-route.ts`\n- `templates\u002Fnextjs\u002Fapi-realtime-route.ts`\n\n---\n\n## Error Handling (9+ Errors Prevented)\n\n### 1. Zod Schema Type Errors\n\n**Error**: Type errors with tool parameters.\n\n**Workaround**: Define schemas inline.\n\n```typescript\n\u002F\u002F ❌ Can cause type errors\nparameters: mySchema\n\n\u002F\u002F ✅ Works reliably\nparameters: z.object({ field: z.string() })\n```\n\n**Source**: [GitHub #188](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fissues\u002F188)\n\n### 2. MCP Tracing Errors\n\n**Error**: \"No existing trace found\" with MCP servers.\n\n**Workaround**:\n```typescript\nimport { initializeTracing } from '@openai\u002Fagents\u002Ftracing';\nawait initializeTracing();\n```\n\n**Source**: [GitHub #580](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fissues\u002F580)\n\n### 3. MaxTurnsExceededError\n\n**Error**: Agent loops infinitely.\n\n**Solution**: Increase maxTurns or improve instructions:\n\n```typescript\nconst result = await run(agent, input, {\n  maxTurns: 20, \u002F\u002F Increase limit\n});\n\n\u002F\u002F Or improve instructions\ninstructions: `After using tools, provide a final answer.\nDo not loop endlessly.`\n```\n\n### 4. ToolCallError\n\n**Error**: Tool execution fails.\n\n**Solution**: Retry with exponential backoff:\n\n```typescript\nfor (let attempt = 1; attempt \u003C= 3; attempt++) {\n  try {\n    return await run(agent, input);\n  } catch (error) {\n    if (error instanceof ToolCallError && attempt \u003C 3) {\n      await sleep(1000 * Math.pow(2, attempt - 1));\n      continue;\n    }\n    throw error;\n  }\n}\n```\n\n### 5. Schema Mismatch\n\n**Error**: Output doesn't match `outputType`.\n\n**Solution**: Use stronger model or add validation instructions:\n\n```typescript\nconst agent = new Agent({\n  model: 'gpt-4o', \u002F\u002F More reliable than gpt-4o-mini\n  instructions: 'CRITICAL: Return JSON matching schema exactly',\n  outputType: mySchema,\n});\n```\n\n**All Errors**: See `references\u002Fcommon-errors.md`\n\n**Template**: `templates\u002Fshared\u002Ferror-handling.ts`\n\n---\n\n## Orchestration Patterns\n\n### LLM-Based\n\nAgent decides routing autonomously:\n\n```typescript\nconst manager = Agent.create({\n  instructions: 'Analyze request and route to appropriate agent',\n  handoffs: [agent1, agent2, agent3],\n});\n```\n\n**Pros**: Adaptive, handles complexity\n**Cons**: Less predictable, higher tokens\n\n### Code-Based\n\nExplicit control flow:\n\n```typescript\nconst summary = await run(summarizerAgent, text);\nconst sentiment = await run(sentimentAgent, summary.finalOutput);\n\nif (sentiment.finalOutput.score \u003C 0.3) {\n  await run(escalationAgent, text);\n}\n```\n\n**Pros**: Predictable, lower cost\n**Cons**: Less flexible\n\n### Parallel\n\nRun multiple agents concurrently:\n\n```typescript\nconst [summary, keywords, entities] = await Promise.all([\n  run(summarizerAgent, text),\n  run(keywordAgent, text),\n  run(entityAgent, text),\n]);\n```\n\n**Template**: `templates\u002Ftext-agents\u002Fagent-parallel.ts`\n\n**References**: `references\u002Fagent-patterns.md`\n\n---\n\n## Debugging & Tracing\n\nEnable verbose logging:\n\n```typescript\nprocess.env.DEBUG = '@openai\u002Fagents:*';\n```\n\nAccess execution details:\n\n```typescript\nconst result = await run(agent, input);\n\nconsole.log('Tokens:', result.usage.totalTokens);\nconsole.log('Turns:', result.history.length);\nconsole.log('Current Agent:', result.currentAgent?.name);\n```\n\n**Template**: `templates\u002Fshared\u002Ftracing-setup.ts`\n\n---\n\n## When to Use This Skill\n\n✅ **Use when**:\n- Building multi-agent workflows\n- Creating voice AI applications\n- Implementing tool-calling patterns\n- Requiring input\u002Foutput validation (guardrails)\n- Needing human approval gates\n- Orchestrating complex AI tasks\n- Deploying to Cloudflare Workers or Next.js\n\n❌ **Don't use when**:\n- Simple OpenAI API calls (use `openai-api` skill instead)\n- Non-OpenAI models exclusively\n- Production voice at massive scale (consider LiveKit Agents)\n\n---\n\n## Production Checklist\n\n- [ ] Set `OPENAI_API_KEY` as environment secret\n- [ ] Implement error handling for all agent calls\n- [ ] Add guardrails for safety-critical applications\n- [ ] Enable tracing for debugging\n- [ ] Set reasonable `maxTurns` to prevent runaway costs\n- [ ] Use `gpt-4o-mini` where possible for cost efficiency\n- [ ] Implement rate limiting\n- [ ] Log token usage for cost monitoring\n- [ ] Test handoff flows thoroughly\n- [ ] Never expose API keys to browsers (use session tokens)\n\n---\n\n## Token Efficiency\n\n**Estimated Savings**: ~60%\n\n| Task | Without Skill | With Skill | Savings |\n|------|---------------|------------|---------|\n| Multi-agent setup | ~12k tokens | ~5k tokens | 58% |\n| Voice agent | ~10k tokens | ~4k tokens | 60% |\n| Error debugging | ~8k tokens | ~3k tokens | 63% |\n| **Average** | **~10k** | **~4k** | **~60%** |\n\n**Errors Prevented**: 9 documented issues = 100% error prevention\n\n---\n\n## Templates Index\n\n**Text Agents** (8):\n1. `agent-basic.ts` - Simple agent with tools\n2. `agent-handoffs.ts` - Multi-agent triage\n3. `agent-structured-output.ts` - Zod schemas\n4. `agent-streaming.ts` - Real-time events\n5. `agent-guardrails-input.ts` - Input validation\n6. `agent-guardrails-output.ts` - Output filtering\n7. `agent-human-approval.ts` - HITL pattern\n8. `agent-parallel.ts` - Concurrent execution\n\n**Realtime Agents** (3):\n9. `realtime-agent-basic.ts` - Voice setup\n10. `realtime-session-browser.tsx` - React client\n11. `realtime-handoffs.ts` - Voice delegation\n\n**Framework Integration** (4):\n12. `worker-text-agent.ts` - Cloudflare Workers\n13. `worker-agent-hono.ts` - Hono framework\n14. `api-agent-route.ts` - Next.js API\n15. `api-realtime-route.ts` - Next.js voice\n\n**Utilities** (2):\n16. `error-handling.ts` - Comprehensive errors\n17. `tracing-setup.ts` - Debugging\n\n---\n\n## References\n\n1. `agent-patterns.md` - Orchestration strategies\n2. `common-errors.md` - 9 errors with workarounds\n3. `realtime-transports.md` - WebRTC vs WebSocket\n4. `cloudflare-integration.md` - Workers limitations\n5. `official-links.md` - Documentation links\n\n---\n\n## Official Resources\n\n- **Docs**: https:\u002F\u002Fopenai.github.io\u002Fopenai-agents-js\u002F\n- **GitHub**: https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\n- **npm**: https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@openai\u002Fagents\n- **Issues**: https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fissues\n\n---\n\n**Version**: SDK v0.2.1\n**Last Verified**: 2025-10-26\n**Skill Author**: Jeremy Dawes (Jezweb)\n**Production Tested**: Yes\n",{"name":5,"license":14,"metadata":24,"description":39},{"packages":25,"frameworks":29,"last_verified":35,"token_savings":36,"errors_prevented":37,"production_tested":38},[26,27,28],"@openai\u002Fagents@0.2.1","@openai\u002Fagents-realtime@0.2.1","zod@^3.24.1",[30,31,32,33,34],"Cloudflare Workers","Next.js","React","Node.js","Hono","2025-10-26","~60%",9,true,"Use this skill when building AI applications with OpenAI Agents SDK for JavaScript\u002FTypeScript. The skill covers both text-based agents and realtime voice agents, including multi-agent workflows (handoffs), tools with Zod schemas, input\u002Foutput guardrails, structured outputs, streaming, human-in-the-loop patterns, and framework integrations for Cloudflare Workers, Next.js, and React. It prevents 9+ common errors including Zod schema type errors, MCP tracing failures, infinite loops, tool call failures, and schema mismatches. The skill includes comprehensive templates for all agent types, error handling patterns, and debugging strategies.\n\nKeywords: OpenAI Agents SDK, @openai\u002Fagents, @openai\u002Fagents-realtime, openai agents javascript, openai agents typescript, text agents, voice agents, realtime agents, multi-agent workflows, agent handoffs, agent tools, zod schemas agents, structured outputs agents, agent streaming, agent guardrails, input guardrails, output guardrails, human-in-the-loop, cloudflare workers agents, nextjs openai agents, react openai agents, hono agents, agent debugging, Zod schema type error, MCP tracing failure, agent infinite loop, tool call failures, schema mismatch agents\n","main","45d5ac830c3e238eeba6d0b4e6fd7cf6b56bf380","https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills","https:\u002F\u002Fgithub.com\u002Fdavidanthonyn","2026-09-09 16:05:56",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":38},[47,50,53],{"tool":48,"command":49},"npx","npx skills add davidanthonyn\u002Fclaude-skills --skill openai-agents",{"tool":51,"command":52},"bunx","bunx skills add davidanthonyn\u002Fclaude-skills --skill openai-agents",{"tool":54,"command":55},"pnpm","pnpm dlx skills add davidanthonyn\u002Fclaude-skills --skill openai-agents","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fopenai-agents\u002FSKILL.md",[58,62,68,72],{"path":59,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":15},"LICENSE","许可证",1078,{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"README.md","REFERENCE","参考文档",4677,"https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fopenai-agents\u002FREADME.md",{"path":69,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":70,"sourceHtmlUrl":71},"SKILL.json",16290,"https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fopenai-agents\u002FSKILL.json",{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"SKILL.md.backup","OTHER","其他",15677,"https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fopenai-agents\u002FSKILL.md.backup",[79,86,94,101,108,117],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7AQPHJF528A4MD52YZEZV3R","zustand-state-management","Production-tested setup for Zustand state management in React applications with TypeScript.\nThis skill provides comprehensive patterns for building scalable, type-safe global state.\n\nUse when: setting up global state in React, migrating from Redux or Context API, implementing\nstate persistence with localStorage, configuring TypeScript with Zustand, using slices pattern\nfor modular stores, adding devtools middleware for debugging, handling Next.js SSR hydration,\nor encountering hydration errors, TypeScript inference issues, or persist middleware problems.\n\nPrevents 5 documented issues: Next.js hydration mismatches, TypeScript double parentheses\nsyntax errors, persist middleware export errors, infinite render loops, and slices pattern\ntype inference failures.\n\nKeywords: zustand, state management, React state, TypeScript state, persist middleware,\ndevtools, slices pattern, global state, React hooks, create store, useBoundStore,\nStateCreator, hydration error, text content mismatch, infinite render, localStorage,\nsessionStorage, immer middleware, shallow equality, selector pattern, zustand v5","https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fzustand-state-management\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7AQP2XJRPNYEH323GJ81NN5","zetic-mlange","Help users integrate the ZETIC Melange (MLange) on-device AI SDK into Android (Kotlin\u002FJava) and iOS (Swift) mobile apps. Use this skill whenever the user mentions Zetic, MLange, Melange, ZeticMLangeModel, ZeticMLangeLLMModel, ZeticMLangeHFModel, on-device NPU inference for mobile, or deploying ML models to Android\u002FiOS with NPU acceleration. Also trigger when users ask about running LLMs on-device with GGUF quantization, mobile NPU model deployment, or converting PyTorch\u002FONNX models for mobile inference. Covers general model inference, LLM inference (streaming token generation), and HuggingFace model loading.","https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fzetic-mlange\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fzetic-mlange\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7AQNEJHD27NNF5PYQDSW8B9","youtube-downloader","Download videos, audio, playlists, and channels from YouTube and 1000+ websites using yt-dlp. Supports quality selection, format conversion, subtitle download, playlist filtering, metadata extraction, thumbnail download, and batch operations. Use when downloading YouTube videos in any quality (4K, 8K, HDR), extracting audio as MP3\u002FM4A\u002FFLAC, downloading entire playlists\u002Fchannels, getting subtitles in multiple languages, converting to specific formats, downloading live streams, archiving content, or batch processing multiple URLs. Optimized for reliability with automatic retries, rate limiting, and error handling.","https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fyoutube-downloader\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7AQJQSD2H04EE2EPNAQ8A3M","wordpress-plugin-core","This skill provides comprehensive knowledge for WordPress plugin development, covering core patterns, security best practices, database interactions, hooks\u002Ffilters, Settings API, custom post types, REST API, and AJAX. This skill should be used when creating WordPress plugins, troubleshooting security issues, implementing custom post types\u002Ftaxonomies, building admin interfaces, or working with the WordPress database.\n\nUse when: Creating new WordPress plugins, implementing nonces\u002Fsanitization\u002Fescaping, working with $wpdb and prepared statements, building Settings API pages, registering custom post types or taxonomies, implementing REST API endpoints, handling AJAX requests, debugging plugin activation\u002Fdeactivation issues, preventing SQL injection\u002FXSS\u002FCSRF vulnerabilities.\n\nKeywords: wordpress plugin development, wordpress security, wordpress hooks, wordpress filters, wordpress database, wpdb prepare, sanitize_text_field, esc_html, wp_nonce, custom post type, register_post_type, settings api, rest api, admin-ajax, wordpress sql injection, wordpress xss, wordpress csrf, plugin header, activation hook, deactivation hook, wordpress coding standards, wordpress plugin architecture","https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fwordpress-plugin-core\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":112,"licenseFileUrl":113,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M7AQJ91T970QCFMN9R1EHZXV","webapp-testing","Test local web applications with Playwright. Use when asked to verify frontend functionality, debug UI behavior, capture browser screenshots, or inspect browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M7AQJ5E89MS8C5K3GZTY4B48","web-performance-audit","Audit web performance using Chrome DevTools MCP. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed.","https:\u002F\u002Fgithub.com\u002Fdavidanthonyn\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fweb-performance-audit\u002FSKILL.md",[],[]]