Image

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 119c44cf54e6 · 20 Oct 2026Report an issue or request a re-scan

• Publishersmixs GitHub userOwner of the repository this skill is read from
• Source foldersmixs/visual-skills/imageThe exact folder we audited
• LicenceCC-BY-4.0As the repository states it
• Commit pinned for this verdict119c44cf54e6A new audit runs when the source changes
• Repository statusNot archivedLast push 33 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Image prompting skill for Nano Banana (NBP/NB2) and GPT Image 2.5 (Flare/Sunburst). Writes ready-to-use prompts with model/quality/size recommendations. Use when: "нарисуй", "сгенерируй картинку", "image prompt",…

---
name: image
license: CC-BY-4.0 (attribution required — Serge Shima, github.com/smixs/visual-skills)
description: >
  Image prompting skill for Nano Banana (NBP/NB2) and GPT Image 2.5 (Flare/Sunburst). Writes ready-to-use
  prompts with model/quality/size recommendations. Use when: "нарисуй", "сгенерируй
  картинку", "image prompt", "промпт для картинки", blog covers, slides, posters,
  product shots, UI mockups, storyboards, character sheets, edit/colorize, style transfer,
  vision analysis, image-to-prompt, nb, NBP, NB2, gpt-image-2.5, multi-panel grids,
  ecommerce product photography, fashion editorial, food/beverage ads, cinematic portraits.
  Do NOT use for: video (use video skill), 3D models, audio, non-image tasks.
---

# Image Prompting — Nano Banana & GPT Image 2.5

This skill writes image prompts. It does not generate images. The output is: model name + quality / size / aspect ratio + the prompt itself.

The body of this SKILL.md is intentionally thin so you cannot fake a result by reading it alone. The actual rules — what the models reward, what they punish, how to phrase a 5-slot template, when to add `quality: high`, when to use image grounding — live only in the reference files.

## Route first — is this actually an image-prompt task?

- **Motion, clips, montage** (Seedance, Kling, Veo, any image-to-video): use the sibling `video` skill. This skill's storyboard and keyframe outputs feed it.
- **No idea or script yet** (user wants a concept or an ad scenario, not a picture): if the `creative-director` skill is installed, start there — it develops ideas and scripts for commercials and beyond ([github.com/smixs/creative-director-skill](https://github.com/smixs/creative-director-skill)).
- **A concrete image is needed** — this skill. Continue below.

---

# Mandatory reading order — DO NOT WRITE A PROMPT WITHOUT THIS

Past attempts to write prompts directly from this skill body produced lazy, generic results. Each model has its own physics; common rules collapse into mush when applied without model-specific syntax. Read in this order before producing any prompt:

### Step 1 — always read first → [models.md](references/models.md)

Decide: Nano Banana (NB2 or NBP) or GPT Image 2.5 (Flare for speed, Sunburst for precision edits). The choice changes the prompt syntax fundamentally — natural-language paragraphs vs. labeled 5-slot template, quality settings, which features exist (image grounding only on NB, EXACT TEXT discipline only on GPT Image, etc.).

If the user named a model — confirm and proceed. If not — pick using the table in `models.md`, then state your choice in the output header.

### Step 2 — read **one** model file (the one you picked)

- **Nano Banana** → [nano-banana.md](references/nano-banana.md)
  Image grounding for real locations. Extreme aspect ratios (1:8, 8:1, 4:1). Thinking mode. JSON for 5+ elements. Up to 14 reference images. Why you must NOT write `50mm / f-stop / ISO` numbers.

- **GPT Image 2.5** → [gpt-image.md](references/gpt-image.md)
  5-slot template (Scene / Subject / Important Details / Use Case / Constraints). Anti-slop banned-words list. `quality: low / medium / high / xhigh / max` as a deliberate fidelity lever. Size constraints (multiples of 16, max 3:1, up to 4K 3840×2160). Two-column edit logic (Change / Preserve / Constraints). Up to 16 reference images with explicit roles.

The model file is non-negotiable. Skipping it is the single biggest cause of weak prompts.

### Step 3 — always read after the model file → [golden-rules.md](references/golden-rules.md)

Universal rules that apply to both models: start with a verb, positive framing, hex colors, quote text, edit don't re-roll, one change per iteration, reference images.

### Step 4 — task-shaped reading (load only what matches the request)

Pick zero or more, depending on what the user asked for:

- Text in image, infographic, diagram, multilingual rendering → [text-rendering.md](references/text-rendering.md)
- Edit existing image (object removal, lighting swap, colorization, restoration, localization) → [editing.md](references/editing.md)
- Character continuity across multiple images / panels → [characters.md](references/characters.md)
- **The image must pass as a real photograph** (portrait, reportage, UGC, casting, product-in-hand) — or the user says the result "looks AI", "too glossy", "not like the reference" → [de-slop.md](references/de-slop.md). Model default priors, banned booster words, capture pipeline instead of adjectives, located imperfections.
- Presentation slides → [slides.md](references/slides.md)
- Sequential narrative (storyboard, comic, panel sequence) → [storyboards.md](references/storyboards.md)
- Sketch → final, wireframes, structural input → [structural.md](references/structural.md)
- 2D → 3D, floor plans, isometric → [dimensional.md](references/dimensional.md)
- **Vision analysis / image-to-prompt / style transfer from a reference image** → [vision-decomposer.md](references/vision-decomposer.md). Load this whenever the user attaches an image and asks to recreate, match, decompose, or transfer its style.
- **Multi-panel compositions** (grids, collages, storyboard sheets in ONE image) → [multi-panel.md](references/multi-panel.md). 9-cell TVC grids, 2x2 portrait grids, 3-panel campaign collages, 4x3 borderless grids, 6-frame cinematic sequences, before/after splits, 12-panel storyboard posters.
- **Industry pattern libraries** — proven prompt templates by vertical. Load the matching file:
  - E-commerce product shots → [patterns/ecommerce.md](references/patterns/ecommerce.md)
  - Fashion editorial campaigns → [patterns/fashion-editorial.md](references/patterns/fashion-editorial.md)
  - Food & beverage advertising → [patterns/food-beverage.md](references/patterns/food-beverage.md)
  - Cinematic portraits → [patterns/portrait-cinema.md](references/patterns/portrait-cinema.md)
  - Posters & illustration → [patterns/poster-illustration.md](references/patterns/poster

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/smixs/visual-skills
git -C visual-skills checkout 119c44cf54e6

Works in

1. 2026-10-20
   ✓SAFE B 89 / 100

   first audit · source 119c44cf54e6

Questions about Image

• github.com/smixs/visual-skills/tree/main/image — the audited source at commit 119c44cf54e6 and every finding aboveObserved · 20 Oct 2026

Spotted something wrong? Report a correction · Methodology