Brief

Organization

with-pebbly

brief

Turn a vague pixel-art request into a written brief — size, palette, view, light, outline style — and confirm it with the user before any pixel is drawn. Use when the request is open-ended ("make me a knight") rather than a specific edit.

Overview

Publisher	with-pebbly
Repository	`aseprite-ai-artist`
Skill name	`brief`
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 Brief 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/brief
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/brief .claude/skills/brief

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

Use it in TypingMind

Enable Brief 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 Brief 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 Brief 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.

Plan a sprite before drawing it

A request like "draw me a knight sprite" contains none of the decisions that determine whether the result is usable. Guessing them and drawing anyway wastes the user's time and yours. Five questions, one answer, then draw.

What you need to know

Decision	Why it cannot be deferred	Reasonable default
Canvas size	Determines how much can be shown at all	32×32 for a character
Palette	Choosing it later means repainting	PICO-8 (16 colours)
View	Side-on, top-down and 3⁄4 are different drawings	3⁄4
Light direction	Must be fixed before any shading	Upper-left
Outline	Changes every edge in the sprite	Selective, dark-coloured
Destination	A game engine wants tags and a sheet	Ask

Procedure

preflight. If not ready, stop and tell the user — nothing below works without a live Aseprite.
Read what already exists. If a sprite is open, sprite_info it. The user's existing canvas size and palette usually answer half the questions, and matching an existing project's style is almost always what they want.
Draft the brief. Fill the table above from what the user said plus the defaults. Do not ask about things you can reasonably infer — "a Game Boy style knight" has already told you the palette and the size range.
Put it to the user in one message, as decisions rather than questions:

32×32, PICO-8 palette, 3⁄4 view, light from upper-left, selective dark outline. Knight in plate with a sword, facing camera. Say if any of that is wrong — otherwise I'll start.

One round trip, not five. If they said nothing about a detail, they probably do not care about it.

When the request is something new — a character, a prop, an animation — aseprite:concept follows, and its offer goes in this same message: the decisions above, then the image-model prompt in one code block, then the choice between sending references and continuing without. The user answers once. If they correct a decision, fix the prompt to match before they copy it.
Ask only what genuinely blocks you. If the sprite is for a specific game and you do not know its tile size, that one is worth asking. Light direction is not.
Record the brief in your working notes and hold to it. Every later decision either follows from the brief or is a mistake.

Then

aseprite:concept for anything drawn from scratch — its offer is already in the message above. Then aseprite:new to create the document, or aseprite:draw if a suitable sprite is already open.

rules://00-core-principles for what the sizes buy you. rules://03-silhouette-and-form for view and proportion. rules://30-proportions-by-size and rules://14-readability-and-scale for what each canvas size can hold; rules://90-platform-styles when the user names a console or era.

Frequently asked questions

What does the Brief AI skill do?

Why use Brief on TypingMind?

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

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

Which AI models can use Brief?

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 Brief?

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

Is the Brief 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

Frontend Slides

affaan-m

CommunityPopular

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a…

Plan Canvas

Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or…

Improve Codebase Architecture

mattpocock

CommunityPopular

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Grilling

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

Brief

Overview