[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-75102":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":10,"languages":10,"totalLinesOfCode":10,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":29,"readmeContent":30,"aiSummary":31,"trendingCount":15,"starSnapshotCount":15,"syncStatus":32,"lastSyncTime":33,"discoverSource":34},75102,"gemini-skills","google-gemini\u002Fgemini-skills","google-gemini","Skills for the Gemini API, SDK and model\u002Fagent interactions","https:\u002F\u002Fai.google.dev\u002Fgemini-api\u002Fdocs",null,3613,353,37,4,0,11,30,152,33,29.65,"Apache License 2.0",false,"main",true,[26,27,28],"gemini","gemini-api","skills","2026-06-12 02:03:32","# Gemini API skills\n\nA library of skills for the Gemini API, SDK and model interactions.\n\n## About\n\nLLMs have fixed knowledge, being trained at a specific point in time. Software\ndev is fast paced and changes often, where new libraries are launched every day\nand best practices evolve quickly.\n\nThis leaves a knowledge gap that language models can't solve on their own. For\nexample, models don't know about themselves when they're trained, and they\naren't necessarily aware of subtle changes in best practices (like [thought\ncirculation](https:\u002F\u002Fai.google.dev\u002Fgemini-api\u002Fdocs\u002Fthought-signatures)) or SDK\nchanges.\n\n[Skills](https:\u002F\u002Fagentskills.io\u002F) are a lightweight technique for adding\nrelevant context to your agents. This repo contains skills related to building\napps powered by the Gemini API.\n\n### Performance\n\nOur evaluations found that adding this skill improved an agent's ability to\ngenerate correct API code following best practices to 87% with Gemini 3 Flash\nand 96% with Gemini 3.1 Pro. For more details, see our blog post: \n[Closing the knowledge gap with agent skills](https:\u002F\u002Fdevelopers.googleblog.com\u002Fclosing-the-knowledge-gap-with-agent-skills\u002F).\n\n## Skills in this repo\n\n> [!IMPORTANT]\n> The `vertex-ai-api-dev` skill has moved to\n> [skills\u002Fcloud\u002Fgemini-api](https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fcloud\u002Fgemini-api).\n\n| Skill | Description |\n| :--- | :--- |\n| [`gemini-api-dev`](skills\u002Fgemini-api-dev) | Skill for developing Gemini-powered apps. Provides the best practices for building apps that use the Gemini API. |\n| [`gemini-live-api-dev`](skills\u002Fgemini-live-api-dev) | Skill for building real-time, bidirectional streaming apps with the Gemini Live API. Covers WebSocket-based audio\u002Fvideo\u002Ftext streaming, voice activity detection, native audio features, function calling, and session management. |\n| [`gemini-interactions-api`](skills\u002Fgemini-interactions-api) | Skill for building apps with the [Gemini Interactions API](https:\u002F\u002Fai.google.dev\u002Fgemini-api\u002Fdocs\u002Finteractions?ua=chat). Covers text generation, multi-turn chat, streaming, function calling, structured output, image generation, Deep Research agents, deprecated model guardrails, and both Python and TypeScript SDKs. |\n\n## Installation\n\nYou can browse and install skills using either the [Vercel skills CLI](https:\u002F\u002Fskills.sh) or the [Context7 skills CLI](https:\u002F\u002Fcontext7.com).\n\n### Using [Vercel skills CLI](https:\u002F\u002Fskills.sh)\n\n```sh\n# Interactively browse and install skills.\nnpx skills add google-gemini\u002Fgemini-skills --list\n\n# Install a specific skill (e.g., gemini-api-dev).\nnpx skills add google-gemini\u002Fgemini-skills --skill gemini-api-dev --global\n```\n\n### Using [Context7 skills CLI](https:\u002F\u002Fcontext7.com)\n\n```sh\n# Interactively browse and install skills.\nnpx ctx7 skills install \u002Fgoogle-gemini\u002Fgemini-skills\n\n# Install a specific skill (e.g., gemini-api-dev).\nnpx ctx7 skills install \u002Fgoogle-gemini\u002Fgemini-skills gemini-api-dev\n```\n\n## Gemini API docs MCP\n\nA public Model Context Protocol (MCP) server for the Gemini API is available at\n`https:\u002F\u002Fgemini-api-docs-mcp.dev`. Connecting your coding agent to this server ensures that\nall queries have access to the latest APIs, code updates, and optimal configuration examples.\n\nRun the following command in your agent's terminal or project root to install\nthe server:\n\n    npx add-mcp \"https:\u002F\u002Fgemini-api-docs-mcp.dev\"\n\nThis server adds a `search_docs` tool that your agent can use to\nretrieve real-time API definitions and integration patterns from the official\nGemini API documentation.\n\nNote that the `gemini-api-dev` skill works with or without the MCP server, so\nwe recommend installing them both.\n\n## More info\n\nYou can find additional information about setting up your coding assistant with\nGemini API MCP and Skills in [the docs](https:\u002F\u002Fai.google.dev\u002Fgemini-api\u002Fdocs\u002Fcoding-agents).\n\n## Disclaimer\n\nThis is not an officially supported Google product. This project is not\neligible for the [Google Open Source Software Vulnerability Rewards\nProgram](https:\u002F\u002Fbughunters.google.com\u002Fopen-source-security).\n","该项目提供了用于Gemini API、SDK及模型交互的技能库。核心功能包括为基于Gemini API开发的应用提供最佳实践指南，支持实时双向流媒体应用构建，并涵盖文本生成、多轮对话等高级功能。技术上，通过添加这些技能，可以显著提升代理遵循最佳实践生成正确API代码的能力，例如在使用Gemini 3 Flash时准确率达到87%，而Gemini 3.1 Pro则达到96%。适用于需要快速集成最新软件开发知识和实践到语言模型中的场景，如开发高效且符合当前标准的AI应用程序或服务。",2,"2026-06-11 03:52:21","high_star"]