AC nano-banana-pro
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image / Imagen Pro) — the premium AI image generation model optimized for professional asset production with advanced reasoning ('Thinking'), high-fidelity text rendering, and complex multi-turn creation. Supports text-to-image and image editing with up to 6 reference images, resolutions up to 4K, and 14+ aspect ratios. Available via Atlas Cloud API. Use this skill whenever the user wants to generate high-quality professional images, create AI art with precise text, edit photos with AI, produce marketing assets, infographics, menus, diagrams, or any visual content requiring detailed text rendering. Also trigger when users mention Nano Banana Pro, Gemini 3 Pro Image, Imagen Pro, or ask for premium/professional-grade AI image generation, concept art, product photography, or visual assets with complex compositions.
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (nano-banana-pro) differs from the folder (nano-banana-pro-image)
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 24 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Execution cost. Instruction body is 1850 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 893: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.