Image prompting for Nano Banana and GPT Image 2.5
Write model-specific image prompts — Nano Banana grounding and aspect tricks, GPT Image 2.5's 5-slot template — via a mandatory reading order, not vibes
- What
- Write model-specific image prompts — Nano Banana grounding and aspect tricks, GPT Image 2.5's 5-slot template — via a mandatory reading order, not vibes
- Cost
- Free
- Needs
- access to an image model API (Nano Banana or GPT Image 2.5, paid usage) — the skill writes prompts, it does not generate images
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @smixs's image-prompting skill for Nano Banana (NB2/NBP) and GPT Image 2.5 (Flare/Sunburst): it refuses to write prompts from the thin skill body alone and enforces a mandatory reading order — a model chooser, one model-specific reference (image grounding and extreme aspect ratios for Nano Banana; the 5-slot template and anti-slop banned words for GPT Image 2.5), universal golden rules, then task-shaped references (text rendering, editing, character continuity, de-slop photorealism, slides). A sibling `video` skill handles motion. Honest caveats: it writes prompts, it does not generate images — you still need API access to an image model, which is paid usage; CC-BY-4.0 requires attribution — credit Serge Shima when reusing it. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: access to an image model API (Nano Banana or GPT Image 2.5, paid usage) — the skill writes prompts, it does not generate images Install "Image prompting for Nano Banana and GPT Image 2.5" for me. It gives my agent @smixs's model-specific image prompting: a mandatory reading order — model chooser, one model-specific reference (image grounding and extreme aspect ratios for Nano Banana; the 5-slot template and anti-slop banned words for GPT Image 2.5), universal golden rules, then task-shaped references (text rendering, editing, character continuity, de-slop photorealism, slides). CC-BY-4.0 licensed — attribute Serge Shima when reusing it. Repository: https://github.com/smixs/visual-skills/blob/main/image/SKILL.md 1. Fetch the SKILL.md file (and any helper files, including the references/ folder) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "image". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. describe the image I want and confirm the model choice; nothing else — the skill writes prompts, generation happens through my own image-model API access). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.