Bexa Dashboard logo

Bexa Dashboard

Community
BekhruzTursunboev
bexa-dashboard

Data-dense dashboard and admin panel design skill for AI agents. Enforces information hierarchy, data visualization clarity, high-density layouts, and professional SaaS-grade UI patterns.

Overview

PublisherBekhruzTursunboev
RepositoryBexa-professional-frontend-design-skills-for-ai-agents
Skill namebexa-dashboard
Stars
9
Forks
2
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Bexa Dashboard 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/BekhruzTursunboev/Bexa-professional-frontend-design-skills-for-ai-agents/tree/main/skills/bexa-dashboard
  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/BekhruzTursunboev/Bexa-professional-frontend-design-skills-for-ai-agents.git /tmp/Bexa-professional-frontend-design-skills-for-ai-agents
mkdir -p .claude/skills
cp -r /tmp/Bexa-professional-frontend-design-skills-for-ai-agents/skills/bexa-dashboard .claude/skills/bexa-dashboard
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bexa Dashboard 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 Bexa Dashboard 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 Bexa Dashboard 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.

FORGE DASHBOARD — Data-Dense SaaS Design Skill

Dashboards fail in two ways: too much clutter, or too little clarity. This skill enforces the third path: information architecture that makes data readable at a glance.


DIAL CONFIGURATION

DATA_DENSITY:     8   (1=Airy metrics / 10=Cockpit-level data saturation)
VISUAL_CLARITY:   8   (1=Decorative charts / 10=Precision data tables)
INTERACTION_DEPTH:6   (1=Static view / 10=Drill-down, filter, real-time)

SECTION 1 — DASHBOARD IDENTITY RULES

Typography for Data UIs

  • Display font: Satoshi or Geist. NEVER serif on dashboards.
  • Numeric data: ALWAYS font-mono (Geist Mono or JetBrains Mono).
  • Label text: 0.6875rem uppercase, letter-spacing: 0.1em, muted color.
  • Table data: 0.875rem, regular weight, tabular-nums (font-variant-numeric: tabular-nums).

Color for Data

  • Background: hsl(220 14% 97%) (not pure white — reduces eye strain)
  • Card surface: hsl(0 0% 100%) with 1px solid hsl(220 13% 91%)
  • Positive delta: hsl(158 60% 40%) — no neon green
  • Negative delta: hsl(0 72% 50%) — no neon red
  • Neutral: hsl(220 8% 58%)
  • Chart palette: accent + 4 harmonious HSL rotations (±40° hue steps)

SECTION 2 — LAYOUT ARCHITECTURE

Grid System

  • Dashboard uses CSS Grid sidebar + main layout:
css
.dashboard {
  display: grid;
  grid-template-columns: 240px 1fr;
  grid-template-rows: 56px 1fr;
  min-height: 100dvh;
}
  • Sidebar: fixed width 240px (collapsed: 64px icon-only mode)
  • Header: 56px height, sticky, backdrop-blur-md
  • Content: p-6 padding, max-w-[1600px]

Metric Cards (KPI Row)

  • Use divide-x divide-border or inline border-right — NOT boxed cards
  • Each metric: label + large number + delta badge + sparkline
  • Numbers: clamp(1.5rem, 2.5vw, 2.25rem), font-mono, font-bold
  • Delta badge: ±X% with directional arrow icon — colored accordingly

Card Usage Rules

  • Cards ONLY when elevation communicates hierarchy (modals, overlays, floating panels)
  • At DATA_DENSITY > 6: separate sections with border-t or divide-y, NOT cards
  • When cards are used: rounded-xl, p-6, diffusion shadow (0 4px 24px -4px hsl(220 20% 8% / 0.06))

SECTION 3 — DATA VISUALIZATION STANDARDS

Chart Library

Check package.json for recharts, nivo, or @tremor/react. Use whichever is installed. If none: install recharts as default (npm install recharts).

Chart Anti-Patterns (BANNED)

  • 3D charts of any kind
  • Pie charts with > 5 segments (use a bar chart instead)
  • Charts without axis labels or tooltips
  • Charts with default library colors (always remap to project palette)
  • Missing loading/empty states for charts

Chart Skeleton

Every chart must have a shimmer skeleton matching its bounding box:

jsx
// Shimmer skeleton for charts
<div className="h-[200px] rounded-lg bg-surface-2 animate-pulse" />

Table Standards

  • Sticky header row
  • Row hover: bg-surface-2 transition
  • Sortable columns: arrow icon that rotates on sort direction change
  • Pagination: < 1 2 3 ... 14 > compact style
  • Empty table: centered illustration + "No results match your filters" + Clear filters CTA
  • Loading: skeleton rows matching column count

SECTION 4 — SIDEBAR NAVIGATION

Structure

[Logo / Brand]
─────────────
[Primary Nav Group]
  Home
  Analytics
  Projects
  Customers
─────────────
[Secondary Nav Group]
  Settings
  Help
─────────────
[User Avatar + Name]
[Logout]

Behavior

  • Active state: accent color left border + accent-dim background fill
  • Hover: bg-surface-2 transition 150ms
  • Collapsed mode (icon-only): tooltip on hover showing label
  • Mobile: off-canvas drawer, AnimatePresence slide-in from left
  • Keyboard navigation: full arrow-key + Enter support

SECTION 5 — INTERACTION PATTERNS

Filters & Search

  • Global search: ⌘K command palette (not inline search bar)
  • Table filters: popover with checkbox groups, date ranges
  • Active filters: badge row below search with × to remove each
  • Filter state: persist in URL params (?status=active&sort=asc)

Real-Time Updates (when INTERACTION_DEPTH >= 7)

  • Websocket data: use optimistic updates — update UI before server confirms
  • New row animation: slide-in from top with AnimatePresence
  • Metric updates: number transition animation (useMotionValue counter)
  • Status indicators: CSS keyframe pulse (@keyframes ping)

Drill-Down Flow

  • Table row click → slide-in detail panel (not new page) with framer-motion layout
  • Back navigation: breadcrumb trail always visible
  • URL updates on drill-down (deep-linkable)

SECTION 6 — QUALITY GATE (DASHBOARD SPECIFIC)

  • Is font-mono used for ALL numeric data?
  • Are charts remapped to the project color palette?
  • Are all charts/tables showing loading, empty, AND error states?
  • Is the sidebar keyboard-navigable?
  • Does the layout use CSS Grid for sidebar+main (not flexbox hacks)?
  • Are KPI metrics separated by borders (not individual cards at density > 6)?
  • Is global search available via keyboard shortcut?
  • Are positive/negative deltas using calibrated (non-neon) colors?

Frequently asked questions

What does the Bexa Dashboard AI skill do?

Data-dense dashboard and admin panel design skill for AI agents. Enforces information hierarchy, data visualization clarity, high-density layouts, and professional SaaS-grade UI patterns.

Why use Bexa Dashboard on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/BekhruzTursunboev/Bexa-professional-frontend-design-skills-for-ai-agents/tree/main/skills/bexa-dashboard. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Bexa Dashboard?

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 Bexa Dashboard?

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

Is the Bexa Dashboard AI skill free?

Yes. It is published on GitHub by BekhruzTursunboev 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 👇