[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AH7AF6FMTTZ8B2PWWZGZGS":3,"skill-same:01M7AH7AF6FMTTZ8B2PWWZGZGS":62},{"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":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":13,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7AH7AF6FMTTZ8B2PWWZGZGS","firebase-ai-logic-basics",null,"Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.","navalkashyapp\u002Fcareer-manager","navalkashyapp","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F262655051?v=4","01M7AH780EACQ1NGMWVZFY45CW","01M7AH781J8K4KTV64YH3G31MK",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ffirebase_ai_logic_basics\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: firebase-ai-logic-basics\ndescription: Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.\nversion: 1.0.1\n---\n\n# Firebase AI Logic Basics\n\n## Overview\n\nFirebase AI Logic is a product of Firebase that allows developers to add gen AI\nto their mobile and web apps using client-side SDKs. You can call Gemini models\ndirectly from your app without managing a dedicated backend. Firebase AI Logic,\nwhich was previously known as \"Vertex AI for Firebase\", represents the evolution\nof Google's AI integration platform for mobile and web developers.\n\nIt supports the two Gemini API providers:\n\n- **Gemini Developer API**: It has a free tier ideal for prototyping, and\n  pay-as-you-go for production\n- **Vertex AI Gemini API**: Ideal for scale with enterprise-grade production\n  readiness, requires Blaze plan\n\nUse the Gemini Developer API as a default, and only Vertex AI Gemini API if the\napplication requires it.\n\n## Setup & Initialization\n\n### Prerequisites\n\n- Before starting, ensure you have **Node.js 16+** and npm installed. Install\n  them if they aren’t already available.\n- Identify the platform the user is interested in building on prior to starting:\n  Android, iOS, Flutter or Web.\n- If their platform is unsupported, Direct the user to Firebase Docs to learn\n  how to set up AI Logic for their application (share this link with the user\n  https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fget-started)\n\n### Installation\n\nThe library is part of the standard Firebase Web SDK.\n\n`npm install -g firebase@latest`\n\nIf you're in a firebase directory (with a firebase.json) the currently selected\nproject will be marked with \"current\" using this command:\n\n`npx -y firebase-tools@latest projects:list`\n\nEnsure there's at least one app associated with the current project\n\n`npx -y firebase-tools@latest apps:list`\n\nInitialize AI logic SDK with the init command\n\n`npx -y firebase-tools@latest init ailogic`\n\nThis will automatically enable the Gemini Developer API in the Firebase console.\n\nMore info in\n[Firebase AI Logic Getting Started](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fget-started.md.txt)\n\n## Core Capabilities\n\n> [!WARNING] **CRITICAL: Use current model names:** Always check the\n> [Firebase AI Logic Models documentation](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fmodels.md.txt)\n> for the currently supported model names. Do NOT use `gemini-2.0-pro` or\n> `gemini-2.0-flash` or other older models that are shutdown.\n\n### Text-Only Generation\n\n### Multimodal (Text + Images\u002FAudio\u002FVideo\u002FPDF input)\n\nFirebase AI Logic allows Gemini models to analyze image files directly from your\napp. This enables features like creating captions, answering questions about\nimages, detecting objects, and categorizing images. Beyond images, Gemini can\nanalyze other media types like audio, video, and PDFs by passing them as inline\ndata with their MIME type. For files larger than 20 megabytes (which can cause\nHTTP 413 errors as inline data), store them in Cloud Storage for Firebase and\npass their URLs to the Gemini Developer API.\n\n### Chat Session (Multi-turn)\n\nMaintain history automatically using `startChat`.\n\n### Streaming Responses\n\nTo improve the user experience by showing partial results as they arrive (like a\ntyping effect), use `generateContentStream` instead of `generateContent` for\nfaster display of results.\n\n### Generate Images with Nano Banana\n\n> [!WARNING] **Use current Image model names:** Always check the\n> [Firebase AI Logic Models documentation](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fmodels.md.txt)\n> for the currently supported image generation (Nano Banana) model names.\n\n- Requires an upgraded Blaze pay-as-you-go billing plan.\n\n### Search Grounding with the built in googleSearch tool\n\n## Supported Platforms and Frameworks\n\nSupported Platforms and Frameworks include Kotlin and Java for Android, Swift\nfor iOS, JavaScript for web apps, Dart for Flutter, and C Sharp for Unity.\n\n## Advanced Features\n\n### Structured Output (JSON)\n\nEnforce a specific JSON schema for the response.\n\n### On-Device AI (Hybrid)\n\nHybrid on-device inference for web apps, where the Firebase Javascript SDK\nautomatically checks for Gemini Nano's availability (after installation) and\nswitches between on-device or cloud-hosted prompt execution. This requires\nspecific steps to enable model usage in the Chrome browser, more info in the\n[hybrid-on-device-inference documentation](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fhybrid-on-device-inference.md.txt).\n\n## Security & Production\n\n### App Check\n\n> [!WARNING] **Critical Safety Requirement:** In order to use AI Logic safely,\n> you MUST set up App Check on your app. This prevents unauthorized clients from\n> using your API quota and accessing your backend resources.\n\nSee\n[App Check with reCAPTCHA Enterprise](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fapp-check\u002Fweb\u002Frecaptcha-enterprise-provider.md.txt)\nfor setup instructions.\n\n### Remote Config\n\nConsider that you do not need to hardcode model names (e.g., a specific model\nversion string). Use Firebase Remote Config to update model versions dynamically\nwithout deploying new client code. See\n[Changing model names remotely](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fchange-model-name-remotely.md.txt)\n\n> [!WARNING] **CRITICAL: Backend Provisioning Required** For all platforms\n> (Flutter, Android, iOS, Web), you MUST run `npx firebase-tools init ailogic`\n> to provision the service. `flutterfire configure` ONLY handles client\n> configuration and does NOT enable the AI service, leading to\n> `PERMISSION_DENIED` errors.\n\n## Initialization Code References\n\n| Language, Framework, Platform | Gemini API provider                  | Context URL                                     |\n| :---------------------------- | :----------------------------------- | :---------------------------------------------- |\n| Web Modular API               | Gemini Developer API (Developer API) | firebase:\u002F\u002Fdocs\u002Fai-logic\u002Fget-started            |\n| iOS (Swift)                   | Gemini Developer API                 | [ios_setup.md](references\u002Fios_setup.md)         |\n| Flutter (Dart)                | Gemini Developer API                 | [flutter_setup.md](references\u002Fflutter_setup.md) |\n\n> [!WARNING] **CRITICAL: Use current model names:** Always check the\n> [Firebase AI Logic Models documentation](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fmodels.md.txt)\n> for the currently supported model names. Do NOT use `gemini-2.0-pro` or\n> `gemini-2.0-flash` or other older models that are shutdown.\n\n## References\n\n[Web SDK code examples and usage patterns](references\u002Fusage_patterns_web.md)\n[iOS SDK code examples and usage patterns](references\u002Fios_setup.md)\n[Flutter SDK code examples and usage patterns](references\u002Fflutter_setup.md)\n\n[Android (Kotlin) SDK usage patterns](references\u002Fusage_patterns_android.md)\n","# Firebase AI Logic Basics\n\n## Overview\n\nFirebase AI Logic is a product of Firebase that allows developers to add gen AI\nto their mobile and web apps using client-side SDKs. You can call Gemini models\ndirectly from your app without managing a dedicated backend. Firebase AI Logic,\nwhich was previously known as \"Vertex AI for Firebase\", represents the evolution\nof Google's AI integration platform for mobile and web developers.\n\nIt supports the two Gemini API providers:\n\n- **Gemini Developer API**: It has a free tier ideal for prototyping, and\n  pay-as-you-go for production\n- **Vertex AI Gemini API**: Ideal for scale with enterprise-grade production\n  readiness, requires Blaze plan\n\nUse the Gemini Developer API as a default, and only Vertex AI Gemini API if the\napplication requires it.\n\n## Setup & Initialization\n\n### Prerequisites\n\n- Before starting, ensure you have **Node.js 16+** and npm installed. Install\n  them if they aren’t already available.\n- Identify the platform the user is interested in building on prior to starting:\n  Android, iOS, Flutter or Web.\n- If their platform is unsupported, Direct the user to Firebase Docs to learn\n  how to set up AI Logic for their application (share this link with the user\n  https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fget-started)\n\n### Installation\n\nThe library is part of the standard Firebase Web SDK.\n\n`npm install -g firebase@latest`\n\nIf you're in a firebase directory (with a firebase.json) the currently selected\nproject will be marked with \"current\" using this command:\n\n`npx -y firebase-tools@latest projects:list`\n\nEnsure there's at least one app associated with the current project\n\n`npx -y firebase-tools@latest apps:list`\n\nInitialize AI logic SDK with the init command\n\n`npx -y firebase-tools@latest init ailogic`\n\nThis will automatically enable the Gemini Developer API in the Firebase console.\n\nMore info in\n[Firebase AI Logic Getting Started](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fget-started.md.txt)\n\n## Core Capabilities\n\n> [!WARNING] **CRITICAL: Use current model names:** Always check the\n> [Firebase AI Logic Models documentation](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fmodels.md.txt)\n> for the currently supported model names. Do NOT use `gemini-2.0-pro` or\n> `gemini-2.0-flash` or other older models that are shutdown.\n\n### Text-Only Generation\n\n### Multimodal (Text + Images\u002FAudio\u002FVideo\u002FPDF input)\n\nFirebase AI Logic allows Gemini models to analyze image files directly from your\napp. This enables features like creating captions, answering questions about\nimages, detecting objects, and categorizing images. Beyond images, Gemini can\nanalyze other media types like audio, video, and PDFs by passing them as inline\ndata with their MIME type. For files larger than 20 megabytes (which can cause\nHTTP 413 errors as inline data), store them in Cloud Storage for Firebase and\npass their URLs to the Gemini Developer API.\n\n### Chat Session (Multi-turn)\n\nMaintain history automatically using `startChat`.\n\n### Streaming Responses\n\nTo improve the user experience by showing partial results as they arrive (like a\ntyping effect), use `generateContentStream` instead of `generateContent` for\nfaster display of results.\n\n### Generate Images with Nano Banana\n\n> [!WARNING] **Use current Image model names:** Always check the\n> [Firebase AI Logic Models documentation](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fmodels.md.txt)\n> for the currently supported image generation (Nano Banana) model names.\n\n- Requires an upgraded Blaze pay-as-you-go billing plan.\n\n### Search Grounding with the built in googleSearch tool\n\n## Supported Platforms and Frameworks\n\nSupported Platforms and Frameworks include Kotlin and Java for Android, Swift\nfor iOS, JavaScript for web apps, Dart for Flutter, and C Sharp for Unity.\n\n## Advanced Features\n\n### Structured Output (JSON)\n\nEnforce a specific JSON schema for the response.\n\n### On-Device AI (Hybrid)\n\nHybrid on-device inference for web apps, where the Firebase Javascript SDK\nautomatically checks for Gemini Nano's availability (after installation) and\nswitches between on-device or cloud-hosted prompt execution. This requires\nspecific steps to enable model usage in the Chrome browser, more info in the\n[hybrid-on-device-inference documentation](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fhybrid-on-device-inference.md.txt).\n\n## Security & Production\n\n### App Check\n\n> [!WARNING] **Critical Safety Requirement:** In order to use AI Logic safely,\n> you MUST set up App Check on your app. This prevents unauthorized clients from\n> using your API quota and accessing your backend resources.\n\nSee\n[App Check with reCAPTCHA Enterprise](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fapp-check\u002Fweb\u002Frecaptcha-enterprise-provider.md.txt)\nfor setup instructions.\n\n### Remote Config\n\nConsider that you do not need to hardcode model names (e.g., a specific model\nversion string). Use Firebase Remote Config to update model versions dynamically\nwithout deploying new client code. See\n[Changing model names remotely](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fchange-model-name-remotely.md.txt)\n\n> [!WARNING] **CRITICAL: Backend Provisioning Required** For all platforms\n> (Flutter, Android, iOS, Web), you MUST run `npx firebase-tools init ailogic`\n> to provision the service. `flutterfire configure` ONLY handles client\n> configuration and does NOT enable the AI service, leading to\n> `PERMISSION_DENIED` errors.\n\n## Initialization Code References\n\n| Language, Framework, Platform | Gemini API provider                  | Context URL                                     |\n| :---------------------------- | :----------------------------------- | :---------------------------------------------- |\n| Web Modular API               | Gemini Developer API (Developer API) | firebase:\u002F\u002Fdocs\u002Fai-logic\u002Fget-started            |\n| iOS (Swift)                   | Gemini Developer API                 | [ios_setup.md](references\u002Fios_setup.md)         |\n| Flutter (Dart)                | Gemini Developer API                 | [flutter_setup.md](references\u002Fflutter_setup.md) |\n\n> [!WARNING] **CRITICAL: Use current model names:** Always check the\n> [Firebase AI Logic Models documentation](https:\u002F\u002Ffirebase.google.com\u002Fdocs\u002Fai-logic\u002Fmodels.md.txt)\n> for the currently supported model names. Do NOT use `gemini-2.0-pro` or\n> `gemini-2.0-flash` or other older models that are shutdown.\n\n## References\n\n[Web SDK code examples and usage patterns](references\u002Fusage_patterns_web.md)\n[iOS SDK code examples and usage patterns](references\u002Fios_setup.md)\n[Flutter SDK code examples and usage patterns](references\u002Fflutter_setup.md)\n\n[Android (Kotlin) SDK usage patterns](references\u002Fusage_patterns_android.md)\n",{"name":5,"version":23,"description":7},"1.0.1","main","2692e7fec5c1e4033e71ae062ad6a3c622650a2c",".agents\u002Fskills\u002Ffirebase_ai_logic_basics","https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager","https:\u002F\u002Fgithub.com\u002Fnavalkashyapp","2026-11-13 00:25:38",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add navalkashyapp\u002Fcareer-manager --skill firebase-ai-logic-basics",{"tool":36,"command":37},"bunx","bunx skills add navalkashyapp\u002Fcareer-manager --skill firebase-ai-logic-basics",{"tool":39,"command":40},"pnpm","pnpm dlx skills add navalkashyapp\u002Fcareer-manager --skill firebase-ai-logic-basics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ffirebase_ai_logic_basics\u002FSKILL.md",true,[44,50,54,58],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"references\u002Fflutter_setup.md","REFERENCE","参考文档",3091,"https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ffirebase_ai_logic_basics\u002Freferences\u002Fflutter_setup.md",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fios_setup.md",4834,"https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ffirebase_ai_logic_basics\u002Freferences\u002Fios_setup.md",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fusage_patterns_android.md",4545,"https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ffirebase_ai_logic_basics\u002Freferences\u002Fusage_patterns_android.md",{"path":59,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fusage_patterns_web.md",5450,"https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ffirebase_ai_logic_basics\u002Freferences\u002Fusage_patterns_web.md",[63,71,78,85,93,99],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M7AH9MM5XWGNSJA5J1Z308QA","career-ops-plugin-notion","How to mirror the career-ops tracker to a Notion database and read records back as job leads.","MIT","https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002Fcareer-ops\u002Fplugins\u002Fnotion\u002Fskill.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M7AH9HJHKW065CFTKYZSPA45","career-ops-plugin-gmail","How to pull job leads from a Gmail label into the career-ops pipeline.","https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002Fcareer-ops\u002Fplugins\u002Fgmail\u002Fskill.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M7AH9FSXMBR88B8R13QQJ9RQ","career-ops-plugin-apify","How to scan a job source through an Apify actor as a keyed provider.","https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002Fcareer-ops\u002Fplugins\u002Fapify\u002Fskill.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M7AH9CQGE2QRNDY9H8R1V9CA","career-ops-plugin-{{NAME}}","How to use the {{NAME}} plugin and the data it produces.","https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002Fcareer-ops\u002Fplugins\u002F_template\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002Fcareer-ops\u002Fplugins\u002F_template\u002Fskill.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M7AH9B90WAXH4KBBV6MM9HBR","career-ops","https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002Fcareer-ops\u002F.qwen\u002Fskills\u002Fcareer-ops\u002FSKILL.md",[],[],{"skillNo":100,"name":95,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":18},"01M7AH98FTERMDZT7AN7W37A94","https:\u002F\u002Fgithub.com\u002Fnavalkashyapp\u002Fcareer-manager\u002Fblob\u002Fmain\u002Fcareer-ops\u002F.opencode\u002Fskills\u002Fcareer-ops\u002FSKILL.md",[],[]]