Styleseed logo

Styleseed

Community
bitjaru
styleseed

Build, improve, or inspect UI with StyleSeed. Preserves project design choices and routes setup, layout, tokens, review, rendered verification, and updates through one entry point.

Overview

Publisherbitjaru
Repositorystyleseed
Skill namestyleseed
Stars
991
Forks
93
Bundled files
68
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.

  • 68 bundled files

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

  • Open source

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

Installation

Install the Styleseed 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/bitjaru/styleseed/tree/main/engine/.claude/skills/styleseed
  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/bitjaru/styleseed.git /tmp/styleseed
mkdir -p .claude/skills
cp -r /tmp/styleseed/engine/.claude/skills/styleseed .claude/skills/styleseed
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Styleseed 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 Styleseed 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 Styleseed 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.

StyleSeed

Use the user's goal to choose one first workflow below. This is the only registered core skill; the 22 workflows and their executable dependencies ship inside this directory. Read only the selected workflow, then references needed for that task.

Registry-first artifact boundary

When .styleseed/project.json and .styleseed/artifacts/index.json exist, resolve the requested artifact first. Read its .styleseed/bundles/<artifact-id>.md and manifest. A partial or invalid registry is an error; never fall back to the global legacy bundle. Legacy projects may use .styleseed/effective-rules.md only when no registry exists.

Before the first workflow in a project/task session, follow the update preflight.

Working contract

  • Preserve approved project design choices. Support expert judgment; a score is not human acceptance.
  • Resolve the current artifact first. For multiple plausible artifacts, ask one bounded clarification question.
  • Never fan out to run every workflow. Choose exactly one first workflow; it may call the required gates.
  • Honor the user's authorized scope. Audit, score, verify, and status requests do not authorize edits. Workflow metadata records the intended tool/scope boundary even though it is not host registration metadata.
  • Paths in workflow files are relative to those files. Resolve installed scripts from this skill's actual directory, never assume a particular agent folder or download a missing sibling skill.
  • In older instructions, /ss-build, $ss-build, and other ss-* names mean the corresponding internal workflow. Read workflows/<name>/WORKFLOW.md; do not invoke an unregistered skill. Users may say StyleSeed build, $styleseed build, or the old workflow name in natural language.
  • Learning is an optional extension, not part of the core install. Only for explicit learning capture, use separately installed ss-learn; if absent, report that dependency and never auto-install it.

Choose exactly one first workflow

RequestRead
Build or redesign a screen, page, or componentbuild
First setup or missing design locksetup
Explore creative directions; direction not yet selectedstudio
Use screenshot, URL, Figma export, or existing UI as a referencereference
What is wrong with this screen; UX critiqueaudit
Review implementation against project design rulesreview
Score implementation or run code/evidence gatesscore
Inspect rendered output, screenshot, or spacing in pixelsverify
Change spacing/density or another single design axisdial
Apply an aesthetic profilerestyle
Brand color, semantic palette, or design tokenstokens
Named animation or motion treatmentmotion
Specifically scaffold a pagepage
Specifically generate a reusable componentcomponent
Compose existing primitives into a UI patternpattern
Accessibility audit and requested fixesa11y
Quick design lintlint
Navigation and user flowsflow
UX microcopycopy
Loading, empty, success, or error statesfeedback
Update installation or consolidate old skill entriesupdate
Compile rules, inspect local install/bundle/evidence healthresolve

For status-only requests use resolve's read-only scripts/styleseed-doctor.mjs; do not update, recompile, or visually inspect instead. For vague requests infer the first step from project state and the user's goal; ask only when an unresolved choice materially changes the work.

Bundled files

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

and 8 more files.

Frequently asked questions

What does the Styleseed AI skill do?

Build, improve, or inspect UI with StyleSeed. Preserves project design choices and routes setup, layout, tokens, review, rendered verification, and updates through one entry point.

Why use Styleseed on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bitjaru/styleseed/tree/main/engine/.claude/skills/styleseed. 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 Styleseed?

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 Styleseed?

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

Is the Styleseed AI skill free?

Yes. It is published on GitHub by bitjaru 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 👇