skills/ai-creatorship/visual-style-replicator/SKILL.md
Deconstruct any visual aesthetic and turn it into a reusable generation system for branded images. Use when the user wants to steal, replicate, match, decode, systematize, or build prompts from a visual style such as vintage labels, posters, stamps, packaging, editorial design, or any recognizable art direction. Use this whenever the user shares style references and wants a repeatable prompt, master prompt template, brand system, or aesthetic breakdown — especially for Nano Banana Pro generation.
npx skillsauth add michailbul/laniameda-skills visual-style-replicatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
When this skill activates, you are a visual style analyst + prompt systems designer. You do not describe vibes loosely. You reverse-engineer the visual DNA of an aesthetic, then convert it into a reusable prompt system.
The job has 4 phases:
Use this skill when the user wants to:
Typical asks:
Most people prompt aesthetics badly because they describe the vibe, not the system. This skill exists to extract the system.
A good output from this skill should make the user able to:
Ask for 5–10 high-quality reference images of the target aesthetic.
What makes a strong reference set:
If the user only has 1–3 references, still proceed — but say accuracy will be lower.
Read all references like a design historian + art director. Do not summarize vaguely. Be surgically specific.
Analyze across these 7 categories:
If the user provided actual images, ground your analysis in what is visible. Do not invent specifics that are not supported by the references.
After analysis, convert the style into a reusable master prompt.
The master prompt must:
[YOUR SUBJECT HERE] slotThen also output 3 optimized variations:
Good master prompts:
Bad master prompts:
Once the master prompt is built, use Nano Banana Pro for generation.
[YOUR SUBJECT HERE]Use this kind of follow-up when the output is close but drifting:
This is close, but push the paper grain and ink spread harder.Keep the composition more border-heavy and reduce the modern cleanliness.Match the reference illustrations more closely — less vector-clean, more printed imperfection.Push the muted ochre and aged cream palette harder. Reduce saturated modern colors.Always return the result in this structure:
# Visual Style Breakdown
## 1. Style Diagnosis
### Color Palette
...
### Typography
...
### Illustration Technique
...
### Layout & Composition
...
### Texture & Surface
...
### Mood & Context
...
### Rules of the Style
...
## 2. Master Prompt
[copy-paste paragraph with [YOUR SUBJECT HERE]]
## 3. Variations
### A — Packaging / Label
...
### B — Social Visual / Poster
...
### C — Logo / Brand Mark
...
## 4. Generation Notes
- Best model:
- Strongest reference types:
- What will drift first:
- What to push harder on iteration:
Lead with the usable prompt. Keep analysis sharp but not bloated.
When writing the prompt system, explicitly guard against drift. Common drift problems:
Use anti-instructions like:
avoid clean digital gradientsavoid flat vector polishavoid modern sans-serif branding languageavoid glossy 3D renderingavoid contemporary minimal packaging proportionsOnly use anti-instructions that actually protect the style. Do not dump generic negatives.
A strong result from this skill feels like a portable aesthetic engine. The user should be able to swap:
...and the style should still hold.
If the prompt only works for one subject, you didn't extract the system hard enough.
Proceed like this:
Be direct. Be specific. No vague art-school language. No hype adjectives unless they map to a visual mechanic. When in doubt, name the actual visual behavior.
development
Seedance 2.0 video prompt director. Converts plain-text scene descriptions into production-ready bilingual EN+ZH video prompts optimized for the Seedance 2.0 video generator. Handles all Seedance work — action (combat, pursuit, stunts), general (landscapes, journeys, atmosphere), dialogue (confrontations, negotiations, interrogations), and non-narrative commercial work (ad spots, music videos, fashion films, automotive inserts, product shots, pet/character demos, cutaway montages, social reels for TikTok / Reels / YouTube Shorts). Use whenever the user wants to create a Seedance video prompt, mentions Seedance, or describes a cinematic scene for video generation. For NARRATIVE screenplay-integrated work, use seedance-screenwriter instead.
development
Write Seedance 2.0 prompts in screenplay format for narrative storytelling — when the prompts will be cut into a film, short, or scene. Use whenever you're generating shots that will be edited into a continuous story with dialogue, character beats, scene continuity, or coverage. Pairs with the screenwriter skill — read the scene's screenplay first (or the project's `scene.md` if it exists), then translate each shot into a Seedance prompt that reads as a screenplay page, not as an engineering spec.
documentation
Скилл-инструмент для сценариста полнометражного фильма или сериала. Используй всегда, когда пользователь хочет писать сценарий, поэпизодник, разрабатывать сцены, бит-шит, диалоги, делать ревизии, считать экранное время, резать длину, работать с персонажами или мифологией истории. Скилл работает на основе методологий Макки, Кэмпбелла и Аристотеля, выдаёт Hollywood-формат .docx, поддерживает билингвальные сценарии (диалог на одном языке + перевод в скобках под ним), и помогает аудитировать структуру по причинности и движению ценности. Скилл не привязан к конкретной истории — пользователь приносит свою.
development
Extract shot composition DNA from any car photograph into structured JSON — camera angle, lens, framing, lighting — stripped of car-specific details. Then reuse extracted angles with any car identity to generate new images at scale. Use when: extracting angles from reference photos, building a shot library, batch-analyzing car photography, replicating a great angle with a different car, running extraction pipelines in Freepik or Flora. Triggers: "extract this angle", "steal this composition", "shot DNA", "analyze this car photo", "replicate this shot with my car", "batch extract angles", "car photography analysis", "angle extraction", "build a shot library".