Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Thalarch Design System

ASecurity

Creates or extracts a semantic visual system for websites and applications. Use before major frontend redesigns, multi-page sites, brand-heavy UI, or when an existing codebase needs its visual language made explicit. Produces a compact design contract covering atmosphere, color roles, typography, spacing, components, layout, motion, responsive behavior, imagery, and anti-patterns without forcing a particular framework or design tool.

2 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsexpressrailsfrontend

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/19/2026

$npx -y skills add LUC4N3X/antigravity-thalarch --skill thalarch-design-system --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Thalarch Design System?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Thalarch Design System
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/luc4n3x-thalarch-design-system/badge)](https://www.skillsdirectory.com/skills/luc4n3x-thalarch-design-system)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: thalarch-design-system
description: >
  Creates or extracts a semantic visual system for websites and applications.
  Use before major frontend redesigns, multi-page sites, brand-heavy UI, or when
  an existing codebase needs its visual language made explicit. Produces a compact
  design contract covering atmosphere, color roles, typography, spacing, components,
  layout, motion, responsive behavior, imagery, and anti-patterns without forcing
  a particular framework or design tool.
---

# Thalarch Design System

A strong site should look like one product, not a sequence of independently
styled sections.

Use this skill to create a **semantic design contract** before implementation or
to reverse-engineer one from an existing frontend.

## 1. Start with product character

Define:

- product/subject;
- audience;
- primary job;
- visual atmosphere;
- density: airy / balanced / dense;
- composition: ordered / asymmetric / expressive;
- motion: restrained / fluid / cinematic;
- one distinctive design idea that belongs to this product.

Avoid design adjectives that could describe any startup.

## 2. Extract before inventing

If an existing product already has UI or brand assets, inspect first:

- theme/tokens;
- CSS variables;
- Tailwind/theme configuration;
- component library;
- typography declarations;
- spacing/radius/shadow patterns;
- icons and imagery;
- screenshots or Figma/Stitch references when available.

Preserve stable identity unless redesign is explicitly requested.

## 2.5 External design-reference atlas

When the project/user does not already provide enough visual direction and external research is
available, use `references/awesome-design-md.md`.

That reference maps `VoltAgent/awesome-design-md` into Thalarch's workflow. The source is valuable
because its analyzed `DESIGN.md` files encode design systems as structured reasoning rather than
surface screenshots.

Use it selectively:

- choose one primary reference by task fit;
- use at most one secondary reference for a clearly distinct quality;
- extract only the relevant atmosphere, hierarchy, palette roles, type character, composition,
  material/depth, imagery treatment, responsive behavior, and guardrails;
- synthesize those qualities into the current project's own design contract;
- never let a famous reference outrank the user's brand or existing project truth.

For raster/image tasks, hand the compact reference capsule to `thalarch-imagegen`; do not dump a
whole external DESIGN.md into the generation prompt.

## 3. Semantic tokens

Define roles, not arbitrary values:

### Color
- canvas / elevated surfaces;
- primary and secondary text;
- muted/supporting content;
- primary action;
- accent;
- borders/dividers;
- success/warning/error/info.

Use exact values in the implementation contract where known, but describe their
visual role too.

### Typography
Define:
- display face/character;
- body face/character;
- scale hierarchy;
- weights;
- line height;
- letter spacing;
- numeral/code treatment when relevant.

Do not default to the same fashionable font stack on every project.

### Geometry
Define:
- spacing rhythm;
- radius philosophy;
- border weight;
- shadow/depth treatment;
- container widths;
- grid/gutter behavior.

## 4. Component behavior

Describe important components semantically:

- navigation;
- buttons/actions;
- cards/containers;
- forms;
- dialogs/sheets;
- lists/tables;
- media blocks;
- domain-specific components.

For each component, define hierarchy and states instead of styling every instance
independently.

## 5. Layout system

Record:

- page frame and max widths;
- grid philosophy;
- whitespace strategy;
- alignment rules;
- section rhythm;
- when asymmetry/overlap is allowed;
- mobile reflow strategy;
- touch-target expectations.

Desktop design must not merely shrink on mobile.

## 6. Motion system

Motion must communicate hierarchy, continuity, or feedback.

Define:
- page-entry behavior;
- hover/focus/press behavior;
- section transitions;
- reduced-motion fallback;
- banned decorative motion.

Prefer a few choreographed moments over dozens of unrelated animations.

## 7. Imagery system

Define what kind of imagery belongs in the product:

- photography / illustration / 3D / abstract / none;
- crop and framing;
- contrast and saturation;
- texture/grain;
- relation to UI surfaces;
- icon/diagram language;
- whether generated imagery is allowed and where.

If generated assets are needed, hand them to `thalarch-imagegen` with this design
contract as the brand reference.

## 8. Anti-pattern contract

Write project-specific bans, such as:

- generic SaaS gradient hero;
- excessive cards-inside-cards;
- every section centered;
- decorative blobs without meaning;
- random glassmorphism;
- uniformly rounded everything;
- interchangeable AI-generated illustrations;
- multiple competing accent colors;
- fake dashboard data or placeholder lorem ipsum in final work.

Do not ban a style merely because it is popular. Ban it when it conflicts with
the product's chosen direction.

## 9. Output

For non-trivial projects, maintain a concise `DESIGN.md` or repository-appropriate
design artifact containing:

1. Product & audience
2. Visual atmosphere
3. Color roles
4. Typography
5. Geometry & spacing
6. Components
7. Layout & responsive rules
8. Motion
9. Imagery
10. Accessibility constraints
11. Anti-patterns
12. Example implementation language

If the repository already uses a design-system document, update that instead of
creating a competing source of truth.

Attribution

LUC4N3XLUC4N3X
View sourceSee grades on GitHubMore from LUC4N3X →
SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills Directory ProSkills Directory

Get any skill into Claude in one click.

Download any skill as a ZIP for Claude.ai, Claude Desktop, or .claude/skills. $9/mo.

See Pro

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1087401 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

697551 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →