google-gemini-image
Plan, generate, edit, and quality-check still images with Google's Gemini native image models (Nano Banana), including Gemini 3.1 Flash Image, Gemini 3.1 Flash-Lite Image, Gemini 3 Pro Image, and legacy Gemini 2.5 Flash Image. Use for model and API-route selection, conversational editing, multi-reference composition, thinking and Google Search grounding, resolution/aspect-ratio control, exact-text and brand workflows, SynthID/provenance, safety, privacy, rights, and migration from legacy Gemini or Imagen image endpoints. Do not use for Veo/video generation or Gemini Live/audio work.
Profile →npx skills add calesthio/generative-media-skills --skill google-gemini-image --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Plan, generate, edit, and quality-check still images with Google's Gemini native image models (Nano Banana), including Gemini 3.1 Flash Image, Gemini 3.1 Flash-Lite Image, Gemini 3 Pro Image, and legacy Gemini 2.5 Flash Image. It guides model selection, conversational editing, multi-reference composition, grounding, resolution/aspect-ratio control, exact-text and brand workflows, SynthID/provenance, safety, privacy, rights, and migration from legacy endpoints. Do not use for Veo/video generation or Gemini Live/audio work.
How it works
- Establish rights and delivery constraints; choose route and model; assign explicit roles to references; generate a reviewable draft; repair one defect class at a time.
- Bound the job before calling a model by collecting fields such as deliverable, intent, must_preserve, may_change, references, factuality, privacy, acceptance_tests, route_constraints.
- Record route and interface details (Gemini Developer API: Interactions API or generateContent) and select the appropriate API based on needs. Use Interactions for server-side continuation and multi-turn editing; use generateContent for legacy or feature gaps.
- For model routing, specify model IDs, response schemas, and asset configurations; ensure not to mix payload dialects.
- Maintain a reference ledger for each input (R1, R2, R3, R4, R5) and name roles in the prompt with a defined priority.
- Build prompts as an acceptance contract covering deliverable, subject, references, composition, materials, exact copy, invariants, grounding source, and output format.
- Apply an edit loop: save accepted images, diagnose a defect class, request a bounded delta, reapply configuration, compare against references, and restart if drift widens.
When to use it
Use the Interactions API for server-side continuation and multi-turn editing; use generateContent for legacy or features not yet exposed by Interactions. Verify API version, model enablement, and whether the cloud route with project credentials is required. Do not switch endpoints silently; check auth, retention, controls, quotas, and agreements.
What it can touch
Gemini 3 image models; Interactions API; generateContent API; possible Cloud routing via Vertex AI. The skill emphasizes recording route, model IDs, aspect ratios, image sizes, and output modalities in a run manifest.
Caveats
Do not cover Veo, motion generation, or Gemini Live/audio. The guidance notes that certain capabilities (e.g., safety settings, batch API) may be limited to specific interfaces; use the appropriate API and model according to the current guide. અભિને
# Produce still images with Gemini Treat this as a production discipline, not a bag of adjectives. Establish rights and delivery constraints, choose a route and model, assign references explicit roles, generate a reviewable draft, and repair one defect class at a time. ## Evidence labels and freshness Interpret labels consistently: - **Documented fact**: stated in a cited Google first-party source
What does the google-gemini-image skill do?
Plan, generate, edit, and quality-check still images with Google's Gemini native image models (Nano Banana), including Gemini 3.1 Flash Image, Gemini 3.1 Flash-Lite Image, Gemini 3 Pro Image, and legacy Gemini 2.5 Flash Image. Use for model and API-route selection, conversational editing, multi-reference composition, thinking and Google Search grounding, resolution/aspect-ratio control, exact-text and brand workflows, SynthID/provenance, safety, privacy, rights, and migration from legacy Gemini or Imagen image endpoints. Do not use for Veo/video generation or Gemini Live/audio work.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill google-gemini-image --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.