Agent skill

Frontend Design

by overmind-core in overmind-core/overmind

Overmind Console design system — semantic tokens, shared primitives, geometry and icons, the border-contrast floor, the duplicated table implementations, and the verification scripts.

AGPL-3.0Auto-check passedFrontend & Design

Install Frontend Design

skills CLI
$ npx skills add overmind-core/overmind --skill frontend-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install overmind-core/overmind frontend-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/overmind-core/overmind.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/frontend-design .claude/skills/frontend-design && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
frontend-design
GitHub stars
597
Token cost
~1.8k tokens
SKILL.md length
851 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Overmind Console design system — semantic tokens, shared primitives, geometry and icons, the border-contrast floor, the duplicated table implementations, and the verification scripts.

  • Works in 2 steps: src/components/ui/data-table.tsx — the… → src/components/datasets/notebook/rows-gri…
  • Changing frontend UI
  • SKILL.md covers Color — semantic tokens only, Border contrast — hard…, Shared primitives — use them,… and Geometry, type, icons, plus 3 more sections
  • Calls bun and bunx; needs PIXELARTICONS_LICENSE_KEY

What it does

Frontend Design is an agent skill from overmind-core/overmind. Overmind Console design system — semantic tokens, shared primitives, geometry and icons, the border-contrast floor, the duplicated table implementations, and the verification scripts. Use when writing or changing frontend UI, styles, tables, or component markup.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Frontend & Design, covering Frontend development and Design systems. The repository describes itself as: The platform for continuously improving AI agents. The licence is AGPL-3.0.

When your agent uses it

  • Changing frontend UI
  • Component markup

Example prompts

  • “/frontend-design”

Requirements

  • A credential in PIXELARTICONS_LICENSE_KEY

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. src/components/ui/data-table.tsx — the shared TanStack (Traces, Sessions, Runs, Datasets, Experiments, Billing)
  2. src/components/datasets/notebook/rows-grid.tsx — the paged rows grid every dataset table (source, cell output, product) renders through

What it can do on your machine

Read from SKILL.md and the folder at commit 3dec73c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • bun
    • bunx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use bunx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • PIXELARTICONS_LICENSE_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Frontend Design loads about 1.8k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 851 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from overmind-core/overmind at commit 3dec73c, republished under its AGPL-3.0 licence (© overmind-core). 851 words, ~1,847 tokens.

Download SKILL.mdSave it as .claude/skills/frontend-design/SKILL.md (or your agent's skills folder).
name
frontend-design
description
Overmind Console design system — semantic tokens, shared primitives, geometry and icons, the border-contrast floor, the duplicated table implementations, and the verification scripts. Use when writing or changing frontend UI, styles, tables, or component markup.

Frontend design conventions

The Console is "a quiet workshop for agent improvement" — warm minimalism, copper/gold brand, NeueBit (pixel, display + labels) and PP Neue Montreal (body), small radii, no shadows. Keep it; don't drift toward default Tailwind.

The token spec is the root DESIGN.md — extend its values, don't restructure it. Tokens are declared in frontend/src/styles.css under @theme inline.

Color — semantic tokens only

  • Never raw Tailwind palette utilities (bg-green-500, text-blue-600, border-amber-400) or hex in class strings (bg-[#1c1917]).
  • Status → the four semantic tokens as a tint triplet. Tokens flip per theme, so no dark: variants: border-success/40 bg-success/10 text-success. Meanings: success = passed/healthy/connected/completed; warning = review/degraded/stale; info = running/pending/queued/training; destructive = failed/error/cancelled. Prefer the components — <Badge variant="success|warning|info|error|neutral"> or <StatusBadge status={domainStatus(state)}> (lib/job-status.tsx, lib/colors.ts).
  • Categorical — a fixed set of entity types, not status → text-cat-1 … text-cat-6 / bg-cat-1/10. Assign a stable slot per type.
  • Login / onboarding, the always-dark cinematic surfaces → the named --auth-* tokens (bg-auth-panel, border-auth-border, text-auth-text-dim, text-auth-accent, …), never inline hex.
  • Neutrals → bg-background/card/muted, text-foreground/muted-foreground, border-border. Titles use text-foreground, never text-black dark:text-white.

Border contrast — hard constraint

--border at full strength is only ~1.3:1 against a card; the visibility floor in scripts/check-contrast.mjs is 1.2. The sanctioned ramp:

  • outline = bare border-border
  • divider = border-border/70
  • faint = border-border/60

Anything below /60 is invisible. Never lower a border opacity without running bun run check:contrast -- --all and reading the border rows.

Shared primitives — use them, don't hand-roll

  • A page title is <PageHeader title description count actions icon leading/>. Never a raw <h1>.
  • A page scaffold is <PageShell variant="scroll|full" header/>.
  • Loading is <Spinner size/> inline (buttons) or <LoadingState label fullPage/> for a region; Skeleton when the layout is known on first paint. Never a raw animate-spin or a "Loading…" text block.
  • An empty state is <EmptyState icon title description action size/>.
  • A titled card is <SectionCard title …>; plain <Card> otherwise. Don't hand-roll rounded-lg border surfaces.
  • A destructive confirm is <ConfirmDialog destructive onConfirm/>. Never window.confirm. Dialog Cancel is always variant="secondary" (what AlertDialogCancel renders).
  • Feedback: sonner toast = transient async result; Alert = persistent inline notice; DismissibleAlert = in-dialog mutation error.
  • Model choices use ModelOptionLabel: provider logo, model name, then separate metadata. Use it in both dropdown rows and selected values, including judge, benchmark, comparison and filter selectors. Keep fit/cost/size annotations and selection rules; model IDs remain the stored values. ModelProviderChip is for read-only badges, not dropdown rows.

Geometry, type, icons

  • No box-shadows — every --shadow-* is none, so shadow-* utilities are dead no-ops. Depth = surface layering + 1px borders.
  • Radii: rounded-sm for interactive primitives, rounded-md for containers. rounded-lg/xl/2xl/3xl are off-system.
  • Headings use font-display (NeueBit, unweighted). font-mono is the loaded system stack — Fira Code is not shipped, don't reference it.
  • Icons: always the central registry — import { Icon } from "@/components/ui/icons" → <Icon.name className="size-4" />. The glyphs are pixelarticons paths vendored into ui/icons/glyphs.ts (24×24 grid, 2px inset, currentColor); never import that module or lucide-react in app code; both fail check:design. One concept = one glyph (Icon.delete = trash, Icon.close/Icon.failed = the "X"). Missing a glyph? Add name: glyph("<svg-name>") to ui/icons/index.ts, the only file that may read the table, then bun run icons:vendor with PIXELARTICONS_LICENSE_KEY set (or --source <svg dir> of an unlocked package) — typecheck fails until the table is regenerated. Removing one is the reverse. There is no icon package to install. Sizes: size-4 in buttons, size-[17px] in nav, size-3 for dense chips.
Show full SKILL.md (323 more words)Show less

Two duplicated table implementations

A table fix applied to one codepath silently misses the other:

  1. src/components/ui/data-table.tsx — the shared TanStack <DataTable> (Traces, Sessions, Runs, Datasets, Experiments, Billing)
  2. src/components/datasets/notebook/rows-grid.tsx — the paged rows grid every dataset table (source, cell output, product) renders through

Sort headers are in components/ui/sortable-header.tsx for hand-built tables and inline inside data-table.tsx for the shared one — check both before declaring a header fix done.

Eval results align model variants by the generated client's rowIndex, including zero. Trace-filter samples use sourceTraceId; samples with neither keep their own identity. Use components/evaluations/sample-index.ts for table and detail lookups so unrelated outputs never collapse or stand in for another model's missing response.

The eval datapoint popup selects one model at a time and shows its input beside its generated output, grading reference, and evaluator reasoning. SampleInput consumes the generated EvalSampleIO contract: captured initial runner requests include system prompts and tools; historical dataset inputs explicitly say the exact request was not captured. Never label a combined trajectory as input or an extracted statistical prediction as the model's full output.

Trajectory model-call cards use ModelProviderChip as their title and a three-line system-prompt preview that opens in a dialog. Mode-specific model/prompt context requires an exact step-anchor match; unbound or shared calls show only context common to their candidates. Never borrow a conflicting worker prompt. Excerpts stay labelled as excerpts; missing capture has no expand control.

App shell

The left sidebar logic in src/routes/_auth.tsx and src/components/ui/sidebar.tsx is owned separately — pages adapt to the native in-flow sidebar. Don't add routes to focus-mode patterns or modify shell logic without explicit approval.

Tooling

  • Package manager is Bun (bun add, bunx shadcn@latest add …) — never pnpm/npm/yarn. New shadcn components get adapted to the token system after generation.
  • Biome must not format assets. .svg is excluded in biome.json — keep it excluded and never run biome … --write over **/*.svg (2.5.x sorts attributes and corrupted a logo's XML prolog).
  • Verify every UI change, in both light and dark:
bash
cd frontend
bun run typecheck && bun run lint
bun run check:all        # check:design + check:contrast + check:controls

© overmind-core, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/frontend-design of overmind-core/overmind.

Open the folder on GitHubat commit 3dec73c

Compare with similar skills

Frontend Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Frontend Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Frontend Design this skillovermind-core/overmind597—~1.8kAutomated safety check: PassAGPL-3.0
Design StyleCastor6/tactus3761 repos~2.1kAutomated safety check: PassApache-2.0
Superdesignsuperdesigndev/superdesign-skill630—~4.1kAutomated safety check: PassMIT
UI Design Braincarmahhawwari/ui-design-brain893—~2.1kAutomated safety check: PassMIT
Frontend Design Routercode-yeongyu/oh-my-openagent70k—~5.3kAutomated safety check: PassCustom licence
Project-Native Component Builderkostja94/bricks199—~965Automated safety check: PassMIT

Similar skills

  • Design Style

    Castor6/tactus

    A skill your agent uses whenever the user asks to build, create, design, develop, improve, or style any frontend interface or visual element.

    376 GitHub starsUsed in 1 repo~2.1k tokens
    Frontend & DesignAuto-check passed
  • Superdesign

    superdesigndev/superdesign-skill

    Design or redesign frontend UI, presentations, and graphics on the Superdesign canvas with a choice of leading AI models.

    630 GitHub stars~4.1k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • UI Design Brain

    carmahhawwari/ui-design-brain

    Generate production-grade UI using real component patterns and best practices from 60+ documented interface components.

    893 GitHub stars~2.1k tokensUpdated 7 mo ago
    Frontend & DesignAuto-check passed
  • Frontend Design Router

    code-yeongyu/oh-my-openagent

    Routes frontend and UI work through design reference rulesets, with a design-system gate plus layout and print guidance, before any UI code is written.

    70k GitHub stars~5.3k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Builds new interface components inside an existing project, reusing its design system, stack and conventions instead of producing isolated demo UI.

    199 GitHub stars~965 tokensUpdated 13 days ago
    Frontend & DesignAuto-check passed
  • Frontend Design

    udecode/plate

    Build web interfaces with genuine design quality, not AI slop.

    17k GitHub stars~3.6k tokensUpdated today
    Frontend & DesignAuto-check passed

More from overmind-core/overmind

All 20 skills in this repo
  • API Endpoints

    overmind-core/overmind

    End-to-end workflow for adding or changing a backend API endpoint — which module the serializer and view belong in, URL registration, OpenAPI client regeneration, and typed consumption from the…

    597 GitHub stars~830 tokensUpdated today
    Auto-check: notes
  • Finetuning Model Onboarding

    overmind-core/overmind

    Rules for adding a new model or model family to the finetuning pipeline, or changing finetuning behavior for an existing one — engine-agnostic customization via family hooks instead of if/else in…

    597 GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • MCP

    overmind-core/overmind

    End-to-end workflow for adding or changing Overmind MCP tools, resources, prompts, authentication, or result contracts — server layers, catalog registration, MCP-impact classification, and required…

    597 GitHub stars~4.3k tokensUpdated today
    Auto-check passed
  • PR Etiquette

    overmind-core/overmind

    How to open a complete pull request on overmind-core/overmind — the CI gates, the cross-cutting surfaces a change must carry with it (MCP, blast radius, the docs repo), gh pr edit being broken here…

    597 GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Seed Demo Data

    overmind-core/overmind

    Run or modify the seeddemo management command (the one-project Support Copilot demo) without breaking the beat-safety invariants that keep celery workers from re-driving seeded rows.

    597 GitHub stars~973 tokensUpdated today
    Auto-check passed
  • Overmind Agent

    overmind-core/overmind

    Inspect an Overmind project's agent map, capabilities, behaviour contracts, repository provenance and evaluation coverage.

    597 GitHub stars~797 tokensUpdated today
    Auto-check passed

Questions about Frontend Design

What does Frontend Design do?

Overmind Console design system — semantic tokens, shared primitives, geometry and icons, the border-contrast floor, the duplicated table implementations, and the verification scripts. Frontend Design is an agent skill from overmind-core/overmind. Overmind Console design system — semantic tokens, shared primitives, geometry and icons, the border-contrast floor, the duplicated table implementations, and the verification scripts.

When should I use Frontend Design?

Frontend Design fits situations like: changing frontend UI; component markup.

How do I install Frontend Design in Claude Code?

Run `npx skills add overmind-core/overmind --skill frontend-design -a claude-code`. Or copy the skill folder (.agents/skills/frontend-design in overmind-core/overmind) into .claude/skills/frontend-design in your project. Claude Code loads it when a task matches its description.

How do I install Frontend Design in Codex?

Run `npx skills add overmind-core/overmind --skill frontend-design -a codex`. Or copy the skill folder (.agents/skills/frontend-design in overmind-core/overmind) into .agents/skills/frontend-design in your project. Codex loads it when a task matches its description.

Can I use Frontend Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add overmind-core/overmind --skill frontend-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/frontend-design, .gemini/skills/frontend-design, .github/skills/frontend-design and .opencode/skills/frontend-design in your project.

What does Frontend Design need to run?

Going by SKILL.md and its folder, Frontend Design needs the command-line tools its instructions call (bun and bunx) and credentials named PIXELARTICONS_LICENSE_KEY. Our summary lists: A credential in PIXELARTICONS_LICENSE_KEY.

Does Frontend Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Frontend Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Frontend Design use?

Frontend Design is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Frontend Design use?

About 1.8k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Frontend Design?

Skills that share tags, products or a category with Frontend Design: Design Style (Castor6/tactus, 376 stars), Superdesign (superdesigndev/superdesign-skill, 630 stars), UI Design Brain (carmahhawwari/ui-design-brain, 893 stars) and Frontend Design Router (code-yeongyu/oh-my-openagent, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Frontend Design?

overmind-core (a GitHub organization) maintains it in overmind-core/overmind, which has 597 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 8, 2026.

Source: overmind-core/overmind on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.