Generate
Generate images and videos using Google's Gemini media models (Nano Banana 2 Lite, Nano Banana 2, Nano Banana Pro, Gemini Omni Flash) via the Gemini API. Use this whenever the user asks to generate, create, or make an image or video, wants a thumbnail, wants to animate a still image, says "generate on brand" or "generate from reference", wants to link or import a folder of reference images, invokes /generate or /generate frf, or asks to update this skill ("/generate update") — even if they don't name a specific model, and even if they just describe a visual they want without saying "generate.
Install
npx skills add AntonioCardenas/generate-nanobanana --skill generategit clone --depth 1 https://github.com/AntonioCardenas/generate-nanobanana.git /tmp/generate-nanobanana
mkdir -p ~/.claude/skills
cp -r /tmp/generate-nanobanana/. ~/.claude/skills/generatePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# /generate Calls Google's Gemini media models directly through the Gemini API — no third-party routing layer. One key, one bill, and access to the newest Google-specific features (Nano Banana Pro's multi-image fusion, Omni Flash's synced audio) as soon as they ship. ## How a generation flows 1. **Route** — pick the model for the job (draft image, standard image, quality image, or video) and read its recipe file before calling anything. Recipes hold the exact request shape and any quirks that have shown up since the model shipped. 2. **Load references** — pull any real reference images (logos, faces, style shots) from `generations/refs/`, or from a named reference set if the request invokes `/generate frf` or says "from reference" or "on brand" (see Reference library). Never substitute a text description for a reference image that exists. 3. **Generate** — call the API per the recipe, through the **Interactions API** (`client.interactions.create`) — the current, documented entry point for every model below. Images reply synchronously; video is a submit-then-poll operation for large outputs. Save the result flat into the generations folder. 4. **Log** — verify the generated file is actually on disk and non-empty, then write the sidecar JSON next to it (see Logging). Never log a generation whose file isn't there. ## Models | Task | Model | Model ID | Recipe | |---|---|---|---|
Details
- Skill name
generate- Repository
- AntonioCardenas/generate-nanobanana
- Repo updated
- 4 August 2026
FAQ
What does the Generate skill do?
Generate images and videos using Google's Gemini media models (Nano Banana 2 Lite, Nano Banana 2, Nano Banana Pro, Gemini Omni Flash) via the Gemini API. Use this whenever the user asks to generate, create, or make an image or video, wants a thumbnail, wants to animate a still image, says "generate on brand" or "generate from reference", wants to link or import a folder of reference images, invokes /generate or /generate frf, or asks to update this skill ("/generate update") — even if they don't name a specific model, and even if they just describe a visual they want without saying "generate.
How do I install the Generate skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add AntonioCardenas/generate-nanobanana --skill generate. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Generate popular?
It lives in AntonioCardenas/generate-nanobanana, which has 6 GitHub stars and 2 forks.
Related skills
Muse Gadget Forge
6Toddoward/muse-gadget-forge
Build your own Muse gadget — your ears and voice in the user's room — on the user's own computer: set up ESP-IDF on the muse-local-gateway workbench, build the Muse Gadget SDK firmware, flash the ESP32 board on their USB port, read its log, and walk the user through pairing. Use when the user wants a new or updated Muse gadget, or one that misbehaves.
Diy Audiobook
6mickyyang-1407/diy-audiobook
Make a finished multi-voice audiobook, children's story or bedtime radio drama from a public-domain book or the user's own story (Sherlock Holmes, fairy tales, Aesop, classics — any language) — translated or adapted, every character with their own voice, optional music (Suno, own files or a free generated lullaby), optional illustrations (local ComfyUI, OpenAI, MiniMax or the user's own), video, cover, subtitles, chapters and upload text. Free voices by default. Use when the user asks for an audiobook, kids' story, bedtime story, sleep story, audio drama, radio play, 有聲書, 兒童故事, 睡前故事, 廣播劇, or "
Script to Guide
6SilverNine/script-to-guide
Turn a written script and real app screenshots into a narrated product walkthrough. Output is a small static web page (searchable transcript, follow-along mode, embeds with an iframe) or an MP4. Every highlight, zoom and cursor move is cued to a word of the synthesized narration, so editing the script re-times the screen. Use when the user wants a product guide, onboarding walkthrough, feature tutorial or help-center video for a web app, or for any app from screenshots.
Voice Skill Builder
7realbrianhanson/voice-skill-builder
Build a person's own personal voice skill from their real writing. Use whenever someone wants Claude to write like them, sound like them, or capture their writing style. Trigger on "build my voice skill," "create my voice," "clone my voice," "make Claude write like me," "capture my writing style," "set up my writing voice," or any request to create a personal writing-style system, even if they never say the word skill. Also use when someone wants to update, re-tune, or add samples to a voice skill that was built with this tool. Runs a plain-English interview, collects writing samples, extracts
Subtitle Optimizer
6Rancho-7/subtitle-optimizer
Use when reviewing or correcting SRT subtitle text while preserving timestamps, especially ASR transcript errors, product-name terminology, homophone mistakes, and visual review workflows.
Video Skill
7michaelgold/videoskill
Run the video-skill pipeline to convert narrated videos into structured step data and enriched timeline-ready outputs. Use when a user asks to process a video into steps, run transcription/chunking/extraction/enrichment, debug provider connectivity, or generate markdown from extracted skills.
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.