Here are a few ways I found that make the best out of Nano bananas:
1. World knowledge
Because Gemini has world's knowledge, it goes beyond just image editing
You can prompt a point on map, and ask it to picture what the view will look like
"What will I see standing at this point on the map" from @tokumin
Similar to the world knowledge use case
You can also ask it to edit image with additional info
"You are a location-based AR experience generator. highlight [xxxxx] in this image and annotate relevant information about it."
from @bilawalsidhu
2. Extraordinary item consistency
Previous models almost never hit production bar, because it lose details of product items
But nano banana is really good at it
"Extract individual product shots from this image. Isolate each clothing item, accessory, and bag into clean, separate images with white backgrounds. Keep proportions accurate and remove the model and background (but each product should be separated from each other, and the product has to look 100% same with original pic in terms of details)"
With high consistency of item
Real life style product shot is so easy now
No reason why you can't generate 50 'user posts' every day
3. Image reference
A picture is worth a thousand words.
Nano banana follow styles incredibly well
4. Character consistency
Transform the same pic to different angles with really high fidelity from @levelsio
• • •
Missing some Tweet in this thread? You can try to
force a refresh
SKILL.md firstly contain a simple yaml contains metadata,
Provides just enough info about when to use this skill
+ Full markdown prompt explain detailed instructions, which will only be fed into context if agent decide to use this skill
-----
For complex skills, in the full markdown instruction,
You can refer to more md files for further instructions
+ Scripts/functions you predefined OR any other resources
So that it can call predefined functions on-demand
2/ Why Skill is more useful than MCP?
MCP was an attempt to extend agent capabilities by feeding it a bundle of tools
It was awesome and composable, however it consume loads of token and often don't work out of box (As often agent needs to use tools in certain order to make it work)
Skill is better because:
1/ Token efficiency
Many MCP contain loads of tools, and all those tools description will be fed into agent context regardless you need it or not
2/ Bundled workflow
Often you need to add additional instruction to CLAUDE.md to instruct when to use which tool
----
My gut feeling is that skill can replace MCP later:
- Skill should programmatically load MCP tools
- And MCP will be no longer needed