Bricks logo

Bricks

Community
wpgaurav
bricks

Author Bricks Builder (WordPress) layouts, templates, and full designs as paste-ready JSON. Use for any Bricks task — sections, pages, headers/footers, query loops, ACF/dynamic data, faceted filters, conditions, interactions/animations, popups, WooCommerce templates, custom elements, or hooks. Verified against Bricks 2.3.6 source.

Overview

Publisherwpgaurav
Repositorybricks-skills
Skill namebricks
Stars
143
Forks
22
Bundled files
39
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.

  • 39 bundled files

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

  • Open source

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

Installation

Install the Bricks 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/wpgaurav/bricks-skills/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/wpgaurav/bricks-skills.git \
  .claude/skills/bricks
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bricks 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 Bricks 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 Bricks 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.

Bricks Builder JSON Authoring

Generate complete Bricks designs as JSON that pastes or imports cleanly on the first try.

Default Deliverable

Produce an actual .json file in the workspace (not inline JSON) unless the user asks otherwise. Use the project's folder convention if one exists; otherwise bricks-json/{type}-{slug}.json. In the final response state: the file path, which JSON format you used, and the validation checks performed.

Workflow

  1. Clarify inputs first — settle two things before writing JSON:
    • rem base — confirm what 1rem equals on the target site (1rem = ? px). Ask the user; default to 16px if unspecified (a html { font-size: 62.5% } reset makes it 10px). All rem/clamp() math and any px→rem conversion from a reference depends on this. → rem base
    • reference URL — if the user provides one (or names asset URLs), fetch it and reference its images/video/SVG/icons by absolute URL. → references/external-assets.md
  2. Pick the format — clipboard paste vs template import vs programmatic insert → references/json-formats.md
  3. Plan structure — semantic section → container → blocks tree; pick elements from the catalog → references/elements.md
  4. Style with settings — every _ style key and its exact value shape → references/style-settings.md
  5. Wire data — dynamic tags, query loops, filters as needed (see routing table)
  6. Validate — checklist below, then deliver

Format Quick Reference

Clipboard (paste into builder) — the default for sections and page content:

json
{
  "content": [ /* flat array of element nodes */ ],
  "source": "bricksCopiedElements",
  "sourceUrl": "https://example.com",
  "version": "2.3.6",
  "globalClasses": [ /* full class objects referenced by _cssGlobalClasses */ ],
  "globalElements": []
}

Element node (every entry in content):

json
{
  "id": "abc123",
  "name": "heading",
  "parent": "xyz789",
  "children": [],
  "settings": {},
  "label": "Optional structure-panel label"
}
  • id: unique 6-char alphanumeric. parent: parent's id, or 0 for root elements.
  • The array is flat — hierarchy lives entirely in parent + children (ids must cross-reference exactly).
  • Root elements are usually section; never nest a section inside anything.

Task Routing

TaskReference
Format selection, clipboard/template/meta storage, programmatic insertreferences/json-formats.md
Element catalog, per-element settings, nestablesreferences/elements.md
Style keys, value shapes (color/typography/border/shadow/gradient/transform), responsive + hover grammarreferences/style-settings.md
Section/grid/flex recipes, cards, overlays, sticky, full designsreferences/layout-recipes.md
Dynamic data tags {post_title}, args, {echo:}references/dynamic-data.md
ACF (incl. repeaters, groups, flexible content), Meta Box, JetEngine, Pods, CMB2references/acf-providers.md
Query loops (hasLoop + query), post/term/user queriesreferences/query-loops.md
Faceted filters, AJAX pagination, load more, infinite scroll, live searchreferences/query-filters.md
Show/hide conditions (_conditions)references/conditions.md
Interactions, animations, scroll triggers (_interactions)references/interactions.md
Popups (templates, triggers, limits, AJAX)references/popups.md
Template types, conditions, import/export, header/footer/archive/404references/templates.md
Components, global classes, global variables, color palettereferences/components-classes.md
Theme styles, breakpoints, CSS generation orderreferences/theme-styles.md
Form element, actions, validationreferences/forms.md
WooCommerce templates and elementsreferences/woocommerce.md
PHP: custom elements with controlsreferences/custom-elements.md
PHP: filters and actionsreferences/hooks.md
External assets from a reference URL (any image/video/SVG/icon, hotlink vs re-host)references/external-assets.md
Asset loading, builder permissionsreferences/assets-permissions.md

Ready-to-paste examples (hero, grids, ACF loops, filtered archive, header/footer, popup…): patterns/ — see patterns/INDEX.md.

Non-Negotiable Rules

  1. Flat tree integrity — every children id exists as a node whose parent points back. No orphans, no duplicates.
  2. Verified value shapes only — colors are objects ({"hex": "#222"} or {"raw": "var(--x)"}), typography keys are CSS property names ("font-size", not fontSize), box-shadow offsets nest under values, gradients use colors: [{color, stop}]. When unsure, check style-settings.md — do not guess shapes.
  3. Responsive grammar — setting:breakpoint:pseudo with colons: _padding:tablet_portrait, _background:hover, _margin:mobile_portrait:hover. Default breakpoint keys: tablet_portrait (991), mobile_landscape (767), mobile_portrait (478). Desktop is the bare key.
  4. Units are strings — "3rem", "100%", "24px". Bare numbers get px appended by Bricks.
  5. Spacing scale discipline — pick a scale (or the site's global variables) and stick to it across the design.
  6. Real structure, no filler — semantic tag settings on sections/blocks (header, nav, article, aside, footer), one h1 per page, descending heading levels.
  7. Global classes ride along — any id listed in an element's _cssGlobalClasses must have its full class object in the top-level globalClasses array.
  8. Don't invent settings keys — only keys documented in the references or found in the Bricks source. Unknown keys are silently ignored and waste the user's trust.
  9. Confirm the rem base before using rem — never assume 1rem = 16px silently. Ask the user; default to 16px only when they don't answer. Convert any px values lifted from a reference using the confirmed base.
  10. Reference external assets by absolute url, never id — when a reference URL or asset URLs are given, resolve every asset to an absolute URL and reference it via the media control's url/external (attachment ids don't resolve cross-site). Respect licensing — don't hotlink copyrighted/brand assets into production. → references/external-assets.md

Validation Checklist (run before delivering)

  • JSON parses (python3 -m json.tool file.json or equivalent)
  • Every parent/children reference resolves; ids unique, 6-char alphanumeric
  • source: "bricksCopiedElements" + version present (clipboard format)
  • Every _cssGlobalClasses id has a matching object in globalClasses
  • Value shapes match style-settings.md (spot-check colors, typography, spacing)
  • Responsive keys use valid breakpoint names
  • Query loops: hasLoop: true + query.objectType present; filters point at a real query element id via filterQueryId
  • Dynamic data tags exist for the stated field provider (e.g. {acf_*} matches the user's field names)

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 Bricks AI skill do?

Author Bricks Builder (WordPress) layouts, templates, and full designs as paste-ready JSON. Use for any Bricks task — sections, pages, headers/footers, query loops, ACF/dynamic data, faceted filters, conditions, interactions/animations, popups, WooCommerce templates, custom elements, or hooks. Verified against Bricks 2.3.6 source.

Why use Bricks on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wpgaurav/bricks-skills/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 Bricks?

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 Bricks?

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

Is the Bricks AI skill free?

It is published on GitHub by wpgaurav. Check the repository for licensing terms. 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 👇