Palette

Q: Why use Palette on TypingMind?

Because you install it once and use it with any model. Palette 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.

Q: How do I install Palette in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/with-pebbly/aseprite-ai-artist/tree/main/skills/palette. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Q: Which AI models can use Palette?

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.

Q: How many AI models can I use with Palette?

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

Q: Is the Palette AI skill free?

Yes. It is published on GitHub by with-pebbly under the MIT license. You only pay your own AI provider for the tokens you use.

Q: 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.

Q: 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.

Organization

with-pebbly

palette

Pick a palette that fits the request, build hue-shifted ramps, or clean up a sprite whose colours have sprawled. Use when the user asks about colour, wants a specific retro look, or when validate reports off-palette colours.

Overview

Publisher	with-pebbly
Repository	`aseprite-ai-artist`
Skill name	`palette`
Stars	456
Forks	28
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

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.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by with-pebbly on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/with-pebbly/aseprite-ai-artist/tree/main/skills/palette
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.

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/with-pebbly/aseprite-ai-artist.git /tmp/aseprite-ai-artist
mkdir -p .claude/skills
cp -r /tmp/aseprite-ai-artist/skills/palette .claude/skills/palette

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Palette 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 Palette 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 Palette 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.

Choose, build and repair a palette

Choosing

Match the request, in this order of preference:

The user named a palette or a game. Use it. palette op="preset" for a bundled one, op="load" for a file they have, or reference op="sample_palette" to pull one out of a screenshot they gave you.
The user described an era. "8-bit" → PICO-8. "Game Boy" → gameboy. "NES" → build 12–16 colours by hand as 3–4 hues × 4 values.
The sprite is joining an existing project. sprite_info an existing asset and match it exactly. Consistency beats a nicer palette.
Nothing said. PICO-8. It is 16 colours, forgiving, and reads well.

palette op="preset" with no valid preset lists what is bundled and says that anything else can be loaded from a file.

Building ramps

A ramp is one material's run of colours. Build them hue-shifted:


palette op="ramp" base="#c04030" steps=5 spread=0.55

Shadows come out cooler, highlights warmer — the thing that separates pixel art from a brightness slider. Three to five steps per material is plenty; more is decisions you will not use.

Reuse steps across materials. Sharing the darkest colour between skin and leather ties the sprite together and costs nothing.

Repairing a sprawled palette

Symptom: validate reports off-palette colours, or the sprite has ninety near-identical browns.

Diagnose:
```
palette op="analyze"
```
This reports off-palette colours in the art, near-duplicate palette entries (ΔE < 3 — the same colour to a viewer), unused slots and the lowest-contrast pair.
Decide the target palette. Either the existing one, minus the near-duplicates, or a fresh one.
Snap the art onto it:
```
recolor op="snap" layer="…"
```
Perceptual (CIELAB) nearest, applied per distinct colour in one pass. The result reports exactly which colour became which and how many pixels moved, so you can see whether a merge was wrong before the user does.
Re-check. palette op="analyze" again, then look op="preview". Merging two colours that were doing different jobs is the risk here; look for a form that has gone flat.

Or start over from the art: palette op="extract" replaces the palette with one quantized from the sprite's own colours (RGB sprites only, maxColors default 16) — useful when the sprite came from a reference image imported at full colour and never had a curated palette to snap onto.

Contrast

Value contrast carries readability, not hue contrast. Check by running recolor op="desaturate" on a copy — if the shapes stop reading in greyscale, the palette's values are too close, and no amount of hue will fix it.

rules://01-palette-and-color, rules://02-shading-and-light, rules://20-color-for-pixel-art, rules://21-limited-and-platform-palettes.

Frequently asked questions

What does the Palette AI skill do?

Why use Palette on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/with-pebbly/aseprite-ai-artist/tree/main/skills/palette. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Palette?

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 Palette?

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

Is the Palette AI skill free?

Yes. It is published on GitHub by with-pebbly 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

To Questionnaire

mattpocock

CommunityPopular

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

Wait What

Stop. That last message did not land: re-pitch it.

Get Search View Results

microsoft

OrganizationPopular

Get the current search results from the Search view in VS Code

React Sync

Build local React changes in the bundle variants consumed by Next.js, sync them into a local Next.js checkout, and test the resulting integration. Use when working on React changes that need…

Palette

Overview