generate-image
Generate or edit images using AI models (FLUX, Nano Banana 2). Use for general-purpose image generation including photos, illustrations, artwork, visual assets, concept art, and any image that is not a technical diagram or schematic. For flowcharts, circuits, pathways, and technical diagrams, use the scientific-schematics skill instead.
84
82%
Does it follow best practices?
Impact
82%
1.78xAverage score across 3 eval scenarios
Passed
No known issues
Evaluation results
100%
25%Visual Assets for Immunotherapy Grant Proposal
Correct script usage and model selection
Correct script invoked
0%
100%
No flux.2-flex model
100%
100%
Quality model selected
0%
100%
Named output paths
100%
100%
Separate calls per image
100%
100%
PNG output format
100%
100%
API key via .env
100%
100%
Four images generated
100%
100%
Descriptive prompts
100%
100%
No scientific-schematics for illustrations
100%
100%
97%
52%Product Image Variants for E-commerce Listing
Image editing with correct model selection
Uses --input flag
0%
100%
No flux.2-flex for editing
100%
100%
Editing-capable model
0%
100%
Correct script used
0%
70%
Specific edit prompts
50%
100%
Output path specified
100%
100%
All three variants produced
100%
100%
Input format is supported
40%
100%
No regeneration from scratch
0%
100%
API key setup via .env
100%
100%
49%
29%Visual Content Package for AI Platform Launch
Correct skill routing for image types
Schematics for system diagram
0%
0%
Schematics for process flow
0%
0%
generate-image for concept photo
0%
100%
generate-image for illustration
0%
100%
No generate-image for diagrams
100%
0%
Correct model for photos
0%
50%
Script uses correct paths
0%
20%
All four assets covered
100%
100%
Named output files
0%
100%
Separate generate-image calls
0%
100%
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
b58ad7e
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.