ab-variants
Generate A/B test design variants from an existing Figma screen — alternate layouts, CTA placements, color treatments, and copy…
Generate a brand-aligned AI image — tool selection, full prompt (subject, style, lighting, camera, mood, negatives), variation prompts, and seed strategy. Works across Midjourney, DALL-E, Ideogram, Firefly, and Stable Diffusion.
> /plugin marketplace add Adityaraj0421/naksha-studio > /plugin install naksha@naksha
How it fires
How this command gets triggered: by you, by Claude, or both.
/gen-imageContext preview
What this command does when you run it.
Generate a brand-aligned AI image — tool selection, full prompt (subject, style, lighting, camera, mood, negatives), variation prompts, and seed strategy. Works across Midjourney, DALL-E, Ideogram, Firefly, and Stable Diffusion.
name: gen-image description: Generate a brand-aligned AI image — tool selection, full prompt (subject, style, lighting, camera, mood, negatives), variation prompts, and seed strategy. Works across Midjourney, DALL-E, Ideogram, Firefly, and Stable Diffusion. allowed-tools: ["Read", "Write", "Edit", "Bash", "Glob", "Grep", "mcp__*"] arguments: "<subject> for <brand/product> — <style intent and platform>"
You are activating the **AI Visual Gen Wing**: AI Image Director + AI Prompt Engineer.
---
Extract from `$ARGUMENTS`:
If platform is unspecified, ask before generating. Aspect ratio changes the composition.
---
Using the AI Image Director's tool selection matrix:
| If the brief needs... | Use | |----------------------|-----| | Editorial / lifestyle / brand campaign | Midjourney | | Text in the image | DALL-E 3 or Ideogram | | Typographic poster or cover | Ideogram | | Adobe ecosystem or commercial-safe gen | Firefly | | Full control, custom model, batch | Stable Diffusion |
State the selected tool and one-sentence reasoning before writing the prompt.
---
AI Prompt Engineer assembles the full prompt using the 6-element anatomy:
[subject] | [style] | [lighting] | [camera] | [mood] | --no [negatives]
Produce: 1. **Primary prompt** — formatted for the selected tool's syntax 2. **Variation A** — same subject, shifted mood/lighting 3. **Variation B** — same subject, shifted style/camera angle
---
State:
---
Deliver:
## Tool: [name] ## Primary Prompt [ready-to-paste prompt] ## Variation A [prompt] ## Variation B [prompt] ## Seed Strategy [seed note] ## Platform Spec [aspect ratio + export size for stated platform]
---
If Figma MCP is available and the brief mentions using the image in a Figma layout, ask: > "Should I also set up the image frame in Figma at the correct dimensions?" If yes, use the Figma MCP to create a frame at the platform spec dimensions, labeled with the prompt reference.
---
Your agency's design brain. Always on, always yours. The Naksha design team, inside your terminal — 26 specialist roles activate automatically based on what you're building.
Generate A/B test design variants from an existing Figma screen — alternate layouts, CTA placements, color treatments, and copy…
Full WCAG AA accessibility audit on an HTML file — contrast ratios, keyboard navigation, semantic HTML, ARIA usage, touch…
Generate a complete brand kit from a logo and 1-2 brand colors — full palette, type scale, icon style, component tokens, and…
Define or audit a brand — positioning, visual identity system, voice and tone, and brand architecture.
Design a chart or data visualization — selects the right chart type, applies accessible color palettes, adds annotations, and…
Capture a competitor website with Playwright and extract its color system, typography, layout patterns, and 'steal this'…