Editorial Dot Cover logo

Editorial Dot Cover

CommunityPopular
Pluviobyte
editorial-dot-cover

Create deterministic editorial-style cover images with a warm paper-gray background, oversized black slab-serif/Chinese display typography, generous whitespace, and a dotted vector analysis icon. Use when the user asks for a “点阵编辑风封面”, “暖灰杂志风封面”, “Codex + Hyperframes 同款封面”, or wants to reproduce/adapt the specific minimal left-text/right-icon banner style. Produce editable SVG and a rendered PNG; do not use this skill for generic covers without this visual direction.

Overview

PublisherPluviobyte
Repositoryrnskill
Skill nameeditorial-dot-cover
Stars
1.6K
Forks
181
Bundled files
4
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.

  • 4 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 Editorial Dot Cover 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/editorial-dot-cover .claude/skills/editorial-dot-cover
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Editorial Dot Cover 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 Editorial Dot Cover 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 Editorial Dot Cover 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.

Editorial Dot Cover

Create a typographically accurate cover from vectors. Prefer the bundled renderer over image generation so Chinese text and punctuation remain exact.

Required inputs

Resolve these values from the request or current project:

  • label: short English/tool label, such as Codex + Hyperframes:
  • title: one concise Chinese headline
  • output: destination SVG and PNG paths

Default to 3168 × 1267 (about 2.5:1). If the user provides no label, derive a short tool/topic label. Ask only when the title itself cannot be inferred safely.

Render

Run:

bash
python3 <skill-dir>/scripts/render_cover.py \
  --label "Codex + Hyperframes:" \
  --title "拆解抖音爆款·吃上自媒体这碗饭!" \
  --output "/absolute/path/cover.svg" \
  --png "/absolute/path/cover.png"

Use --width and --height only when a different landscape ratio is requested. Use --font-en or --font-cn when the user specifies a font. Run --help for all parameters.

Use --label-size or --title-size for art-directed pixel sizes when mixed-language font metrics make the automatic fit inaccurate. Preserve the required text-to-icon gap after overriding either value.

Use assets/style-reference.png only as a visual comparison target when checking fidelity; generate new covers from the script instead of copying pixels from the sample.

The script keeps an editable SVG as the source of truth and uses an installed Chromium-family browser or rsvg-convert for PNG rendering. If neither renderer exists, deliver the SVG and report that PNG rendering remains pending.

Style contract

Preserve these traits:

  • Warm gray paper background near #D6D0C5, with subtle grain and a weak center glow/vignette.
  • Nearly black foreground near #050505; do not introduce accent colors unless requested.
  • Left-aligned text block occupying about 68–72% of the canvas.
  • Right-side dotted film-and-magnifier symbol occupying about 18–20%.
  • English line in a heavy slab serif. Prefer Roboto Slab Black; fall back to Rockwell or a heavy serif.
  • Chinese line in a very heavy display sans. Prefer a licensed installed display face; fall back to Source Han Sans SC Heavy or PingFang SC Heavy.
  • Tight tracking, compact line gap, and large empty top/bottom margins.
  • Use · or to create an internal headline pause; preserve the user’s final punctuation.
  • Render the pictogram as vectors with round dotted strokes. Do not substitute a raster stock icon.

Do not add portraits, stickers, gradients with visible color shifts, badges, drop shadows, or decorative copy. The visual identity comes from typography, whitespace, paper texture, and the dotted pictogram.

Layout decisions

  • Keep one Chinese headline line when it remains legible and fits before the icon.
  • For a long headline, first tighten phrasing. If wording must remain unchanged, insert one intentional line break and vertically recenter the full group.
  • Keep at least 4% canvas width between the text and pictogram.
  • Reduce the English label before reducing the Chinese headline when they compete.
  • For ratios narrower than 1.8:1, preserve the style but allow the icon to move below/right of the text. Do not compress the title until its glyphs look unnaturally narrow.

Quality gate

Before delivery:

  1. Open the PNG at full size and at 25% scale.
  2. Confirm every Chinese character and punctuation mark matches the requested text.
  3. Confirm no glyph, dotted stroke, or magnifier handle is clipped.
  4. Confirm the headline is the first focal point and the icon remains secondary.
  5. Confirm background texture is visible only on inspection, not as obvious noise.
  6. Confirm the SVG remains editable and the PNG dimensions match the contract.

If the dotted symbol collapses at thumbnail size, increase dot spacing or stroke width and rerender.

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 Editorial Dot Cover AI skill do?

Create deterministic editorial-style cover images with a warm paper-gray background, oversized black slab-serif/Chinese display typography, generous whitespace, and a dotted vector analysis icon. Use when the user asks for a “点阵编辑风封面”, “暖灰杂志风封面”, “Codex + Hyperframes 同款封面”, or wants to reproduce/adapt the specific minimal left-text/right-icon banner style. Produce editable SVG and a rendered PNG; do not use this skill for generic covers without this visual direction.

Why use Editorial Dot Cover on TypingMind?

Because you install it once and use it with any model. Editorial Dot Cover 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 Editorial Dot Cover in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Pluviobyte/rnskill/tree/main/skills/editorial-dot-cover. 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 Editorial Dot Cover?

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 Editorial Dot Cover?

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

Is the Editorial Dot Cover 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 👇