By fakoli
Generate, edit, remix, and optimize images using Google's Gemini 3 Pro Image Preview model
Set up or update Nano Banana Pro configuration (API key, defaults, agents)
Edit an existing image with natural language instructions
Generate an image from a text prompt using Gemini 3 Pro
Optimize image size for GitHub, Slack, web, or custom constraints
Generate an image styled from a webpage's design (colors, fonts, imagery)
Evaluates generated images against requirements, scoring faithfulness, readability, aesthetics, and conciseness, then recommends approval or revision
Transforms user requests and context into detailed visual specifications with layout, composition, and spatial relationships
Analyzes the user's project to find brand assets, color palettes, typography, and reference images for guiding image creation
Applies aesthetic guidelines, color palettes, typography, and design principles to create a style-enhanced image generation prompt
Executes image generation using nanobanana.py scripts — the only agent that creates images
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Extend Claude Code with production-grade plugins.
A curated collection of battle-tested Claude Code plugins — covering Google Workspace automation, AI image generation, text-to-speech, diagram authoring, secure web fetching, and marketplace self-management. Every plugin ships with skills, commands, agents, and CI validation.
Add this marketplace to Claude Code with one command:
/plugin marketplace add fakoli/fakoli-plugins
Then install any plugin:
/plugin install gws
/plugin install safe-fetch
/plugin install nano-banana-pro
Claude Code plugins extend the assistant with domain-specific capabilities. A plugin can bundle:
/send-email, /speak, /fetch) that invoke specific behaviorsPlugins live in directories with a .claude-plugin/plugin.json manifest. The marketplace validates every plugin against a JSON Schema on every push and pull request.
Three plugins designed to work together — each useful standalone, all three together the full stack:
| Plugin | Role | What It Does |
|---|---|---|
| fakoli-crew | Specialist agents | 8 polyglot agents (TypeScript / Python / Rust) — architect, reviewer, researcher, plugin engineer, integration specialist, documenter, infrastructure engineer, QA |
| fakoli-flow | Workflow orchestration | Intent-driven pipeline: brainstorm → plan → execute → verify → finish. Wave-based dispatch with mandatory critic gates between every code-writing phase |
| systems-thinking | Architecture analysis | Multi-agent infrastructure analysis: discovery → extraction → synthesis. Built for decisions that affect the whole system |
fakoli-crew provides the workers. fakoli-flow orchestrates them. systems-thinking analyzes architecture before the workers start.
Install any combination — each works standalone. All three together give you a complete multi-agent development pipeline: architecture analysis, intent-driven planning, parallel agent execution, and evidence-based verification.
| Plugin | Description |
|---|---|
| gws | Full Google Workspace via the gws CLI — 100 skills, 15 commands, 11 role-based agents, and 44 recipes spanning Gmail, Calendar, Drive, Docs, Sheets, Slides, Chat, and more. The most comprehensive Workspace plugin available for any AI assistant. |
| notebooklm-enhanced | Programmatic control of Google NotebookLM — create notebooks, ingest PDFs and YouTube videos, generate podcasts and slide decks, and run end-to-end research workflows with a single command. |
| Plugin | Description |
|---|---|
| nano-banana-pro | Generate, edit, and remix production-ready images with Google Gemini 3 Pro. Includes a 5-agent PaperBanana pipeline (Retriever → Planner → Stylist → Visualizer → Critic) that iteratively refines images until they pass a quality threshold. |
| fakoli-speak | Multi-provider TTS for Claude Code — stream any response as speech via /speak using OpenAI ($0.015/1K), Deepgram, ElevenLabs, Google Gemini (free), or macOS Say (free). Switch with /provider, track spending with /cost, toggle auto-narration with /autospeak. |
| excalidraw-diagram | Generate .excalidraw files from natural language or by analyzing your codebase. Supports flowcharts, architecture diagrams, ER diagrams, and dependency graphs across four color themes — zero dependencies beyond Node.js 18. |
Apply systems thinking to infrastructure decisions so you stop discovering hidden costs, vendor assumptions, and scaling traps after you've committed. Extract what vendors bury in their docs, map dependencies the design review missed, reuse what worked before instead of forgetting lessons, and produce structured artifacts grounded in source evidence — not confident guesses.
Bloomberg-style financial terminal — 32 MCP tools, 6 workflow skills, audit trails, Polygon.io fallback, usage tracking
Intent-driven workflow orchestration — brainstorm, plan, and execute complex projects through coordinated specialist agents with critic gates and evidence-based verification.
Comprehensive Google NotebookLM automation — create notebooks, add sources, generate podcasts/videos/quizzes/slides, and run multi-notebook research workflows via RPC API
Operate across all Google Workspace services using the gws CLI — 100 skills, 15 slash commands, 11 role-based agents, and 44 automation recipes covering email, calendar, drive, docs, sheets, slides, tasks, chat, meet, forms, classroom, keep, people, events, admin reports, model armor, and apps script.
npx claudepluginhub fakoli/fakoli-plugins --plugin nano-banana-proAI image generation Creative Director powered by Google Gemini Nano Banana models. Claude interprets intent, selects domain expertise, constructs optimized prompts, and orchestrates Gemini for best results.
Generate optimized prompts for Gemini 2.5 Flash Image (Nano Banana). Use for image generation, crafting photo prompts, art styles, or multi-turn editing workflows with best practices.
Generate or edit images using Google Gemini API via nanobanana
Generate images and videos using Google Gemini and Veo models. Provides skills for AI image generation, image editing, text-to-video, and image-to-video workflows.
OpenAI GPT Image 2 prompt gallery, image prompt library, agentic skill + CLI. Gallery-first prompt patterns, reference-image editing workflows, and a packaged CLI for skill-capable agent runtimes.
Generate and edit images using Gemini's Nano Banana Pro (gemini-3-pro-image-preview) model