Oil Icon logo

Oil Icon

Community
oil-oil
oil-icon

生成风格统一的图标集合,通过宫格生图、切分和去背景交付透明 PNG。用户需要成套自定义图标、栏目图标或匹配品牌风格的图标时使用;不用于单个简单矢量图标或小尺寸密集功能符号。

Overview

Publisheroil-oil
Repositoryoil-icon
Skill nameoil-icon
Stars
314
Forks
30
Bundled files
85
LicenseMIT
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.

  • 85 bundled files

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

  • Open source

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

Installation

Install the Oil Icon 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.
    https://github.com/oil-oil/oil-icon/tree/main
  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/oil-oil/oil-icon.git \
  .claude/skills/oil-icon
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Oil Icon 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 Oil Icon 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 Oil Icon 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.

oil-icon

Generate a set of icons that share one visual style, output as transparent PNGs.

Image generation runs on a flat grey backdrop as a 4×4 sheet — 16 icons in one generation, 有助于统一风格,但仍需逐个检查 — then each cell is sliced out and background-removed.

Agent owns the design decisions (which style, which palette, which metaphors, whether to match a brand); image generation and slicing are mechanical steps.

API Key 配置入口

需要外部服务凭据时先读API Key 配置与业务读取:复用已有安全入口;本机缺少 Key 时使用随附固定页面,保存后通过业务包装入口读取。内置能力与纯本地流程不要求配置 Key。

Workflow

  1. Choose the style. Either pick a built-in from styles/ (table below), or match the user's brand by reading their project's design tokens / assets and deriving a custom style-spec — see reference/style-adaptation.md. Freeze the result as a style-spec with the same fields as the built-in JSONs; 后续批次复用同一规范,并检查生成偏差.
  2. List the icons. Write each concept as name — short concrete metaphor (e.g. settlement — a wallet with a coin). One clear idea per icon; keep the detail level consistent across the set. 默认每张 16 格;明确选择 9 格时,提示词使用 3×3,切图命令必须同时传 --grid 3。 If the user asks for an exact count below 16, still use a 4x4 / 16-cell sheet: place the requested icons first in row-major order, then explicitly ask the remaining cells to stay empty grey background.
  3. Compose the prompt. style.preamble + the style's construction fields (as short guidance) + palette-lock line + numbered metaphors + the fixed composition text — see reference/prompt-template.md and reference/construction.md.
  4. Generate the sheet(s). Choose an image provider by capability, in order (see reference/image-providers.md) — never assume Codex is present:
    1. Built-in / host imagegen first — if the running agent already has a callable image-generation tool, including Codex's built-in image_gen tool or the imagegen skill, call it directly. Do not delegate to external Codex CLI just to reach imagegen from another process.
    2. Codex CLI fallback — only if this agent has no callable image-generation tool, and Codex is available (从可用 Skill 清单定位 codex,或使用 PATH 中已有的 codex), delegate generation to it.
    3. External API fallback — only if neither of the above exists, 沿用用户已授权的供应商;缺少凭据时按配置说明打开随附页面,不索要聊天中的 Key; for OpenAI Images, scripts/gen_image.py --prompt "…" --out raw/<style>.png is ready. Save or copy each generated sheet to raw/<style>.png on flat grey #808080. Built-in imagegen may save under $CODEX_HOME/generated_images/...; after generation, move or copy the selected PNG into the task output raw/ folder. 同一张图更容易保持共同风格,但仍须逐个验收,不能把一次生成视为一致性保证; a provider only has to turn the prompt into a grey-background PNG.
  5. Slice. Run scripts/setup.sh once, then: .venv/bin/python3 scripts/slice_icons.py <raw>.png <outdir> --mode <cutout> [--thresh N] [--grid 4] [--count N] using the style's cutout mode (floodfill for flat/hard-edge, rembg for soft / 3D / glossy / photo).
  6. QA (mandatory). Composite the sliced PNGs onto a contrasting colour (e.g. magenta) and check every icon for (a) a fragment bled in from a neighbouring cell, (b) leftover grey, and (c) consistency against the style's construction — uniform stroke, one radius, matched detail level, shared parts, motif present, single perspective, and no accent out-weighting the defining element (in line styles the accent must be lighter and smaller than the stroke). Re-slice or regenerate any that fail — never ship an icon carrying part of the one above it.
  7. Deliver the transparent PNGs, organized and named.

Built-in styles

stylelookcutoutfits
linearmono line / outlinefloodfillutility, settings
filledsolid single-colour glyphsfloodfillmobile nav / tab bars
colorblockbold flat multi-colour blocksfloodfillkids, creative
cartoonsticker-style cartoonrembggames, entertainment
isometricisometric 3D miniaturesrembgSaaS, dashboards
render3dglossy puffy 3Drembgrewards, onboarding
stickerdie-cut glossy vinylrembgsocial, reactions
realisticphotoreal product rendersrembge-commerce, hero
animal-badgeanimal emblems in badgesrembgavatars, kids

Each styles/<name>.json holds the preamble, locked palette, cutout mode, threshold, construction system, and what it fits.

Key rules (see reference/design-rules.md)

  • Lock the palette as hex in the spec — colourful styles drift run-to-run otherwise.
  • Never make black filled icons — near-black / black may be used as a thin outline or line stroke, but never as the dominant filled mass of an icon set. If the brand foreground is black, map it to strokes only; for filled or duotone styles, choose a mid-light brand colour for the main shape and keep dark colours small.
  • Start from the real product context — when a user gives a live site, screenshot, mascot, logo, or brand asset, derive the icon concepts and construction from that source first. Do not jump straight into generic style families such as isometric, duotone, 3D, or colorblock; those are finishes applied after the product motif, real navigation, and real feature names are locked.
  • Slicing drops neighbour bleed — the slicer keeps only the centred icon per cell.
  • Cutout by edge type — flat/hard-edge → floodfill; soft / 3D / glossy / photo → rembg.
  • Design sophistication comes from a construction system + a brand motif, not from tinting a generic set — each style's construction object encodes the grid, stroke, radius, detail budget, shared parts, and motif (see reference/construction.md). A rigorous system ultimately wants vector; raster is for direction and spot icons.

Bundled files

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

and 25 more files.

Frequently asked questions

What does the Oil Icon AI skill do?

生成风格统一的图标集合,通过宫格生图、切分和去背景交付透明 PNG。用户需要成套自定义图标、栏目图标或匹配品牌风格的图标时使用;不用于单个简单矢量图标或小尺寸密集功能符号。

Why use Oil Icon on TypingMind?

Because you install it once and use it with any model. Oil Icon 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 Oil Icon in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/oil-oil/oil-icon/tree/main. 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 Oil Icon?

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 Oil Icon?

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

Is the Oil Icon AI skill free?

Yes. It is published on GitHub by oil-oil under the MIT license. 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 👇