lumina: Skill for Claude Code

.agents/skills/lumina_frontend_design/SKILL.md

lumina_frontend_design is a skill for Claude Code, Codex from zwl467135974/lumina. It costs 57 tokens per session (1,727 once invoked), scanned A, original, Apache-2.0.

A design guide for building Lumina's frontend with Vue 3, Element Plus, CSS, and SCSS. It defines the project's visual style, including colors, spacing, typography, dark themes, and animation.

In plain words
What is it for?
Use it when creating or modifying Vue components, pages, layouts, themes, styles, animations, or visualizations. It applies to frontend changes that affect what users see.
Why use it?
It keeps new or changed screens visually consistent with the rest of the application. It also provides rules for responsive layouts, motion, and preserving design decisions between sessions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is zwl467135974/lumina's own configuration. It tells Claude Code and Codex how to work on lumina itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lumina configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zwl467135974/lumina. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zwl467135974/lumina/master/.agents/skills/lumina_frontend_design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zwl467135974/lumina

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for lumina_frontend_design

README.md
[![agentmods](https://agentmods.dev/badge/skills/zwl467135974/lumina/lumina_frontend_design/github.svg)](https://agentmods.dev/skills/zwl467135974/lumina/lumina_frontend_design)
Your own site
<a href="https://agentmods.dev/skills/zwl467135974/lumina/lumina_frontend_design"><img src="https://agentmods.dev/badge/skills/zwl467135974/lumina/lumina_frontend_design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for lumina_frontend_design

Your own site · 80×15
<a href="https://agentmods.dev/skills/zwl467135974/lumina/lumina_frontend_design"><img src="https://agentmods.dev/badge/skills/zwl467135974/lumina/lumina_frontend_design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,727 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.01727
Opus 5 $0.00028 $0.00864
Sonnet 5 $0.00011 $0.00345
Haiku 4.5 $0.00006 $0.00173

Measured 12d ago against content hash da5c5f5130bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

lumina_frontend_design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/lumina_frontend_design/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lumina Frontend Design Skill

When to Apply

Must Use (always load this skill):

  • Creating or modifying .vue files (template, style, or script affecting UI)
  • Writing or editing SCSS/CSS in src/assets/styles/
  • Building new pages, components, or layouts
  • Theme changes (dark/light, color adjustments)

Recommended:

  • Adding ECharts/visualization configurations
  • Modifying i18n keys that affect UI labels
  • Responsive design adjustments

Skip:

  • Pure backend Java changes
  • API type definitions with no visual impact
  • Test file modifications
  • Build config / package.json changes

Design Philosophy: "Luminous"

Lumina's UI follows the Luminous design language:

  • Brand: Indigo-Violet #7c3aed × Amber #f59e0b — confident, warm, techy
  • Mood: Dark-first, deep space backgrounds with glowing accents
  • Density: Comfortable spacing, breathable cards, clear visual hierarchy
  • Motion: Subtle transitions (150-400ms), staggered entrance animations, no bounce
  • Typography: Outfit (display) / IBM Plex Sans (body) / JetBrains Mono (code)

Self-Evolution Protocol (CRITICAL)

This skill learns from every session. Follow exactly:

Before any UI task:

  1. Read lumina-frontend/DESIGN.md — this is the current design source of truth
  2. Read lumina-frontend/.agents/ui-learnings.md — accumulated discoveries
  3. Summarize 3-5 relevant learnings before proceeding (do not skip this step)

After completing a UI task:

  1. Update DESIGN.md if design tokens, patterns, or principles changed
  2. Append to .agents/ui-learnings.md:
    ## [Date] — [Task type]
    - Observation: [what happened / what worked / what didn't]
    - Action: [what to do or avoid going forward]
    - Confidence: [high/medium/low]
    
  3. Reject vague entries ("be careful with styling" = useless). Be specific.
  4. Prune Learnings.md at ~80 lines — signal density over size.

Workflow (4 Phases)

Phase 1: Audit (read-only)

  • Read lumina-frontend/src/assets/styles/variables.scss — the --lumina-* token system
  • Read lumina-frontend/DESIGN.md — current design state
  • Scan target files for hardcoded colors, non-token spacing, missing CSS vars
  • Report drift (e.g., #fff instead of var(--lumina-bg-card))

Read the full file on GitHub · 136 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 136 lines · 57 tokens per session scan A da5c5f5130bc

Subscribe to this mod's changes

lumina_frontend_design is a skill published in the GitHub repository zwl467135974/lumina (66 stars, last pushed 22d ago), licensed Apache-2.0. It adds 57 tokens to every session and 1,727 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

vue-base-skill

A parent guide for building Vue interface components with shared rules for cards, buttons, labels, and tables. It requires these components to sit inside a base card and use shared CSS design values.

jiushiwon/wg-skills · 108 tokens

ui-ux-design

Generate design systems and implement UX/UI for software products using Astro, Svelte, Tailwind CSS, Material Design 3, and OKLCH color system. Covers style selection, color palettes, typography, layout patterns, accessibility, and frontend code generation. Triggers on "design system", "UI design", "color palette"…

nexus-substrate/nexus-agents · 99 tokens

shadcn-sveltekit-design

Use when building, redesigning, beautifying, or refactoring SvelteKit pages and reusable components with shadcn-svelte, Bits UI, or the shadcn-svelte MCP. Trigger on landing pages, dashboards, marketing sites, app shells, forms, navbars, tables, dialogs, responsive layouts, theming, icon selection, and requests to…

Michael-Obele/shadcn-svelte-mcp · 99 tokens

pandacss-styling

Use when panda CSS zero-runtime styling — token system, patterns, recipes, conditions, JSX styles. Use when working with pandacss styling.

oyi77/1ai-skills · 36 tokens

atai-design-system

Build the front-end for a Newton demo with the Archetype AI Design System — the published, versioned packages (@archetypeai/ds-lib-tokens, @archetypeai/ds-ui-svelte-console, @archetypeai/ds-ui-svelte-labs) and the ds scaffolding CLI (@archetypeai/ds-cli) — instead of hand-rolling tokens, components, fonts, or brand…

archetypeai/agent-skills · 259 tokens

od-vue-export

Use this plugin when the user wants to hand an accepted Open Design artifact to a Vue 3 project.

wolfenazz/YzPzCode · 0 tokens