Component Builder

Community

kostja94

component-builder

Build new interface components and bounded composition patterns inside an existing project. Use for named components, interface blocks, and workspaces. Preserve the target project's design system and stack; for a complete new page with page-level structure and multiple sections, use Pagina page-builder instead. Do not use to audit or reconstruct an existing component, plan a whole product or website, or handle purely editorial copy requests.

Overview

Publisher	kostja94
Repository	`bricks`
Skill name	`component-builder`
Stars	191
Forks	0
Bundled files	37
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.
37 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by kostja94 on GitHub. Read the source before you install it.

Installation

Install the Component Builder 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/kostja94/bricks/tree/main/skills/component-builder
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/kostja94/bricks.git /tmp/bricks
mkdir -p .claude/skills
cp -r /tmp/bricks/skills/component-builder .claude/skills/component-builder

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

Use it in TypingMind

Enable Component Builder 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 Component Builder 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 Component Builder 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.

Component Builder

Create new components that belong in the target product instead of producing isolated demo UI.

Start With The Project

Inspect the relevant page, nearby components, design tokens, dependencies, content model, responsive conventions, and tests before choosing an implementation. Reuse established primitives and icon libraries. Do not replace an existing design system merely because another library is familiar.

Identify:

the requested component concept and user task;
the surface and interface type;
where the new component belongs and which existing primitives it may reuse;
the component's real content and states;
the target stack and existing ownership boundary.

For a page composition, define the page's job and reuse child components from the catalog. Do not turn a page pattern into a second maintenance source for every component it contains.

Load Only Relevant Guidance

Read references/workflow.md for construction work. Read references/foundational-controls.md when the request involves Button, Link, Input, Select, Form, or another foundational control and references/quality-gates.md before final verification.

Read references/pagina.md when the request may be a complete page rather than a bounded component.

Find the component ID in ../../catalog/components.json, then read only its referenced component file. If the requested concept is absent, use the shared workflow, state the inferred canonical name in the result, and do not invent a permanent catalog entry unless the task includes repository maintenance.

Build

Define the semantic responsibility and boundary before styling.
Choose a variant from context and content, not fashion.
Preserve project conventions and integrate real content or data contracts.
Implement expected states, responsive behavior, keyboard behavior, and failure handling.
Verify the component in its actual page context. A component that only looks correct in isolation is incomplete.

Boundaries

One component concept has one maintained reference. Role, placement, visual variant, and runtime state do not create new catalog entries.
Established independent terminology and discovery intent may justify separate entries that share a model, as with Grid, List, and Masonry.
A component reference is guidance, not a fixed code template.
Bounded composition patterns may coordinate catalog components. Complete page construction belongs to Pagina; whole-site information architecture and product planning remain outside both component construction and this skill.
Stop and report the scope mismatch when the named component already exists and the request is primarily an audit, optimization, or reconstruction.
Do not add dependencies without a concrete implementation benefit.
Do not claim compliance, performance, or conversion outcomes that were not tested.
Use proven domain libraries when the component depends on complex editors, tables, charts, calendars, accessibility primitives, or agent runtimes.

Completion

Report what changed, which project conventions were reused, how the component was verified, and any material constraint that remains.

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 Component Builder AI skill do?

Why use Component Builder on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kostja94/bricks/tree/main/skills/component-builder. 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 Component Builder?

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 Component Builder?

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

Is the Component Builder AI skill free?

Yes. It is published on GitHub by kostja94 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

Crosspost

affaan-m

CommunityPopular

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user…

Deep Research

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any…

Documentation Lookup

Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React,…

Everything Claude Code

affaan-m

CommunityPopular

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Component Builder

Start With The Project

Load Only Relevant Guidance

Build

Boundaries

Completion

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now