Rn Cover Skill logo

Rn Cover Skill

CommunityPopular
Pluviobyte
rn-cover-skill

Create reference-free 5:2 editorial technology covers with exact

Overview

PublisherPluviobyte
Repositoryrnskill
Skill namern-cover-skill
Stars
1.6K
Forks
181
Bundled files
3
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Pluviobyte on GitHub. Read the source before you install it.

Installation

Install the Rn Cover Skill AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Pluviobyte/rnskill.git /tmp/rnskill
mkdir -p .claude/skills
cp -r /tmp/rnskill/skills/rn-cover-skill .claude/skills/rn-cover-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Rn Cover Skill in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Rn Cover Skill on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Rn Cover Skill is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

RN Cover Skill

Create each cover from a written style contract, not an image reference. Use ImageGen only for fresh right-side artwork. Use the bundled compositor for the exact background and controlled but adjustable grid, geometry, and typography.

Inputs

Resolve:

  • label: optional short Latin/tool line, such as Codex + Hyperframes + HeyGen:
  • title: Chinese benefit or topic headline
  • subtitle: optional one- or two-line supporting sentence
  • theme: semantic concept for the right-side diagram
  • output directory

Default to 3000 × 1200 (5:2). Split a combined title at or : when the left part is mostly Latin/tool names and the right part is Chinese.

Workflow

  1. Plan the text before generating artwork.
    • Keep the Chinese title on one line whenever it fits at 96px or larger.
    • Begin from an asymmetric left-text/right-visual composition, then adjust by optical balance.
    • Let Chinese and mixed-language titles expand; move or resize the artwork only as much as needed.
    • Make Chinese the primary focal point; keep the Latin label smaller.
    • Vertically center the complete left text group, whether it contains a title only or a label plus title.
  2. Read references/style-contract.md.
  3. Choose a fresh right-side visual family and topology from the topic semantics.
  4. Call built-in ImageGen in generate mode for an isolated diagram asset on a flat #00FF00 chroma-key background.
    • Omit referenced_image_paths.
    • Omit num_last_images_to_include.
    • Generate new artwork for every new cover; never reuse a previous cover’s right-side artwork unless the user explicitly asks.
    • Request no canvas background, grid, title, letters, numbers, logos, or watermark.
    • Keep the diagram tightly cropped and fully separated from the chroma background.
  5. Remove the chroma key:
bash
python "${CODEX_HOME:-$HOME/.codex}/skills/.system/imagegen/scripts/remove_chroma_key.py" \
  --input "/absolute/path/cover-artwork-chroma.png" \
  --out "/absolute/path/cover-artwork-transparent.png" \
  --auto-key border \
  --soft-matte \
  --transparent-threshold 12 \
  --opaque-threshold 220 \
  --despill
  1. Inspect the transparent artwork. Require transparent corners, clean line edges, no green fringe, and no pseudo-text.
  2. Compose exact text and deterministic geometry:
bash
python3 <skill-dir>/scripts/compose_cover.py \
  --artwork "/absolute/path/cover-artwork-transparent.png" \
  --label "Codex + Hyperframes + HeyGen:" \
  --title "开源自媒体涨粉的秘诀" \
  --output "/absolute/path/cover.svg" \
  --png "/absolute/path/cover.png"

Use --subtitle, --italic-title-lines, --artwork-start, or the grid/artwork geometry overrides only when the content calls for them. Run --help for overrides.

Non-negotiable style

  • Fix the canvas background to #FAF9F5; never take the background color from ImageGen.
  • Draw a visible but quiet square grid in SVG across the right visual field. Keep its start, density, and strength adaptable instead of copying one template; omit it only when the user explicitly asks for no grid.
  • Keep the diagram on the right while allowing it to approach the center or move farther right according to headline length.
  • Use charcoal diagram strokes and one restrained muted-coral signal; no broad orange fills.
  • Left typography expands horizontally; the illustration shrinks or moves right to yield space.
  • Vertically center the complete left text group.
  • Use a heavy editorial serif for Latin headlines and italicize only an intentional emphasis line.
  • Chinese title uses a near-black heavy sans and carries more visual weight.
  • Use a smaller heavy italic serif for optional supporting copy.
  • Do not add an underline, divider, rule, or decorative line beneath the text.
  • No portraits, stickers, neon, glossy 3D, dense UI, or decorative copy.
  • Treat reference covers as aesthetic calibration only. Do not copy their node count, exact loop, object placement, labels, or decorative details.

Do not ask the image model to render final title text. Keep all real text in SVG.

Regeneration rule

  • New cover: always generate a new right-side illustration from scratch with no reference inputs.
  • Concept or layout revision: regenerate the right-side illustration.
  • Minor typography-only correction: reuse the current illustration unless the user asks for a new one.

Vary visual family, topology, node count, connector route, central object, curve, and coral signal placement while preserving the style contract. Do not make a series look like the same diagram with only text swapped.

Quality gate

  1. Inspect the transparent artwork before composition. Reject pseudo-text, green fringe, clipped geometry, excessive padding, or an oversized diagram.
  2. Inspect final PNG at full size and 25%.
  3. Confirm every requested character and punctuation mark is exact.
  4. Confirm Chinese remains readable first, Latin second, diagram third.
  5. Confirm at least 4% canvas-width clearance between text and artwork.
  6. Confirm the left text group is vertically centered and has no decorative underline.
  7. Sample clean background pixels and confirm they are exactly #FAF9F5.
  8. Confirm the right-side grid remains perceptible at 25% scale without competing with the artwork, and that both are optically balanced rather than mechanically matched to a reference.
  9. Confirm SVG is editable/self-contained and PNG dimensions match.
  10. Report the final paths, the no-reference ImageGen prompt, and that built-in ImageGen was used.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Rn Cover Skill AI skill do?

Create reference-free 5:2 editorial technology covers with exact

Why use Rn Cover Skill on TypingMind?

Because you install it once and use it with any model. Rn Cover Skill is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Rn Cover Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Pluviobyte/rnskill/tree/main/skills/rn-cover-skill. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Rn Cover Skill?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Rn Cover Skill?

As many as you like. As long as a model supports skills, you can use Rn Cover Skill with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Rn Cover Skill AI skill free?

It is published on GitHub by Pluviobyte. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇