By jawhnycooke
Convert natural language image descriptions into structured JSON schemas for Nano Banana Pro (Gemini 3 Pro Image), enabling generation of marketing images, UI mockups, diagrams, data visualizations, and social graphics.
Stop rolling dice. Start turning dials.
This repository contains a Claude Code slash command that translates natural language descriptions into structured JSON schemas for Nano Banana Pro (Gemini 3 Pro Image).
Instead of writing vague prompts and hoping for the best, the translator helps you build precise specifications where every element - lighting, camera angle, composition, props - lives on its own "fader." Change one thing without affecting everything else.
Supported schema types:
First, add the marketplace to Claude Code:
/plugin marketplace add https://github.com/jawhnycooke/claude-code-nano-banana
Then install the plugin:
/plugin
Follow these steps:
1. Browse and install pluginsclaude-code-nano-bananaSpace bar to select nano-bananai to install/exit Claude code and restartThis installs the plugin directly from this repository.
Invoke the command with a rough description:
/nano-banana vinyl record product shot, moody lighting, vintage feel
The translator will ask clarifying questions, then output a complete JSON specification ready to paste into Nano Banana Pro.
See the full tutorial: Dials, Not Dice: A Precision Prompting Guide for Nano Banana Pro and Claude Code
The examples/vinyl-record-tutorial/ folder contains the JSON files from the tutorial so you can follow along.
For questions, issues, or contributions, contact: [email protected]
MIT
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.
npx claudepluginhub joshuarweaver/cascade-code-general-misc-4 --plugin jawhnycooke-claude-code-nano-bananaStructured collaborative document creation workflow with three stages: context gathering, refinement & structure, and reader testing. Creates professional documentation, proposals, and technical specs.
A comprehensive example plugin demonstrating all Claude Code extension options including commands, agents, skills, hooks, and MCP servers
Notion workspace integration. Search pages, create and update documents, manage databases, and access your team's knowledge base directly from Claude Code for seamless documentation workflows.
Interactive learning mode that requests meaningful code contributions at decision points (mimics the unshipped Learning output style)
Apply Anthropic's official brand colors and typography to visual artifacts. Includes brand color palette, typography standards, and automatic styling.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.