[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71JCSH6S6ERWPK34TVWC03Y":3,"skill-same:01M71JCSH6S6ERWPK34TVWC03Y":76},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":53,"commitSha":54,"skillDirectory":5,"forksCount":55,"repositoryHtmlUrl":56,"repositoryHomepageUrl":57,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M71JCSH6S6ERWPK34TVWC03Y","chat-adapter-imessage",null,"Connect the Vercel AI SDK to iMessage. Build AI agents and assistants that communicate over iMessage using chat-adapter-imessage, the official Photon adapter. Local mode (runs on your Mac) and remote mode (Photon's production infrastructure). Covers createiMessageAdapter, postMessage, editMessage, deleteMessage, react, startGatewayListener, types, and integration with the Chat SDK. Keywords: vercel ai sdk, imessage, chat adapter, ai agent, chatbot, conversational ai, messaging, apple messages, vercel, nextjs, ai assistant, chat sdk, real-time, macos.","caezium\u002Fskills","caezium","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113233555?v=4","01M71JB77ZPBAWEK009Y2W8BP7","Henry Zhang","01M71JB792NVXCWSYD27HQ0964",3,"MIT","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fchat-adapter-imessage\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发","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],"imessage","adapter","chat","chat adapter imessage","ai sdk","apple","vercel ai sdk","react","ai agents","ai agent","connect","remote","local","mode","messages","time","types","official","nextjs","messaging","2026-11-10 10:12:30",false,"---\nname: chat-adapter-imessage\ndescription: >\n  Connect the Vercel AI SDK to iMessage. Build AI agents and assistants that communicate over iMessage using\n  chat-adapter-imessage, the official Photon adapter. Local mode (runs on your Mac) and remote mode (Photon's\n  production infrastructure). Covers createiMessageAdapter, postMessage, editMessage, deleteMessage, react,\n  startGatewayListener, types, and integration with the Chat SDK.\n  Keywords: vercel ai sdk, imessage, chat adapter, ai agent, chatbot, conversational ai, messaging, apple messages,\n  vercel, nextjs, ai assistant, chat sdk, real-time, macos.\nlicense: MIT\nmetadata:\n  author: photon-hq\n  version: '1.0.0'\n---\n\n# Vercel AI SDK: iMessage Adapter Skill\n\nThis skill provides a complete reference for using `chat-adapter-imessage`, the official Photon adapter for connecting the [Vercel AI SDK (Chat SDK)](https:\u002F\u002Fsdk.vercel.ai) to iMessage.\n\n## Overview\n\nThe adapter acts as a bridge, allowing you to build AI agents and assistants with the Vercel AI SDK that communicate with users over iMessage. It leverages `@photon-ai\u002Fimessage-kit` (self-hosted) and `@photon-ai\u002Fadvanced-imessage-kit` (production infrastructure by Photon) under the hood.\n\n### Key Features\n\n- **Two Modes:** Run in **local mode** on any Mac for development, or **remote mode** connected to Photon's production iMessage infrastructure.\n- **Unified Interface:** Provides a consistent API for sending and receiving messages, regardless of the underlying mode.\n- **Vercel AI SDK Integration:** Implements the `Adapter` interface from the `chat` package, making it a drop-in solution.\n- **Markdown Conversion:** Automatically converts markdown from the AI SDK into iMessage-compatible plain text.\n\n---\n\n## Setup and Initialization\n\n### Installation\n\n```bash\npnpm install chat-adapter-imessage @photon-ai\u002Fimessage-kit\n# For remote mode, also install the advanced kit\npnpm install @photon-ai\u002Fadvanced-imessage-kit\n```\n\n### `createiMessageAdapter(config)`\n\nThis is the main entry point. It creates and configures an instance of the `iMessageAdapter`.\n\n```typescript\nimport { createiMessageAdapter } from 'chat-adapter-imessage';\n\n\u002F\u002F Local Mode: Runs on your Mac, uses your iMessage\nconst localAdapter = createiMessageAdapter({ local: true });\n\n\u002F\u002F Remote Mode: Connects to Photon's production servers\nconst remoteAdapter = createiMessageAdapter({\n  local: false,\n  serverUrl: process.env.IMESSAGE_SERVER_URL, \u002F\u002F Provided by Photon\n  apiKey: process.env.IMESSAGE_API_KEY      \u002F\u002F Provided by Photon\n});\n```\n\n#### Configuration (`iMessageAdapterConfig`)\n\n| Mode | `local` | `serverUrl` | `apiKey` | Description |\n| :--- | :--- | :--- | :--- | :--- |\n| Local | `true` | Optional | Optional | Runs on macOS using `@photon-ai\u002Fimessage-kit`. `serverUrl` and `apiKey` are ignored. |\n| Remote | `false` | **Required** | **Required** | Connects to Photon's infra using `@photon-ai\u002Fadvanced-imessage-kit`. |\n\n### Integrating with `Chat`\n\nOnce created, the adapter is passed to the `Chat` constructor from the Vercel AI SDK.\n\n```typescript\nimport { Chat } from 'chat';\nimport { createiMessageAdapter } from 'chat-adapter-imessage';\n\nconst adapter = createiMessageAdapter({ local: true });\n\nconst chat = new Chat({\n  adapter,\n  \u002F\u002F ... your other Chat config\n});\n```\n\n---\n\n## Core Adapter Methods\n\n### `adapter.initialize(chat)`\n\nCalled by the `Chat` instance to link the adapter. In remote mode, this method also establishes the WebSocket connection to the Photon server.\n\n### `adapter.postMessage(threadId, message)`\n\nSends a message to a specific iMessage thread.\n\n- `threadId`: The encoded thread identifier, which is the `chatGuid` (e.g., `iMessage;-;+15551234567`).\n- `message`: An `AdapterPostableMessage` object, which can be a simple string or a `FormattedContent` object with markdown.\n\n```typescript\nconst threadId = 'iMessage;-;+15551234567'; \u002F\u002F A direct message thread\n\n\u002F\u002F Send a simple text message\nawait adapter.postMessage(threadId, 'Hello from the adapter!');\n\n\u002F\u002F Send a message with markdown (will be converted to plain text)\nawait adapter.postMessage(threadId, {\n  markdown: 'Here are the results:\\n\\n- **Item 1**\\n- *Item 2*'\n});\n```\n\n### `adapter.editMessage(threadId, messageId, message)`\n\nEdits a previously sent message. **Only supported in remote mode.**\n\n```typescript\nawait adapter.editMessage(\n  'iMessage;-;+15551234567',\n  'p:0\u002FGUID-OF-MESSAGE-TO-EDIT',\n  'This is the corrected text.'\n);\n```\n\n### `adapter.deleteMessage(threadId, messageId)`\n\nUnsends\u002Fdeletes a previously sent message. **Only supported in remote mode.**\n\n```typescript\nawait adapter.deleteMessage(\n  'iMessage;-;+15551234567',\n  'p:0\u002FGUID-OF-MESSAGE-TO-DELETE'\n);\n```\n\n### `adapter.react(threadId, messageId, emoji)`\n\nAdds a tapback\u002Freaction to a message. **Only supported in remote mode.**\n\n- `emoji`: A standard emoji character or a name like `heart`, `like`, `laugh`.\n\n```typescript\nawait adapter.react(\n  'iMessage;-;+15551234567',\n  'p:0\u002FGUID-OF-MESSAGE-TO-REACT-TO',\n  '❤️'\n);\n```\n\n### `adapter.startGatewayListener(options)`\n\nThis is the primary method for receiving messages. It starts a listener that ingests messages from both local and remote SDKs and forwards them to the `Chat` instance.\n\n```typescript\n\u002F\u002F In your main application file\n\nconst adapter = createiMessageAdapter({ local: true });\nconst chat = new Chat({ adapter });\n\n\u002F\u002F Start listening for incoming iMessages\nadapter.startGatewayListener();\n\n\u002F\u002F Now, messages sent to your iMessage will be processed by the Chat SDK\nchat.on('message', (message) => {\n  console.log(`[${message.author.userName}]: ${message.text}`);\n  \u002F\u002F Your AI logic here...\n});\n```\n\n### `adapter.handleWebhook(request)`\n\n**This method is not supported.** The adapter does not use traditional webhooks for message ingestion. You must use `startGatewayListener()` instead.\n\n---\n\n## Type Reference\n\n### `iMessageThreadId`\n\nThe decoded `threadId` object.\n\n```typescript\ninterface iMessageThreadId {\n  chatGuid: string; \u002F\u002F e.g., \"iMessage;-;+1234567890\"\n}\n```\n\n### `iMessageGatewayMessageData`\n\nThe normalized message object that the adapter uses internally.\n\n```typescript\ninterface iMessageGatewayMessageData {\n  guid: string;\n  text: string | null;\n  sender: string;\n  senderName: string | null;\n  chatId: string;\n  isGroupChat: boolean;\n  isFromMe: boolean;\n  date: string; \u002F\u002F ISO 8601\n  attachments: iMessageAttachment[];\n  source: 'local' | 'remote';\n  raw?: unknown; \u002F\u002F Original message object from the underlying SDK\n}\n```\n\n### `NativeWebhookPayload`\n\nIf using the Self-Hosted Kit's native webhook feature, this is the shape of the JSON payload that will be sent to your endpoint. The adapter can process this payload.\n\n```typescript\ninterface NativeWebhookPayload {\n  guid: string;\n  text: string | null;\n  sender: string;\n  chatId: string;\n  \u002F\u002F ... and other fields from the Basic Kit Message object\n}\n```\n\n---\n\n## References\n\n1.  [Vercel AI SDK (Chat)](https:\u002F\u002Fsdk.vercel.ai\u002Fdocs\u002Fchat)\n2.  [chat-adapter-imessage on npm](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fchat-adapter-imessage)\n3.  [Photon](https:\u002F\u002Fphoton.codes\u002Fspectrum)\n","# Vercel AI SDK: iMessage Adapter Skill\n\nThis skill provides a complete reference for using `chat-adapter-imessage`, the official Photon adapter for connecting the [Vercel AI SDK (Chat SDK)](https:\u002F\u002Fsdk.vercel.ai) to iMessage.\n\n## Overview\n\nThe adapter acts as a bridge, allowing you to build AI agents and assistants with the Vercel AI SDK that communicate with users over iMessage. It leverages `@photon-ai\u002Fimessage-kit` (self-hosted) and `@photon-ai\u002Fadvanced-imessage-kit` (production infrastructure by Photon) under the hood.\n\n### Key Features\n\n- **Two Modes:** Run in **local mode** on any Mac for development, or **remote mode** connected to Photon's production iMessage infrastructure.\n- **Unified Interface:** Provides a consistent API for sending and receiving messages, regardless of the underlying mode.\n- **Vercel AI SDK Integration:** Implements the `Adapter` interface from the `chat` package, making it a drop-in solution.\n- **Markdown Conversion:** Automatically converts markdown from the AI SDK into iMessage-compatible plain text.\n\n---\n\n## Setup and Initialization\n\n### Installation\n\n```bash\npnpm install chat-adapter-imessage @photon-ai\u002Fimessage-kit\n# For remote mode, also install the advanced kit\npnpm install @photon-ai\u002Fadvanced-imessage-kit\n```\n\n### `createiMessageAdapter(config)`\n\nThis is the main entry point. It creates and configures an instance of the `iMessageAdapter`.\n\n```typescript\nimport { createiMessageAdapter } from 'chat-adapter-imessage';\n\n\u002F\u002F Local Mode: Runs on your Mac, uses your iMessage\nconst localAdapter = createiMessageAdapter({ local: true });\n\n\u002F\u002F Remote Mode: Connects to Photon's production servers\nconst remoteAdapter = createiMessageAdapter({\n  local: false,\n  serverUrl: process.env.IMESSAGE_SERVER_URL, \u002F\u002F Provided by Photon\n  apiKey: process.env.IMESSAGE_API_KEY      \u002F\u002F Provided by Photon\n});\n```\n\n#### Configuration (`iMessageAdapterConfig`)\n\n| Mode | `local` | `serverUrl` | `apiKey` | Description |\n| :--- | :--- | :--- | :--- | :--- |\n| Local | `true` | Optional | Optional | Runs on macOS using `@photon-ai\u002Fimessage-kit`. `serverUrl` and `apiKey` are ignored. |\n| Remote | `false` | **Required** | **Required** | Connects to Photon's infra using `@photon-ai\u002Fadvanced-imessage-kit`. |\n\n### Integrating with `Chat`\n\nOnce created, the adapter is passed to the `Chat` constructor from the Vercel AI SDK.\n\n```typescript\nimport { Chat } from 'chat';\nimport { createiMessageAdapter } from 'chat-adapter-imessage';\n\nconst adapter = createiMessageAdapter({ local: true });\n\nconst chat = new Chat({\n  adapter,\n  \u002F\u002F ... your other Chat config\n});\n```\n\n---\n\n## Core Adapter Methods\n\n### `adapter.initialize(chat)`\n\nCalled by the `Chat` instance to link the adapter. In remote mode, this method also establishes the WebSocket connection to the Photon server.\n\n### `adapter.postMessage(threadId, message)`\n\nSends a message to a specific iMessage thread.\n\n- `threadId`: The encoded thread identifier, which is the `chatGuid` (e.g., `iMessage;-;+15551234567`).\n- `message`: An `AdapterPostableMessage` object, which can be a simple string or a `FormattedContent` object with markdown.\n\n```typescript\nconst threadId = 'iMessage;-;+15551234567'; \u002F\u002F A direct message thread\n\n\u002F\u002F Send a simple text message\nawait adapter.postMessage(threadId, 'Hello from the adapter!');\n\n\u002F\u002F Send a message with markdown (will be converted to plain text)\nawait adapter.postMessage(threadId, {\n  markdown: 'Here are the results:\\n\\n- **Item 1**\\n- *Item 2*'\n});\n```\n\n### `adapter.editMessage(threadId, messageId, message)`\n\nEdits a previously sent message. **Only supported in remote mode.**\n\n```typescript\nawait adapter.editMessage(\n  'iMessage;-;+15551234567',\n  'p:0\u002FGUID-OF-MESSAGE-TO-EDIT',\n  'This is the corrected text.'\n);\n```\n\n### `adapter.deleteMessage(threadId, messageId)`\n\nUnsends\u002Fdeletes a previously sent message. **Only supported in remote mode.**\n\n```typescript\nawait adapter.deleteMessage(\n  'iMessage;-;+15551234567',\n  'p:0\u002FGUID-OF-MESSAGE-TO-DELETE'\n);\n```\n\n### `adapter.react(threadId, messageId, emoji)`\n\nAdds a tapback\u002Freaction to a message. **Only supported in remote mode.**\n\n- `emoji`: A standard emoji character or a name like `heart`, `like`, `laugh`.\n\n```typescript\nawait adapter.react(\n  'iMessage;-;+15551234567',\n  'p:0\u002FGUID-OF-MESSAGE-TO-REACT-TO',\n  '❤️'\n);\n```\n\n### `adapter.startGatewayListener(options)`\n\nThis is the primary method for receiving messages. It starts a listener that ingests messages from both local and remote SDKs and forwards them to the `Chat` instance.\n\n```typescript\n\u002F\u002F In your main application file\n\nconst adapter = createiMessageAdapter({ local: true });\nconst chat = new Chat({ adapter });\n\n\u002F\u002F Start listening for incoming iMessages\nadapter.startGatewayListener();\n\n\u002F\u002F Now, messages sent to your iMessage will be processed by the Chat SDK\nchat.on('message', (message) => {\n  console.log(`[${message.author.userName}]: ${message.text}`);\n  \u002F\u002F Your AI logic here...\n});\n```\n\n### `adapter.handleWebhook(request)`\n\n**This method is not supported.** The adapter does not use traditional webhooks for message ingestion. You must use `startGatewayListener()` instead.\n\n---\n\n## Type Reference\n\n### `iMessageThreadId`\n\nThe decoded `threadId` object.\n\n```typescript\ninterface iMessageThreadId {\n  chatGuid: string; \u002F\u002F e.g., \"iMessage;-;+1234567890\"\n}\n```\n\n### `iMessageGatewayMessageData`\n\nThe normalized message object that the adapter uses internally.\n\n```typescript\ninterface iMessageGatewayMessageData {\n  guid: string;\n  text: string | null;\n  sender: string;\n  senderName: string | null;\n  chatId: string;\n  isGroupChat: boolean;\n  isFromMe: boolean;\n  date: string; \u002F\u002F ISO 8601\n  attachments: iMessageAttachment[];\n  source: 'local' | 'remote';\n  raw?: unknown; \u002F\u002F Original message object from the underlying SDK\n}\n```\n\n### `NativeWebhookPayload`\n\nIf using the Self-Hosted Kit's native webhook feature, this is the shape of the JSON payload that will be sent to your endpoint. The adapter can process this payload.\n\n```typescript\ninterface NativeWebhookPayload {\n  guid: string;\n  text: string | null;\n  sender: string;\n  chatId: string;\n  \u002F\u002F ... and other fields from the Basic Kit Message object\n}\n```\n\n---\n\n## References\n\n1.  [Vercel AI SDK (Chat)](https:\u002F\u002Fsdk.vercel.ai\u002Fdocs\u002Fchat)\n2.  [chat-adapter-imessage on npm](https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fchat-adapter-imessage)\n3.  [Photon](https:\u002F\u002Fphoton.codes\u002Fspectrum)\n",{"name":5,"license":15,"metadata":49,"description":52},{"author":50,"version":51},"photon-hq","1.0.0","Connect the Vercel AI SDK to iMessage. Build AI agents and assistants that communicate over iMessage using chat-adapter-imessage, the official Photon adapter. Local mode (runs on your Mac) and remote mode (Photon's production infrastructure). Covers createiMessageAdapter, postMessage, editMessage, deleteMessage, react, startGatewayListener, types, and integration with the Chat SDK. Keywords: vercel ai sdk, imessage, chat adapter, ai agent, chatbot, conversational ai, messaging, apple messages, vercel, nextjs, ai assistant, chat sdk, real-time, macos.\n","main","6ef866230c1ba3459fd08fc65141dfd37fffd41a",0,"https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills","https:\u002F\u002Fskills.henryzh.dev","https:\u002F\u002Fgithub.com\u002Fcaezium","henryzh.dev","quant, data science, full-stack, robotics.\r\nbuilding cool stuff","2026-08-24 19:21:44",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add caezium\u002Fskills --skill chat-adapter-imessage",{"tool":68,"command":69},"bunx","bunx skills add caezium\u002Fskills --skill chat-adapter-imessage",{"tool":71,"command":72},"pnpm","pnpm dlx skills add caezium\u002Fskills --skill chat-adapter-imessage","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fchat-adapter-imessage\u002FSKILL.md",true,[],[77,99,127,145,166,188],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":91,"publishedAt":44},"01M71JT4RYCAS18RF6003YYR1D","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwriting-for-agents\u002FSKILL.md",[83,86],{"categoryNo":84,"categoryName":85,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":87,"categoryName":88,"taxonomyType":89,"taxonomyTypeDesc":90},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[92,93,94,95,96,97,98],"writing for agents","for","writing","editing","use","documents","when",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":108,"publishedAt":44},"01M71JT0GES4AZ5ADH8EADNN1Z","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwrangler\u002FSKILL.md",[105],{"categoryNo":106,"categoryName":107,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",[101,109,110,111,112,113,114,115,116,117,118,119,120,93,121,122,123,124,125,126],"cloudflare","d1","knowledge","workflows","cli","secrets","commands","syntax","cloudflare workers","r2","queues","running","containers","correct","load","workers","best practices","store",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":133,"publishedAt":44},"01M71JSWX4R203M32K9A18AAW8","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fworkers-best-practices\u002FSKILL.md",[],[134,124,125,135,136,137,93,109,138,111,139,101,94,123,98,140,141,142,143,144],"workers best practices","observability","reviews","promises","worker","new","code","common","streaming","state","anti-patterns",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":44},"01M71JST6P88MXGT2MWDTPJGEG","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwizard\u002FSKILL.md",[],[147,120,152,93,153,154,155,156,96,157,98,158,159,160,161,162,163,164,165,114],"setting","up","ci","provisioning infrastructure","only","invoke","Bash","one","interactive","can","credentials","dashboard","generate","human",{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":170,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":44},"01M71JSQ95S7BQ61DAPN95X2W4","why","Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available evidence sources, searches each relevant category, and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fwhy\u002FSKILL.md",[],[168,174,175,176,177,93,178,179,96,180,181,182,183,184,185,186,187],"sources","thresholds","evidence","relevant","runtime","design","decisions","work","how","behavior","read","data","rationale","returns",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":197,"publishedAt":44},"01M71JSMHFVSH8HK8GXN6YAX6J","week-prep","Generate a briefing with calendar, tasks, and attention flags. Use for \"week prep\", \"briefing\", or \"what's on this week\".","https:\u002F\u002Fgithub.com\u002Fcaezium\u002Fskills\u002Fblob\u002Fmain\u002Fweek-prep\u002FSKILL.md",[194],{"categoryNo":195,"categoryName":196,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[198,199,200,201,202,93,203,38,204,205,96,158,206,207,208,164,209,184,210,211],"week prep","prep","deep","attention","get","search","briefing","MCP","tasks","with","slack","calendar","flags","grep"]