Dark Tech

Community

madebymustafa

dark-tech

Genre pack: dark, precise, developer-adjacent minimalism — the Linear/Vercel/Stripe-dark school. Near-black surfaces, one restrained accent, fine hairline borders, compact type, subtle glow only on the accent, dashboard-ready density. Use for developer tools, infra products, AI platforms, and technical audiences. Stack on the design-taste core skill.

Overview

Publisher	madebymustafa
Repository	`design-taste`
Skill name	`dark-tech`
Stars	198
Forks	10
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

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 madebymustafa on GitHub. Read the source before you install it.

Installation

Install the Dark Tech 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/madebymustafa/design-taste/tree/main/skills/dark-tech
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/madebymustafa/design-taste.git /tmp/design-taste
mkdir -p .claude/skills
cp -r /tmp/design-taste/skills/dark-tech .claude/skills/dark-tech

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

Use it in TypingMind

Enable Dark Tech 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 Dark Tech 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 Dark Tech 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.

dark-tech

One identity: a machine you can trust — precise, quiet, fast.

1. PALETTE (Fixed)

Ground: #08090A (near-black). Panels: #0E0F11 and #131417. Hover surfaces: #181A1D.
Ink text: #F7F7F8 (primary), #9CA3AD (secondary), #5C6370 (tertiary/muted).
Borders: rgba(255, 255, 255, 0.08) hairlines. Stronger on interactive: rgba(255, 255, 255, 0.16).
Accent — exactly one: indigo #5E6AD2, violet #7C7CF0, or emerald-safe #34D399 — selected by brand/meaning. Accent used for: links, the single primary button, active states, one data series.
No gradients (flat surfaces only), no colored full-bleed backgrounds. Glow allowed ONLY on the accent: box-shadow: 0 0 0 1px rgba(accent, .35), 0 0 24px rgba(accent, .25) on the primary button.

2. TYPOGRAPHY (Fixed)

Display: neutral grotesk with personality — Space Grotesk, or system sans at 500–600 weight. Sizes clamp(2.2rem, 5vw, 4rem), tracking −0.03em, leading 1.05. Dark tech is restrained: powerful but not shouting.
Body: 14–15px, #9CA3AD secondary for almost everything; pure #F7F7F8 reserved for headings, key values, and interactive labels. Line-height 1.55.
Labels/metadata: monospaced (IBM Plex Mono / ui-monospace), 11–12px, #5C6370, no letterspacing theatrics (0–0.02em). Version numbers, keys, statuses live here.
UI density: 12–14px is normal. This is an instrument console, not a billboard.

3. COMPOSITION (Fixed)

Fine border discipline: every panel, row, and table cell is separated by 1px rgba(255,255,255,0.08) borders. Inner fills are tonal (#0E0F11 / #131417), never white cards on black.
Hero: small caps mono kicker, medium-size headline (max 4rem), sub in secondary, CTA row — primary accent button + ghost button. Optional: a metrics strip or product panel below, bordered.
Data is the hero: metrics, code blocks, terminal snippets, and status tables are aesthetic assets. A bordered panel with mono numbers beats a decorative illustration.
Radius: 6–10px on panels (this is the ONE pack where a bit of radius is correct — machine parts), 4–6px on buttons. Shadows only at hover: 0 4px 20px rgba(0,0,0,0.5).
Pricing: bordered rows or 3-panel grid; featured panel gets a 1px accent border + accent dot/check list.

4. CONTENT TREATMENT

No emoji as icons. Draw icons: 1.5px stroke, rounded caps, 16–20px grid, #9CA3AD at rest, accent at active.
No photography by default. Dark-tech surfaces are better empty: hairlines, mono labels, and metrics.
Status language: status: healthy, v2.4.1, 99.99% SLA — product authenticity beats marketing claims.
CTA text: concrete ("Deploy now", "Run benchmark"), never "Get started today!!".

5. MOTION (Precise)

Durations 120–240ms. Easing cubic-bezier(0.4, 0, 0.2, 1) (Material-style) or ease-out hovers.
Hover: surface tone shift (#0E0F11 → #131417) + border brighten. Border/glow transitions only, 150ms.
One allowed flourish: a slow ambient status pulse on one accent element (like a "live" dot), 2–4s cycle, opacity only.
Respect prefers-reduced-motion: everything off.

6. CHECKLIST (Fail the page if…)

Any white or light background surfaces (main background must be near-black).
More than one accent color in use.
Any gradient fill.
Headline above 4rem or in a display serif.
Body text in pure white for normal paragraphs.
Rounded corners above 10px on panels or above 6px on buttons.
Emoji icons or bright marketing photography.
Any section that could not exist in a developer tool.

Frequently asked questions

What does the Dark Tech AI skill do?

Why use Dark Tech on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/madebymustafa/design-taste/tree/main/skills/dark-tech. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dark Tech?

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 Dark Tech?

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

Is the Dark Tech AI skill free?

Yes. It is published on GitHub by madebymustafa 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

Plan Canvas

affaan-m

CommunityPopular

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.

Teach

Teach the user a new skill or concept, within this workspace.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

dark-tech

1. PALETTE (Fixed)

2. TYPOGRAPHY (Fixed)

3. COMPOSITION (Fixed)

4. CONTENT TREATMENT

5. MOTION (Precise)

6. CHECKLIST (Fail the page if…)

Frequently asked questions

Related AI Skills

Set up your own AI workspace now