AC nano-banana
Use to write great prompts for Nano Banana (Google's Gemini image model: Nano Banana Pro = Gemini 3 Pro Image) to generate or edit images for social media — the image-prompt-craft mini-skill. Run when the user wants a nano-banana / Gemini image prompt, an AI image for a post (quote graphic, carousel slide, thumbnail, infographic, product shot, ad creative), or conversational image editing. Reads brand-profile for brand colours/style. Strengths: best-in-class legible in-image text (route typography/layout-led design to ideogram), multi-image consistency, conversational editing, and Google's photoreal lane (Imagen deprecated); surreal art stays Midjourney's. Teaches prompt anatomy, the text-first approach, reference-image consistency, and per-platform aspect ratios. Honest: SynthID watermark + AI disclosure; never real identifiable people or copyrighted characters/logos; verify spelling/data. The API/connection and WoopSocial upload flow live in tools/integrations/nano-banana.md.
Use to write great prompts for Nano Banana (Google's Gemini image model: Nano Banana Pro = Gemini 3 Pro Image) to generate or edit images for social media —…
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 62/100
- 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. 5 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 29 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1336 tokens
- low 10 top-level sections: this looks like several domains in one skill
- low No test case covers injection arriving through data
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 992: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 29 items
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.