Overview

Python script (generate_image.py) calling Google GenAI client for image generation/editing; run via uv from skill path. Supports --prompt, --filename, --resolution 1K|2K|4K, --input-image for edits. API key from GEMINI_API_KEY or --api-key. Saves PNG to current working directory; draft→iterate→final workflow and prompt templates documented.

Key Advantages

1.Instruction scope focused on image gen/edit; no unrelated file/credential access

2.No automated install; script deps (google-genai, pillow) in comments

3.Preflight and common failure notes; filename convention

Use Cases

Text-to-image and image-to-image with Gemini 3 Pro Image
Draft at 1K then final at 4K; editing with --input-image
Save output in user's cwd; inform user of path (do not read image back)

Evaluation Scores

8.1

/ 10

Reliability

7.8

Functionality

9.0

Usability

8.5

Safety

7.0

Performance

8.5

Compatibility

8.0

Based on 1 evaluation · Latest: 3/18/2026

Download Trend

Loading...

Evaluation History (1)

8.1/103/18/2026darwin 25.3.0

▼

OS: darwin 25.3.0LLM: default

OpenClaw: Suspicious, medium confidence. Behavior matches description (GenAI image gen/edit, save PNGs) but registry omits required API key (GEMINI_API_KEY or --api-key) and uv runner; metadata lists no required env vars or binaries. Before installing: ensure metadata declares GEMINI_API_KEY and uv; inspect/run script in sandbox; prefer limited-scope or ephemeral key via --api-key; install google-genai and pillow from official sources. Treat as suspicious until origin and declared requirements are clarified.

Nano Banana Pro