← All skills

nano-banana

CommunityMIT

Generate and edit high-quality AI images using Google's Gemini image models (Nano Banana series) via MCP. Use when user wants to create images, edit photos, generate graphics, or needs visual content with text rendering. Supports gemini-3.1-flash-image-preview (Nano Banana 2) and gemini-2.5-flash-image-preview (Nano Banana).

The ZIP contains only this skill. It lives on GitHub Releases of the public orlandoneto/agent-skills repo — Ontoom is the showcase. A daily crawler refreshes the catalog.

How to install

  1. Download the ZIP and extract the skill folder.
  2. Cursor: .agents/skills/ck-nano-banana/ or .cursor/skills/ck-nano-banana/
  3. Claude Code: .claude/skills/ck-nano-banana/
  4. Other AIs: .agents/skills/ck-nano-banana/
cursorclaude-codecodexgeminiany

Source / credits: ckorhonen/claude-skills

Other skills in this collection

Skills (ckorhonen)

  • playdate-dev

    Playdate game development in Lua with the Playdate SDK. Covers game loop, sprites, graphics, input (crank, buttons, accelerometer), audio, UI, performance, metadata (pdxinfo), and simulator/device workflow. Use when asked to make a Playdate game, implement Playdate-specific mechanics, or apply Playdate design and accessibility guidelines.

  • practical-typography

    Professional typography guidance based on Matthew Butterick's Practical Typography. Use when evaluating, critiquing, or improving document formatting, text layout, font choices, punctuation, spacing, or any typography-related decisions for print or web content.

  • qmd

    Local hybrid search for markdown notes and docs. Use when searching notes, finding related content, or retrieving documents from indexed collections.

  • scientific-critical-thinking

    Evaluate research rigor and scientific claims. Assess methodology, experimental design, statistical validity, biases, confounding, and evidence quality using GRADE, Cochrane ROB, and preregistration standards. Use for critical analysis of research papers, evaluating AI/ML study claims, reviewing preprints, or fact-checking scientific assertions in any domain.

  • security-best-practices

    Perform language and framework specific security best-practice reviews and suggest improvements. Trigger when the user requests: security review, security report, threat assessment, vulnerability scan, security audit, secure-by-default coding, hardening guidance, or security best practices guidance. Supported languages: Python, JavaScript/TypeScript, Go. Covers OWASP Top 10, supply chain security, secrets management, dependency auditing, and modern cloud deployment hardening.

  • security-threat-model

    Repository-grounded threat modeling that enumerates trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, then writes a concise actionable Markdown threat model. Trigger only when the user explicitly asks to threat model a codebase or path, enumerate threats/abuse paths, or perform AppSec threat modeling. Covers STRIDE, PASTA, and attacker-goal-based methodologies, with modern considerations for AI/ML systems, cloud-native deployments, and supply chain threats.