Agent skill

Design Craft

by WrongStack in WrongStack/WrongStack

Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique.

MITAuto-check passedFrontend & Design

Install Design Craft

skills CLI
$ npx skills add WrongStack/WrongStack --skill design-craft -a claude-code

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

GitHub CLI
$ gh skill install WrongStack/WrongStack design-craft --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/WrongStack/WrongStack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/core/skills/design-craft .claude/skills/design-craft && 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
design-craft
GitHub stars
368
Token cost
~2k tokens
SKILL.md length
948 words
Files
7 (incl. references)
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique.

  • Works in 5 steps: Establish structure with representative… → Exercise the main task, keyboard flow… → Inspect the actual rendered surface.… → …
  • Typography/layout work
  • SKILL.md covers Establish the design boundary, Write a useful brief, Make originality come from the… and Build, inspect, correct, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Design Craft is an agent skill from WrongStack/WrongStack. Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique. Use for new screens, landing pages, redesigns, typography/layout work, or UI that feels generic or AI-generated. For small fixes, preserve the existing design without starting a new brief.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/color.md`, `references/composition.md` and `references/copy.md`).

It sits in Frontend & Design, covering Landing pages and Typography. The repository describes itself as: An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, and a browser UI, while you keep your… The licence is MIT.

When your agent uses it

  • Typography/layout work
  • UI that feels generic

Example prompts

  • “/design-craft”

Workflow steps

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

  1. Establish structure with representative content, then type and spacing,
  2. Exercise the main task, keyboard flow and reachable loading, empty, error,
  3. Inspect the actual rendered surface. Test the relevant desktop size, a narrow
  4. Run the design tool with {action:"verify"} when a kit is pinned. Review findings against
  5. Use the design-critique skill to identify the highest-impact visible problems. Fix

What it can do on your machine

Read from SKILL.md and the folder at commit ec76a20. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

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

  • Network

    No URLs in SKILL.md.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Design Craft loads about 2k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 85 tokens; SKILL.md has 948 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

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 WrongStack/WrongStack at commit ec76a20, republished under its MIT licence (© WrongStack). 948 words, ~2,032 tokens.

Download SKILL.mdSave it as .claude/skills/design-craft/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
design-craft
description
Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique. Use for new screens, landing pages, redesigns, typography/layout work, or UI that feels generic or AI-generated. For small fixes, preserve the existing design without starting a new brief.
version
2.0.0
required-capabilities
filesystem.read, filesystem.write
required-tools
design, skill
optional-capabilities
web.research, browser.interact, verification.run

Design Craft — WrongStack

The outcome is an interface suited to this product, its content and its users. Token consistency helps, but cannot establish visual quality. A kit supplies reusable decisions, not a finished composition. Removing gradients or changing three cards to four does not make a design original.

Establish the design boundary

Inspect the relevant screens, components, theme, assets and framework before choosing a direction. Reuse an established system by default. Follow the user's supplied reference or explicit direction. For a small change, match the surrounding interface and check affected states without inventing a new product identity.

For a new screen or substantial redesign, use the design-system skill to resolve the token source: the existing system, or one kit for a new system. Read a supplied reference before claiming to follow it. If it cannot be accessed, state that limitation and distinguish assumptions from observations.

Write a useful brief

Record decisions in .design/brief.md. Design Studio includes a bounded excerpt in subsequent UI requests; keep critical decisions at the top. This directory is local and self-ignored once Design Studio persists a kit. Put decisions the team must share in its normal tracked design docs too.

Use only the fields that affect this task:

markdown
# Design brief — <product / surface>
Audience and primary task: <who needs to do what, under which constraints>
System and scope: <existing tokens/components or selected kit; what is changing>
Content priority: <primary action, essential information, supporting evidence>
Direction: <visual idea tied to this product, and why it supports the task>
References: <inspected artifact / URL / local file and the specific lesson>
Layout and type: <reading order, density, grid, type roles and prose measure>
Color and assets: <semantic roles, actual imagery/data, asset sources>
States and adaptation: <mobile/short viewports, themes, key edge cases>
Avoid: <specific failure modes for this product>
Acceptance: <observable checks, not adjectives such as premium or clean>
Assumptions: <unknown content, data or constraints; clearly labelled>

Do not fabricate three famous references to fill a template. When the prompt is sufficient, state the direction briefly and continue. Ask only when a missing fact changes the product outcome; otherwise use a reversible assumption.

For an open-ended new identity, compare a few directions briefly before choosing one. Distinguish them by layout, content emphasis, typography or interaction, not just palette. Explain why the selected direction fits. When the user asks to choose, present real alternatives; otherwise continue with the best fit. Style vocabulary and kit mappings: load references/directions.md with skill.

Make originality come from the product

Start with its distinctive content or workflow. A dispatch screen can prioritize exceptions and arrival windows; an archive can use dates, captions and source material; a field tool can make offline state and recovery unmistakable. These decisions create identity without decorative tricks.

  • Content first: use representative real text, realistic lengths and useful data. Label demo data. Never invent customer logos, testimonials, usage counts, awards or conversion claims as evidence.
  • Composition: choose hierarchy from reading order and action. Tables, repeated rows and equal product cards often need consistency. Vary layout when content roles differ, not to satisfy an asymmetry quota.
  • Typography: decide display, text, label and numeric roles. A single family can be excellent. Use loaded/licensed fonts available to the project, test fallback and wrapping, and control prose measure without applying it to tables.
  • Color: assign semantic roles and protect the primary action's salience. 60/30/10 is a possible starting point, not an acceptance rule. Links, data categories and status indicators may need many accent uses.
  • Surfaces: grouping must mean something. Use spacing, borders, radii and elevation by role; a border plus shadow can improve separation. Do not wrap every paragraph in a card.
  • Assets: choose imagery that explains the product or establishes its tone. Use available assets or appropriate generation/search tooling when needed; inspect the actual asset, crop, resolution, rights and contrast. Do not fill space with unrelated stock illustrations or present a mockup as a real screenshot.
  • Distinctiveness: express a coherent idea where it helps. A quiet form does not need a signature gimmick; a brand surface may carry a stronger motif.
  • Motion: explain a state change or spatial relationship; respect reduced motion and keep controls usable without animation.

Use skill({ name: "design-craft", resource: "references/<file>.md" }) as needed: composition, typography, color, copy, slop-inventory. These references are diagnostic aids; user intent, accessibility and product context outrank stylistic recipes. A pattern alone is not proof of low quality.

Show full SKILL.md (334 more words)Show less

Build, inspect, correct

  1. Establish structure with representative content, then type and spacing, then color, assets and motion. Preserve semantic markup and working controls.
  2. Exercise the main task, keyboard flow and reachable loading, empty, error, success, disabled and overflow states. Avoid decorative controls that do nothing.
  3. Inspect the actual rendered surface. Test the relevant desktop size, a narrow viewport and a short viewport where dialogs/toolbars may hide actions. Include supported themes, long labels and realistic content volume. For mobile changes, check touch affordances and scrolling; for native stacks use device evidence.
  4. Run the design tool with {action:"verify"} when a kit is pinned. Review findings against the brief and token source. Fix drift; retain justified design choices. Zero findings and a 100% palette score do not establish quality or accessibility.
  5. Use the design-critique skill to identify the highest-impact visible problems. Fix them within the authorized scope, then inspect the affected screens again. Stop when acceptance checks are met, not after arbitrary cosmetic churn.

Make rendered checks concrete:

  • Hierarchy: can the main task and content priority be identified quickly?
  • Product swap: would changing only the logo leave an equally plausible unrelated product? If so, improve domain content or workflow, not decoration.
  • Constraint stress: does the primary action remain reachable with a short viewport, long text, keyboard focus and supported content extremes?
  • Reference fidelity: compare geometry, type, spacing, imagery and colors literally when matching a reference; explain deliberate deviations.

If rendering tools are unavailable, inspect source and state precisely what remains unverified. Do not claim screenshot, contrast, responsive or interaction checks that were not performed. Native theme constants and dynamically generated classes are outside much of the source scanner's coverage.

Handoff

Give the direction and its product rationale, implementation outcome, observed checks with viewport/state or artifact evidence, and material unknowns. For substantial work, keep this concise record in .design/review.md so a later turn can distinguish inspected behavior from pending checks. Keep speculative improvements separate from defects; a prompt or scanner cannot guarantee originality.

© WrongStack, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in packages/core/skills/design-craft of WrongStack/WrongStack.

  • SKILL.md
  • references/color.md
  • references/composition.md
  • references/copy.md
  • references/directions.md
  • references/slop-inventory.md
  • references/typography.md

Open the folder on GitHubat commit ec76a20

Compare with similar skills

Design Craft 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.

Design Craft compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Design Craft this skillWrongStack/WrongStack368—~2kAutomated safety check: PassMIT
Impeccablebestofjs/bestofjs3.1k27 repos~2.6kAutomated safety check: PassMIT
UI UX Pro Maxsaoudi-h/solar-icons18218 repos~11kAutomated safety check: NotesCustom licence
Frontend Designanthropics/skills180k38 repos~2.3kAutomated safety check: PassApache-2.0
UI/UX Design System AdvisorGalaxy-Dawn/claude-scholar5.7k1 repos~1.1kAutomated safety check: PassMIT
Blueprint UIsuperhq-ai/shuru862—~1.9kAutomated safety check: PassApache-2.0

Similar skills

  • Impeccable

    bestofjs/bestofjs

    A skill your agent uses when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a…

    3.1k GitHub starsUsed in 27 repos~2.6k tokens
    Frontend & DesignAuto-check passed
  • UI UX Pro Max

    saoudi-h/solar-icons

    UI/UX design intelligence for web and mobile. An agent skill from saoudi-h/solar-icons.

    182 GitHub starsUsed in 18 repos~11k tokens
    Frontend & DesignAuto-check: notes
  • Frontend Design

    anthropics/skills

    Official

    Pushes the agent toward distinctive visual design for new or reworked UI: a clear aesthetic direction, deliberate typography and choices rooted in the subject.

    180k GitHub starsUsed in 38 repos~2.3k tokens
    Frontend & DesignAuto-check passed
  • UI/UX Design System Advisor

    Galaxy-Dawn/claude-scholar

    Turns a vague UI request into a concrete design system with style, palette, typography and layout guidance from a search script, plus stack-specific implementation advice.

    5.7k GitHub starsUsed in 1 repo~1.1k tokens
    Frontend & DesignAuto-check passed
  • Blueprint UI

    superhq-ai/shuru

    Build landing pages and web UIs using a dark blueprint/wireframe aesthetic with sharp edges, connected sections, dashed outlines, measurement annotations, and technical typography.

    862 GitHub stars~1.9k tokensUpdated 16 days ago
    Frontend & DesignAuto-check passed
  • Gridgeist

    ohmiler/gridgeist

    A skill your agent uses when creating, redesigning, or reviewing web interfaces that need product-specific structure, clear hierarchy, responsive composition, accessible interaction, or relief from…

    115 GitHub stars~2.6k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check passed

More from WrongStack/WrongStack

All 38 skills in this repo
  • Design Critique

    WrongStack/WrongStack

    A skill your agent uses to audit an interface that already exists and say precisely why it looks generated, templated, or unfinished — a scored rubric across composition, typography, color, states…

    368 GitHub stars~3k tokensUpdated today
    Auto-check passed
  • Mailbox Bridge

    WrongStack/WrongStack

    A skill your agent uses when external coding agents (Claude Code, Aider, custom scripts) need to participate in the project's shared WrongStack mailbox, or when a user asks to "expose the mailbox"…

    368 GitHub stars~3.9k tokensUpdated today
    Auto-check passed
  • Multi Agent

    WrongStack/WrongStack

    A skill your agent uses whenever work can be split across multiple AI agents running in parallel, or when orchestrating leader/worker patterns in WrongStack.

    368 GitHub stars~3.6k tokensUpdated today
    Auto-check passed
  • Web Platform Baseline

    WrongStack/WrongStack

    Use this skill before asserting that a CSS, HTML or accessibility capability is available, unavailable, or the right tool — it carries dated, refreshable platform facts and refuses to let stale…

    368 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Wrongstack Mailbox

    WrongStack/WrongStack

    A skill your agent uses when the user wants to communicate with WrongStack's shared project mailbox from outside WrongStack — read messages sent by WrongStack agents, send replies, broadcast to all…

    368 GitHub stars~3.5k tokensUpdated today
    Auto-check passed
  • API Design

    WrongStack/WrongStack

    A skill your agent uses when designing, implementing, or reviewing an HTTP API — endpoints, request and response shapes, errors, pagination, versioning, and authorization.

    368 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Questions about Design Craft

What does Design Craft do?

Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique. Design Craft is an agent skill from WrongStack/WrongStack. Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique.

When should I use Design Craft?

Design Craft fits situations like: typography/layout work; UI that feels generic.

How do I install Design Craft in Claude Code?

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

How do I install Design Craft in Codex?

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

Can I use Design Craft 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 WrongStack/WrongStack --skill design-craft -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/design-craft, .gemini/skills/design-craft, .github/skills/design-craft and .opencode/skills/design-craft in your project.

What does Design Craft need to run?

SKILL.md names no scripts, command-line tools or credentials: Design Craft is instructions for the agent only.

Does Design Craft 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 Design Craft 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 Design Craft use?

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

How many tokens does Design Craft use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.1k tokens, read only when the agent opens those files.

What are the alternatives to Design Craft?

Skills that share tags, products or a category with Design Craft: Impeccable (bestofjs/bestofjs, 3.1k stars), UI UX Pro Max (saoudi-h/solar-icons, 182 stars), Frontend Design (anthropics/skills, 180k stars) and UI/UX Design System Advisor (Galaxy-Dawn/claude-scholar, 5.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Design Craft?

WrongStack (a GitHub organization) maintains it in WrongStack/WrongStack, which has 368 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on October 6, 2026.

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