[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-gemini-cli-extensions-starter-fr":3,"seo:pack:gemini-cli-extensions-starter:fr":96},{"code":4,"message":5,"data":6},200,"操作成功",{"pack":7},{"slug":8,"icon":9,"tone":10,"status":11,"status_label":12,"title":13,"description":14,"items":15,"install_cmd":95},"gemini-cli-extensions-starter","✨","#4285F4","new","Nouveau · cette semaine","Pack de Démarrage Extensions Gemini CLI","Dix choix pour le dev qui vient d'installer Gemini CLI et veut tirer parti du multimodal Gemini et de l'écosystème Google. La base CLI, les extensions officielles sous-cotées (BigQuery \u002F Genkit \u002F Firebase \u002F Flutter \u002F gcloud) et quatre MCPs qui transforment Gemini en designer Stitch, opérateur Workspace, analyste NotebookLM et copilote Cloud Ops.",[16,28,38,45,52,58,65,75,82,89],{"id":17,"uuid":18,"slug":19,"title":20,"description":21,"author_name":22,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},795,"926633bc-d041-486a-bda3-5a3cecabc0a8","gemini-cli-google-ai-coding-agent-terminal-926633bc","Gemini CLI — Google AI Coding Agent in Terminal","Google's official CLI coding agent powered by Gemini 2.5 Pro. Free 60 requests\u002Fmin for Gemini users with 1M token context, MCP support, and Google ecosystem integration.","AI Open Source",125,0,"en","script","Script",{"id":29,"uuid":30,"slug":31,"title":32,"description":33,"author_name":34,"view_count":35,"vote_count":24,"lang_type":25,"type":36,"type_label":37},87,"4fd37d4a-e375-41e6-bf0d-121659056855","gemini-cli-extension-bigquery-data-analytics-sql-4fd37d4a","Gemini CLI Extension: BigQuery — Data Analytics & SQL","Gemini CLI extension for BigQuery. Write SQL queries, analyze datasets, optimize performance, and manage tables.","Google · Gemini Team",135,"skill","Skill",{"id":39,"uuid":40,"slug":41,"title":42,"description":43,"author_name":34,"view_count":44,"vote_count":24,"lang_type":25,"type":36,"type_label":37},88,"70150d0c-4b06-447f-9bde-9a6741a06389","gemini-cli-extension-gcloud-cloud-cli-operations-70150d0c","Gemini CLI Extension: gcloud — Cloud CLI Operations","Gemini CLI extension for Google Cloud Platform. Deploy, configure, and manage GCP resources via natural language commands.",138,{"id":46,"uuid":47,"slug":48,"title":49,"description":50,"author_name":34,"view_count":51,"vote_count":24,"lang_type":25,"type":36,"type_label":37},91,"0f9fe677-0066-422d-9738-c4a8dede50bc","gemini-cli-extension-genkit-ai-framework-development-0f9fe677","Gemini CLI Extension: Genkit — AI Framework Development","Gemini CLI extension for Firebase Genkit. Build AI-powered features with flows, prompts, retrievers, and model integration.",119,{"id":53,"uuid":54,"slug":55,"title":56,"description":57,"author_name":34,"view_count":51,"vote_count":24,"lang_type":25,"type":36,"type_label":37},83,"43efc92f-0517-4ad5-907c-08d899f32c66","gemini-cli-extension-firebase-project-deploy-manage-43efc92f","Gemini CLI Extension: Firebase — Project Deploy & Manage","Gemini CLI extension for Firebase. Deploy functions, manage databases, configure auth, and monitor projects via natural language.",{"id":59,"uuid":60,"slug":61,"title":62,"description":63,"author_name":34,"view_count":64,"vote_count":24,"lang_type":25,"type":36,"type_label":37},85,"7d515779-d57f-4604-a034-630ce676e80f","gemini-cli-extension-flutter-cross-platform-app-dev-7d515779","Gemini CLI Extension: Flutter — Cross-Platform App Dev","Gemini CLI extension for Flutter development. Widget creation, state management, navigation, and platform-specific code generation.",150,{"id":66,"uuid":67,"slug":68,"title":69,"description":70,"author_name":71,"view_count":72,"vote_count":24,"lang_type":25,"type":73,"type_label":74},3782,"9fd620b8-2e2b-5913-b38a-076deb3c396c","gemini-cloud-assist-mcp-google-cloud-ops-tools","Gemini Cloud Assist MCP — Google Cloud Ops Tools","Google Cloud Assist MCP server (Private Preview) that connects MCP clients to Gemini Cloud Assist APIs; verified 60 stars and remote MCP endpoints.","MCP Hub",3,"mcp","MCP",{"id":76,"uuid":77,"slug":78,"title":79,"description":80,"author_name":34,"view_count":81,"vote_count":24,"lang_type":25,"type":73,"type_label":74},151,"05e7ef0b-cc4a-46e5-8b15-d78a626fcd6f","google-stitch-mcp-ai-design-via-model-context-protocol-05e7ef0b","Google Stitch MCP — AI Design via Model Context Protocol","Connect Claude Code, Cursor, Gemini CLI, or VS Code to Google Stitch for AI-driven UI design. Create projects, generate screens from text, edit designs, manage design systems — all via MCP.",450,{"id":83,"uuid":84,"slug":85,"title":86,"description":87,"author_name":71,"view_count":88,"vote_count":24,"lang_type":25,"type":73,"type_label":74},787,"557765e3-1497-4f9d-ad89-23f9460c6d75","google-workspace-mcp-gmail-drive-calendar-ai-557765e3","Google Workspace MCP — Gmail Drive Calendar for AI","Official Google CLI with built-in MCP server for all Workspace APIs. One command gives AI agents access to Gmail, Drive, Calendar, Docs, Sheets, and 10+ Google services.",141,{"id":90,"uuid":91,"slug":92,"title":93,"description":94,"author_name":71,"view_count":72,"vote_count":24,"lang_type":25,"type":73,"type_label":74},3176,"bc3d5f4b-e533-40fa-b9e9-20ce7708c643","notebooklm-mcp-cli-35-tools-for-agents","NotebookLM MCP — CLI + 35 Tools for Agents","NotebookLM MCP (notebooklm-mcp-cli) gives you a CLI (`nlm`) and an MCP server (`notebooklm-mcp`) so assistants can operate Google NotebookLM notebooks.","tokrepo install pack\u002Fgemini-cli-extensions-starter",{"pageType":97,"pageKey":8,"locale":25,"title":98,"metaDescription":99,"h1":100,"tldr":101,"bodyMarkdown":102,"faq":103,"schema":119,"internalLinks":125,"citations":138,"wordCount":151,"generatedAt":152},"pack","Gemini CLI Extensions Starter Pack — 10 Picks for a Multimodal Google-Native Setup","Just installed Gemini CLI? Ten picks that play to Gemini's strengths — BigQuery, Genkit, Firebase, Flutter, gcloud official extensions plus Stitch \u002F Workspace \u002F NotebookLM \u002F Cloud Assist MCPs. Multimodal-first, Google-native, install in order.","Gemini CLI Extensions Starter Pack — Multimodal & Google-Native, In Install Order","Ten picks for the developer who installed Gemini CLI and wants the Google-native angle that Claude Code and Cursor can't touch: the CLI itself, five official extensions that don't usually make the highlight reel (BigQuery, gcloud, Genkit, Firebase, Flutter), and four MCPs that turn Gemini into a Stitch designer, Workspace operator, NotebookLM analyst, and Cloud Assist co-pilot. Skip the polished but redundant ones; install these.","## What's in this pack\n\nGemini CLI hit GA, the official extension list grew to ~10 entries, and most tutorials walk you through the same four (Stitch, Workspace, Code Review, Postgres). Fine for a demo. Useless if you actually work in the Google stack day to day.\n\nThis pack is for the developer who chose Gemini CLI deliberately — because of the **1M-token context window**, the **free 60 requests\u002Fmin** tier for Gemini users, the **native multimodal input** (screenshots, PDFs, video frames feed straight in), and the **deep Google ecosystem hooks** (BigQuery, Firebase, GCP) that Claude Code and Cursor have to bolt on as third-party MCPs. You want the picks that lean *into* those strengths instead of treating Gemini CLI as a Claude Code clone.\n\nTen entries: the **CLI itself**, the **five official extensions that get under-discussed** (the BigQuery \u002F gcloud \u002F Genkit \u002F Firebase \u002F Flutter quartet plus Cloud Assist), and **four high-leverage MCPs** that extend Gemini's native vision and Google-app reach. By install #10 you have a coding agent that drafts SQL against your real warehouse, deploys Firebase functions, designs Flutter screens via Stitch, reads Gmail + Drive, and queries NotebookLM corpora — none of which is bolt-on theater. All Google-native.\n\n## Install in this order\n\n1. **Gemini CLI** — install the base agent first. `npm i -g @google\u002Fgemini-cli`, sign in with a Google account, you get 60 req\u002Fmin free (Gemini API user) + 1M-token context. Don't skip the tier check: the free quota is the reason this stack is even viable for solo devs.\n2. **Gemini CLI Extension: gcloud** — the foundation. Once gcloud is bound to natural-language commands, every later GCP-touching extension (BigQuery, Firebase, Cloud Assist) inherits sane authentication and project scoping. Install gcloud second; everything else depends on `gcloud auth login` being healthy.\n3. **Gemini CLI Extension: BigQuery** — the data-analytics killer feature. Gemini's 1M context means you can paste a 500-table schema, ask \"why did Q4 revenue dip,\" and get a real SQL draft. This is the use case Claude Code can't match without a third-party MCP and 4 hours of setup.\n4. **Gemini CLI Extension: Firebase** — deploy functions, manage Firestore rules, configure auth — all from chat. If you build mobile \u002F web apps and your backend is Firebase, this collapses a `firebase deploy` workflow into one prompt.\n5. **Gemini CLI Extension: Flutter** — pair with Firebase (#4) for the canonical Google mobile stack. Widget generation, state management scaffolding, platform-specific code. Multimodal angle: paste a screenshot of the UI you want, get the widget tree.\n6. **Gemini CLI Extension: Genkit** — the AI-app framework. When you stop *using* Gemini and start *embedding* it (RAG flows, structured outputs, retrievers), Genkit is the SDK. Extension makes flow scaffolding a 30-second job.\n7. **Gemini Cloud Assist MCP** — Private Preview MCP server that surfaces Google Cloud Ops APIs (logs, traces, IAM diagnostics) to any MCP client. Pairs with gcloud (#2): one talks *to* GCP, this one talks *about* GCP — debugging a 502 in production means asking Gemini to read the actual Cloud Logging stream.\n8. **Google Stitch MCP** — the multimodal showcase. Paste a Figma URL, an old screenshot, or a hand-drawn wireframe — Stitch generates a real UI. Wired through MCP, Gemini can iterate (\"make the CTA blue, add a search bar\") and the design system stays consistent. This is where Gemini's vision tokens earn their keep.\n9. **Google Workspace MCP** — official Google CLI with a built-in MCP server for Gmail, Drive, Calendar, Docs, Sheets and 10+ services. Once installed, Gemini reads your inbox, drafts replies, creates calendar holds, and edits Docs in place. The mundane productivity layer that turns CLI from \"coder\" into \"assistant.\"\n10. **NotebookLM MCP** — the `nlm` CLI plus MCP server lets Gemini operate NotebookLM notebooks: upload sources, generate audio overviews, query against a private RAG corpus. Pair with Workspace MCP and you have a complete \"read everything I work with, then reason\" loop — the long-context use case Gemini was literally built for.\n\n## How they fit together\n\n```\nGemini CLI (#1)\n   │\n   └─ 1M context · multimodal · free 60 rpm\n         │\ngcloud extension (#2)  ←─ foundation: auth + project scope\n   │\n   ├─ BigQuery (#3) ────────── data + SQL\n   ├─ Firebase (#4)  ─┐\n   │                  ├─ mobile \u002F web app stack\n   ├─ Flutter (#5)  ──┘       (screenshot → widget tree)\n   │\n   └─ Genkit (#6) ─────────── build AI features yourself\n\nGoogle ecosystem MCPs (drop-in, not extensions):\n   ├─ Cloud Assist MCP (#7) ── debug GCP prod (logs \u002F traces)\n   ├─ Stitch MCP (#8)  ─────── multimodal design (image → UI)\n   ├─ Workspace MCP (#9) ───── Gmail \u002F Drive \u002F Calendar \u002F Docs\n   └─ NotebookLM MCP (#10) ── long-context RAG over your sources\n```\n\nThe load-bearing trio is **CLI (#1) + gcloud (#2) + one MCP that fits your workflow**. If you're a data person, that MCP is Cloud Assist (#7). If you're a designer\u002FPM, it's Stitch (#8). If you're an ops generalist, it's Workspace (#9). Don't install all four MCPs day one — pick the one matching what you do, add others as you hit the gap.\n\n## Tradeoffs you'll hit\n\n- **Gemini CLI vs Claude Code vs Cursor** — Different bets. Claude Code is the strongest *agent* (best at multi-step reasoning, sub-agents, hooks). Cursor is the strongest *editor* (in-IDE diff UI, tab-complete). Gemini CLI is the strongest *Google-native multimodal* tool (1M context, free tier, BigQuery \u002F Firebase \u002F Stitch first-class). Most pros run two: Claude Code or Cursor for daily code, Gemini CLI when they need to dump a PDF or screenshot in.\n- **Official extensions vs MCPs** — Extensions (#2-#6) are first-party, ship signed, no setup. MCPs (#7-#10) are richer but require a JSON config and sometimes a separate auth flow. Lean on extensions where they exist; reach for MCP when no extension covers the target.\n- **Stitch MCP vs Stitch extension** — The existing official Stitch *extension* is fine for inside-CLI use. The MCP version is the same capability exposed over MCP so Cursor and Claude Code can call it too. Install whichever your daily editor speaks; install both if you switch.\n- **Workspace MCP vs Gmail API directly** — Workspace MCP is one config away from \"AI reads my inbox.\" Raw Gmail API is two hours of OAuth scaffolding for the same thing. If you ever found yourself writing a Google Apps Script to forward emails, the MCP route is strictly better.\n- **Free tier reality check** — 60 rpm sounds generous but multimodal calls (image \u002F video frames) burn it faster. If you'll be pasting screenshots all day, budget for a paid Gemini API key before week 2.\n\n## Common pitfalls\n\n- **Skipping gcloud (#2) because \"I don't use GCP\"** — Even if your prod is on AWS, the gcloud extension is what wires `gcloud auth` to the BigQuery \u002F Firebase \u002F Cloud Assist trio. Install it; ignore the GCP-only commands.\n- **Installing every extension** — There are ~10 official extensions. You don't need all of them. Pick the ones touching your stack. Extra extensions inflate the prompt context Gemini has to scan to route a request, which makes everything slightly slower.\n- **Pasting a 500-page PDF on a free tier** — Gemini will accept it, parse it, and you'll watch your daily quota evaporate in one call. Chunk first, or upgrade to paid.\n- **Wiring Workspace MCP into the wrong Google account** — Easy to OAuth into your personal account when your work data is in `@company.com`. Double-check the consent screen.\n- **Treating Stitch MCP output as ready-to-ship** — It's a great first draft. Hand it to a designer before pushing to prod. The aesthetic is competent-default, not on-brand.\n\n## Why this complements the other Gemini pack\n\nTokRepo already has a [Gemini CLI Extensions](\u002Fen\u002Ftopics\u002Fgemini-cli-extensions) pack covering the **10 official extensions Google ships** (Stitch, Workspace, Code Review, Postgres, Vertex AI, and others). That one is a *completionist* index — install everything, see what sticks.\n\nThis pack is the **opposite curation**: a small, opinionated, multimodal-first short list mixing the CLI itself, the five less-hyped official extensions, and four MCPs that extend Gemini into Google Workspace, NotebookLM, Stitch, and Cloud Ops. If the official pack is the spec sheet, this is the playbook.",[104,107,110,113,116],{"q":105,"a":106},"How is this different from the existing Gemini CLI Extensions pack?","The existing pack is a completionist index of the 10 official extensions Google ships with Gemini CLI — Stitch, Workspace, Code Review, Postgres, Vertex AI, etc. This pack is curated differently: it starts with the CLI binary itself, picks five official extensions that don't usually make highlight reels (BigQuery \u002F gcloud \u002F Genkit \u002F Firebase \u002F Flutter), then adds four MCPs (Cloud Assist, Stitch MCP, Workspace MCP, NotebookLM MCP) that lean into Gemini's multimodal vision tokens and Google-app integrations. Different angle, mostly different workflow_ids, intentionally complementary.",{"q":108,"a":109},"Is Gemini CLI actually worth installing alongside Claude Code or Cursor?","Yes, if you have multimodal inputs in your workflow. Gemini's 1M-token context plus native image \u002F PDF \u002F video-frame ingestion handle things Claude Code and Cursor can only fake. Concrete examples: pasting a 200-page contract and asking for clause diffs, dropping a Figma screenshot into chat and getting Flutter widget code, dumping a folder of competitor screenshots and getting a comparison table. The free 60 rpm tier makes it cheap to keep around as a second tool. Most engineers don't replace their daily driver — they add Gemini CLI as the multimodal back-pocket option.",{"q":111,"a":112},"Do I need a paid Google Cloud account to use any of these?","For the CLI plus most extensions, no — a free Google account works and you get 60 requests\u002Fminute on the Gemini API free tier. The BigQuery \u002F Firebase \u002F Cloud Assist extensions touch your real GCP resources, so they do need a Google Cloud project. There's a perpetual free tier for both (BigQuery: 10 GB storage + 1 TB queries \u002F month; Firebase: Spark plan), so you can play without a credit card. Workspace MCP works with any Google account, personal or paid. NotebookLM is free.",{"q":114,"a":115},"Why install Cloud Assist MCP instead of just using gcloud directly?","Different surface area. The gcloud extension (#2) is for issuing commands ('deploy this,' 'create that bucket'). Cloud Assist MCP is for reasoning over Cloud's *operational* APIs — Cloud Logging streams, traces, IAM diagnostics, recommended actions. When a Cloud Run service throws 502s in production, gcloud helps you redeploy; Cloud Assist helps you find out why. Install both; they're complementary.",{"q":117,"a":118},"Does this work on Windows?","Yes, with caveats. Gemini CLI itself is npm-distributed and runs cross-platform fine. The Google Workspace MCP and NotebookLM MCP are Node-based and work under Windows or WSL2. The Firebase and Flutter extensions need their respective SDKs installed locally (firebase-tools and flutter SDK) — both have Windows installers but WSL2 is friendlier. gcloud has a native Windows installer. The only friction point is shell-quoting in PowerShell vs bash for long prompts; most users default to WSL2 for that reason alone.",{"@context":120,"@type":121,"name":122,"description":123,"numberOfItems":124,"inLanguage":25},"https:\u002F\u002Fschema.org","ItemList","Gemini CLI Extensions Starter Pack","Ten picks for a developer setting up Gemini CLI with a multimodal, Google-native focus — CLI base plus under-discussed official extensions plus high-leverage MCPs, in install order.",10,[126,130,134],{"url":127,"anchor":128,"reason":129},"\u002Fen\u002Ftopics\u002Fgemini-cli-extensions","Gemini CLI Extensions — the official complete index","This pack is the curated counterpart to that completionist list",{"url":131,"anchor":132,"reason":133},"\u002Fen\u002Fai-tools-for\u002Fcoding","AI tools for coding","Compare Gemini CLI with Claude Code, Cursor, Codex CLI",{"url":135,"anchor":136,"reason":137},"\u002Fen\u002Ftopics","Browse other topic packs","Adjacent packs include MCP Server Stack, Claude Code 30-Minute Onboarding, Workflow Orchestration",[139,143,147],{"claim":140,"source_name":141,"source_url":142},"Gemini CLI is Google's official open-source CLI coding agent with 1M-token context","Google AI Developer docs — Gemini CLI","https:\u002F\u002Fai.google.dev\u002Fgemini-api\u002Fdocs\u002Fgemini-cli",{"claim":144,"source_name":145,"source_url":146},"Gemini CLI supports MCP servers as a native extension mechanism","google-gemini\u002Fgemini-cli on GitHub","https:\u002F\u002Fgithub.com\u002Fgoogle-gemini\u002Fgemini-cli",{"claim":148,"source_name":149,"source_url":150},"Google Stitch generates UI designs from text and images","Google Stitch product page","https:\u002F\u002Fstitch.withgoogle.com\u002F",1360,"2026-05-22T00:00:00Z"]