SkillFoxx

tait-crt-interface-skill

Codex skill that turns a portrait, photo or text description into a retro illustration in the style of an early CRT interface.

  • 547 ★ on the repository
  • Last commit
Skill

Minimal access

Why this level

  • Uploaded photos of people are processed by your environment's image generation model.
All reasons and checks

tait-tt/tait-crt-interface-skillAuthor:TaiT-tt

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/tait-crt-interface-skill

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Minimal accessThe tool runs nothing and makes no network calls.

  • Uploaded photos of people are processed by your environment's image generation model.

This is third-party code. Review the repository files before installing.

What it does

The skill takes an uploaded portrait, photograph or text description and generates one finished image. A pixel subject fills most of the frame, surrounded by windows in the spirit of early Macintosh, Minitel and 8-bit computers, with scanlines, glow and CRT barrel distortion. Before generating, the skill asks for a palette (`经典`, `粉黛`, `极客01`, `极客02`, `复古01`, `复古02`, `游戏01`, `游戏02` or `如图`) and an aspect ratio: `3:4`, `4:3`, `9:16`, `16:9`. Three ready style templates exist: `街头怪诞`, `巨像符号`, `冷面几何`.

Who it is for. Designers and content authors who want retro illustrations and covers in the style of old computers without hand-made pixel art.

Good fit when

  • A post cover needs the author's portrait in a 1980s aesthetic.
  • A team photo should become a poster with old interface windows.
  • One idea is tried in several palettes and aspect ratios.
  • A text description of an image turns into a picture with no uploaded photo.
  • A series of illustrations sticks to one visual style.

Not a fit when

  • You need photorealistic graphics or exact likeness of faces.
  • The environment cannot generate images, and the skill stops with a message.
  • Several variants are required in one run, while the skill produces exactly one image.

Example request

Use $tait-crt-interface-skill to make a CRT illustration from this photo, palette `极客02`, ratio 4:3.

Limitations

The skill is written for Codex and relies on built-in image generation. Without it the skill stops. The dialogue and palette names are mostly in Chinese. The repository states no licence. The last commit dates to August 2026.

How to disable. Delete the `~/.codex/skills/tait-crt-interface-skill` folder.

FAQ

How do I call the skill?

With a command such as "Use $tait-crt-interface-skill, generate an image, palette `极客02`, ratio 4:3" and an uploaded image.

What if I give no palette and ratio?

The skill asks for a palette from a list, then a ratio, and only then creates the image.

Can I use my own palette?

Yes, the `如图` value derives two to five colours from the mood of the uploaded image.

Does it work without Codex?

The README presents it as a Codex skill. SKILL.md defines a simplified mode for environments with image generation but no local scripts.

How many images does one run produce?

One. The skill does not create repeat variants.

Discussion

No questions or reviews yet.

Skills

A Codex skill that redraws your photo as a watercolor illustration on white paper, with wide margins and a handwritten caption

SkillMinimal access610

A skill that turns a picture into a generator prompt: frame breakdown, an enhanced version, three variants and platform editions.

SkillMinimal access61

A Codex skill that turns a photograph into a vertical composition with an abstract memory panel and an English title

SkillMinimal access6.1K

Five image-generation skills: Qwen-Image prompts, logos with shared geometry, diary comics, transparent PNGs and process dioramas

SkillMinimal access241

Codex skill for Pikatang-inspired pixel art: characters, pets, houses, interiors and icons from a brief or a reference.

SkillExtended access95

A skill that adds image generation to Claude Code and Cursor through the Codex CLI on a ChatGPT subscription, no API key.

SkillExtended access84

README in short

The Chinese and English README lists the visual traits of the style, ready palettes, three templates and installation into the Codex skills folder.

README badge

Original SKILL.md

---
name: tait-crt-interface-skill
description: Generate exactly one finished CRT retro computer-interface illustration from an uploaded portrait, group photo, creature, object, or described theme. Use when the user wants anchored subjects re-authored as an exaggerated circa-1980s bitmap editorial caricature beneath early Macintosh or Minitel-style windows, optionally invoking the exact Chinese presets 街头怪诞, 巨像符号, or 冷面几何. Before generation, collect a named or image-derived palette and aspect ratio through a strict two-stage intake unless supplied. Preserve each intended subject as a distinct identity, one shared pixel lattice, restricted non-skin checkerboard midtones, low-facet geometry, unequal extraction windows, mandatory barrel-curved CRT edges, and the immutable tait-crt-interface-skill title-bar signature. Never trace, auto-pixelate, imitate photographic detail, omit, merge, or duplicate subjects, retry, resize, expose prompts, or ask users to choose a style preset.
---

Report a problem