skills/transparent-bg/SKILL.md
Produce a truly RGBA-transparent asset from a brief. Handles the
npx skillsauth add MohamedAbdallah-14/prompt-to-asset transparent-bgInstall 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.
Almost every modern T2I VAE is RGB-only. Asking Imagen 3/4 or Gemini 2.5/3 Flash Image for a "transparent logo" triggers one of two failures:
| Provider | Mechanism |
|---|---|
| gpt-image-1 / gpt-image-1.5 | API param background: "transparent" + output_format: "png" or "webp" |
| Ideogram 3 Turbo | Dedicated /ideogram-v3/generate-transparent endpoint; set rendering_speed: "TURBO" for Turbo tier |
| Recraft V3 | native SVG output (alpha is trivial); rasterize if raster needed |
| LayerDiffuse on SDXL / Flux | In-diffusion-loop transparency adapter; better edges than post-matte |
| Matting model | License | Strength | |---|---|---| | BiRefNet | MIT | Default choice 2026; best soft-edge handling | | BRIA RMBG-2.0 | CC-BY-NC-4.0 (hosted API for commercial) | Best overall quality | | U²-Net | Apache-2.0 | Legacy fallback | | rembg | wrapper around U²-Net / BiRefNet | Easy CLI integration | | SAM 2 | Apache-2.0 | For complex/multi-object scenes; 2-stage (segment → matte) |
alpha = (white_version - black_version + 255) / 2 in luminance.rembg/BiRefNet produce hard-cutout artifacts.vtracer or potrace.@resvg/resvg-js for RGBA PNGs.Tier-0 alpha validator (see packages/mcp-server/src/pipeline/validate.ts):
1. Check PNG/WebP header has alpha channel type (RGBA, not RGB).
2. Reject if no pixels have alpha < 255 (it's opaque).
3. Reject if >5% of pixels have alpha ∈ [0.05, 0.95] AND FFT signature shows gray-tile band frequency (Gemini fake checkerboard).
4. Alpha coverage: subject pixels (alpha > 0.5) should occupy 30–85% of frame (sanity check).
5. Premultiplied-alpha check: no RGB values where alpha==0 (cleanup artifacts).
Do not ask for transparency in the prompt. Ask for pure white:
[SUBJECT, concrete].
Centered, isolated, no surrounding context or props.
Solid pure white #FFFFFF background.
Clean silhouette with distinct outline.
No drop shadow, no ground plane, no reflection.
1:1 square, 1024x1024.
Then post-process with BiRefNet / BRIA.
"transparent background" as a prompt to Imagen or Gemini (checkerboard result).output_format: "png" alone to produce alpha (PNG supports alpha, but the model has to emit it).#FFFFFF → alpha=0 thresholding (loses anti-aliasing, creates jagged edges).transparent/
├── mark.png # RGBA, validated
├── [email protected] # optional high-DPI
├── mark.svg # if vector path chosen
└── meta.json # alpha_coverage, matting_method, validation_hash
testing
Translate a UI brief (a page, a screen, a single component, a feature) into a paste-ready prompt for Nano Banana Pro / gpt-image-2 / Ideogram / Flux 2 / Midjourney that produces a designer-grade mockup as visual inspiration — not pixel-spec UI, not AI slop. Use whenever the user asks for "imagine the X page", "mock up the Y screen", "give me a prompt for nano banana / gpt image 2 to design", "describe this UI for an image model", "draft a prompt for the designer to take inspiration from", or any time the agent needs to produce a UI image-gen prompt for a real product surface (pricing page, dashboard, settings, onboarding, mobile screen, marketing hero, single component). Be pushy — trigger even when the user says "design" without "prompt", or "show me what X could look like" — the agent should reach for this skill before hand-rolling a brief.
testing
Translate a UI brief (a page, a screen, a single component, a feature) into a paste-ready prompt for Nano Banana Pro / gpt-image-2 / Ideogram / Flux 2 / Midjourney that produces a designer-grade mockup as visual inspiration — not pixel-spec UI, not AI slop. Use whenever the user asks for "imagine the X page", "mock up the Y screen", "give me a prompt for nano banana / gpt image 2 to design", "describe this UI for an image model", "draft a prompt for the designer to take inspiration from", or any time the agent needs to produce a UI image-gen prompt for a real product surface (pricing page, dashboard, settings, onboarding, mobile screen, marketing hero, single component). Be pushy — trigger even when the user says "design" without "prompt", or "show me what X could look like" — the agent should reach for this skill before hand-rolling a brief.
development
Rewrite an asset brief into the exact prompt dialect of the target image model (OpenAI gpt-image-1, Google Imagen/Gemini, SDXL, Flux.1/Flux.2, Midjourney, Ideogram, Recraft). Handles negative-prompt translation, token budgets, transparency quirks, brand-palette injection, and text-in-image ceilings so that `asset_generate_*` submissions succeed on the first try.
development
Generate a production-grade logo (primary brand mark). Returns RGBA PNG master + SVG vector + monochrome variant. Route by text-length and per-model ceiling. Strong-text models render multi-word and even paragraph-length wordmarks reliably; weak-text models composite SVG type post-render.