ui-craft icon

ui-craft

eduardo-calvo/ui-craft · v1.0.0 · Agent Skills

by Eduardo CalvoAwesome AI Plugins

Design engineering skill collection for AI coding agents with slash commands, review agents, and MCP quality gates

Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is ui-craft a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • Agent Skills
  • MCP
  • Claude Code
  • Cursor
  • 246 skills
  • 1 MCP server

Before you install

Sign-in
Not declared
Declared access
Not declared
License
MIT

Check before relying on it

  • Some security checks did not finish: Cisco skill scan and Cisco MCP scan. See the evidence
  • 1 medium finding from the scan. See the evidence
  • The publisher has not verified ownership on HOL.

What is ui-craft?

ui-craft is a published agent skills plugin for AI coding agents that works with Agent Skills, MCP, Claude Code and Cursor, developed by Eduardo Calvo and distributed through the HOL AI plugin registry. Design engineering skill collection for AI coding agents with slash commands, review agents, and MCP quality gates.

Canonical slug
eduardo-calvo/ui-craft
Version
v1.0.0 · updated Nov 16, 2026

Registry snapshot

Support the project
GitHub Sponsors
Owner verification
Not verified
Marketplace source
.claude-plugin/marketplace.json
Scanner
HOL plugin scanner
Security result
Partial scan
Digest verified
Yes
100 bundled skillsRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

79

HOL Trust Score

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
100/100
Maintenance
100/100
MCP server setup
100/100
Plugin Security
91/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
.
Source repo
https://github.com/educlopez/ui-craft
Source commit
c1e556ed843b…
Publisher verified
No
Owner verified
Not owner verified
Agent Plugins 1.0
Not detected

Continuous scanner CI not detected

This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.

Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.

README badge not detected

Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.

Partial scan
Security result
91
Score from finished checks
0
High findings

Some checks did not finish: Cisco skill scan and Cisco MCP scan. No blocking issue was found in the checks that did finish, but this is not a passed scan.

Provider
codex-plugin-scanner
Grade
A · Excellent
Version
3.24.2
codex:hol-plugin-scanner-tdplW4 / cisco-skill-scanner: failedcodex:hol-plugin-scanner-tdplW4 / cisco-mcp-scanner: unavailable

[claude:.] Claude Plugin

13/18

5 checks

[claude:.] Security

20/20

6 checks

[claude:.] Operational Security

6/6

5 checks

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

24/31

9 checks

[codex:.] Security

20/20

9 checks

[codex:.] Operational Security

6/6

5 checks

[codex:.] Best Practices

9/12

5 checks

[codex:.] Marketplace

N/A

3 checks · not applicable

[codex:.] Skill Security

5/5

4 checks

[codex:.] Code Quality

10/10

2 checks

[opencode:.] OpenCode Plugin

2/2

4 checks

[opencode:.] Security

20/20

6 checks

[opencode:.] Operational Security

6/6

5 checks

[opencode:.] Code Quality

10/10

2 checks

Published advisories

None matched in GitHub security advisories, checked . This covers published advisories only, not problems nobody has reported.

GitHub security advisories are those the source repository has published.

Findings

mediumsecurityCLAUDE_FIELD_MISSING_VERSION

The Claude manifest requires a non-empty "version" string.

Add "version" to the Claude manifest.

infomanifest-validationPLUGIN_JSON_RECOMMENDED_KEYWORDS

The manifest is missing the documented recommended field "keywords".

Add "keywords" to strengthen the plugin manifest metadata.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_SCREENSHOTS

The interface field "screenshots" must use HTTPS or point to a safe in-repo asset.

Update "screenshots" to use HTTPS or an existing relative asset path.

infobest-practicesCODEXIGNORE_MISSING

A .codexignore file helps prevent accidental inclusion of local artifacts and secrets.

Add a .codexignore file with generated assets, local state, and secret paths.

Install guidance

Install in Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs

Optional: install HOL Guard for Claude Code first, so it can check this plugin's tools on your machine before Claude Code uses them.

  1. 1

    Add the marketplace

    Run this inside a Claude Code session. It registers the marketplace manifest shipped at the repository root. If the repository ships none, add the generated entry from the Advanced section below first.

    claude code
  2. 2

    Install the plugin

    Installs the ui-craft entry from the ui-craft marketplace.

    claude code
  3. 3

    Scripted alternative

    Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.

    shell
  4. 4

    Check it is installed

    Lists installed plugins. The entry should appear as enabled.

    shell

To remove it later, run claude plugin uninstall ui-craft@ui-craft.

Did setup work in Claude Code?

No setup reports for Claude Code yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W46, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

Loading reviews

Plugin manifest

{
  "name": "ui-craft",
  "version": "1.0.0",
  "description": "Design-engineering skills and local MCP quality gates for AI coding agents.",
  "author": {
    "name": "Eduardo Calvo",
    "url": "https://github.com/educlopez"
  },
  "homepage": "https://ui-craft.smoothui.dev",
  "repository": "https://github.com/educlopez/ui-craft",
  "license": "MIT",
  "skills": "./",
  "mcpServers": "./.registry/mcp.json",
  "requires_local_executor": true,
  "interface": {
    "displayName": "UI Craft",
    "developerName": "Eduardo Calvo",
    "shortDescription": "Build better interfaces",
    "longDescription": "Design engineering for AI coding agents: build interfaces, establish design tokens, review accessibility, and refine typography, layout, motion, and responsive behavior. Includes focused workflows and a local MCP server for deterministic design-quality checks. Requires local execution and Node.js 20 or newer; the MCP server is installed from npm on first use. No hosted account is required.",
    "category": "Developer Tools",
    "capabilities": [
      "Build interfaces",
      "Review UI quality",
      "Audit accessibility",
      "Establish design tokens"
    ],
    "websiteURL": "https://ui-craft.smoothui.dev",
    "supportURL": "https://github.com/educlopez/ui-craft/issues",
    "privacyPolicyURL": "https://github.com/educlopez/ui-craft/blob/main/PRIVACY.md",
    "termsOfServiceURL": "https://github.com/educlopez/ui-craft/blob/main/LICENSE",
    "composerIcon": "./assets/icon.svg",
    "logo": "./assets/icon.svg",
    "defaultPrompt": [
      "Build a dashboard with clear hierarchy and accessible interactions.",
      "Review my interface for accessibility and generic design patterns.",
      "Establish a consistent token system for this project."
    ]
  },
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/educlopez/ui-craft
Marketplace path
.claude-plugin/marketplace.json
Source path
.
Install policy
Unspecified

Skills

246 SKILL.md files ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli
  • adapt

    .agents/skills/adapt/SKILL.md

    Responsive layout pass covering breakpoints, touch targets, safe areas, and fluid type. Use when the UI has layout or touch issues on mobile/tablet, when adding a new screen that hasn't been tested across viewports, or when the user says \"make it responsive\" / \"fix mobile layout\". Invoke when the user asks for adapt on their UI, or mentions 'adapt' alongside design / UI / frontend work.

    Raw SKILL.md
  • animate

    .agents/skills/animate/SKILL.md

    Motion design pass — adds purposeful animations or removes excessive ones, respecting MOTION_INTENSITY and the project's animation stack. Use when the user asks to add animation, \"make it feel smoother\", fix janky transitions, or trim motion that's distracting. Invoke when the user asks for animate on their UI, or mentions 'animate' alongside design / UI / frontend work.

    Raw SKILL.md
  • audit

    .agents/skills/audit/SKILL.md

    Technical UI audit — a11y, performance, responsive. Produces a prioritized findings table. Invoke when the user asks for audit on their UI, or mentions 'audit' alongside design / UI / frontend work.

    Raw SKILL.md
  • bolder

    .agents/skills/bolder/SKILL.md

    Amplify personality — raises layout variance and motion, strengthens typography and one signature detail, without slop. Use when the UI works but feels safe, flat, or \"template-y\", or when the user says \"bolder\", \"more personality\", \"more creative\", or \"make it pop\" (still professional). Invoke when the user asks for bolder on their UI, or mentions 'bolder' alongside design / UI / frontend work.

    Raw SKILL.md
  • brief

    .agents/skills/brief/SKILL.md

    Write or update the project's durable design brief at .ui-craft/brief.md. Invoke when the user asks for brief on their UI, or mentions 'brief' alongside design / UI / frontend work.

    Raw SKILL.md
  • clarify

    .agents/skills/clarify/SKILL.md

    UX copy review across buttons, errors, empty states, and form hints — critiques by default, applies only on request. Use when copy feels vague, generic, or AI-sounding, or when the user says \"fix the labels\", \"improve error messages\", or \"review the copy\". Invoke when the user asks for clarify on their UI, or mentions 'clarify' alongside design / UI / frontend work.

    Raw SKILL.md
  • colorize

    .agents/skills/colorize/SKILL.md

    Color strategy pass — introduces a single accent at 3-5 intentional placements, or reduces an over-colored UI back to 90% neutral. Use when the UI has no color identity, uses blue by default, or is shouting with too many competing accents. Invoke when the user asks for colorize on their UI, or mentions 'colorize' alongside design / UI / frontend work.

    Raw SKILL.md
  • craft

    .agents/skills/craft/SKILL.md

    One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface (\"build me a dashboard\", \"hazme un dashboard\") and expects a shippable result, not component-level help. Invoke when the user asks for craft on their UI, or mentions 'craft' alongside design / UI / frontend work.

    Raw SKILL.md
  • critique

    .agents/skills/critique/SKILL.md

    Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says \"what's wrong with this UI\", or needs a second opinion before a handoff or presentation. Invoke when the user asks for critique on their UI, or mentions 'critique' alongside design / UI / frontend work.

    Raw SKILL.md
  • delight

    .agents/skills/delight/SKILL.md

    Delight pass — adds one or two memorable micro-interactions (copy specificity, hover choreography, state transitions, one signature detail) without decoration or confetti. Use when the UI works but feels generic, or when the user says \"make it feel special\" / \"add some personality\". Invoke when the user asks for delight on their UI, or mentions 'delight' alongside design / UI / frontend work.

    Raw SKILL.md
  • distill

    .agents/skills/distill/SKILL.md

    Reduction pass — cuts content, structure, visuals, and dead code that doesn't answer a user question or drive an action, respecting CRAFT_LEVEL. Use when the UI feels cluttered, has too many CTAs, walls of text, or decorative noise, or when the user says \"simplify this\" / \"it feels too busy\". Invoke when the user asks for distill on their UI, or mentions 'distill' alongside design / UI / frontend work.

    Raw SKILL.md
  • extract

    .agents/skills/extract/SKILL.md

    Refactoring pass — extracts repeated Tailwind class combos and markup into components, and lifts magic values into design tokens. Use when the codebase has obvious duplication, hardcoded hex values or pixel sizes, or when the user says \"clean this up\" / \"extract components\" / \"tokenize styles\". Invoke when the user asks for extract on their UI, or mentions 'extract' alongside design / UI / frontend work.

    Raw SKILL.md
  • finalize

    .agents/skills/finalize/SKILL.md

    Pre-ship gate — runs detector, verifies brief and tokens, applies the 10-pass finish bar, ranks findings by feedback hierarchy. Use when the user wants to ship, merge, or finalize a surface and needs a verdict (READY / NOT READY / BLOCKED) before committing. Invoke when the user asks for finalize on their UI, or mentions 'finalize' alongside design / UI / frontend work.

    Raw SKILL.md
  • harden

    .agents/skills/harden/SKILL.md

    Production-readiness pass — audits and implements the full non-happy-path matrix: loading skeletons, empty states, error messages, partial data, i18n, offline, permissions, and first-run guidance. Use when preparing a surface for production or when the user says \"it crashes on empty data\" / \"there's no loading state\" / \"harden this\". Invoke when the user asks for harden on their UI, or mentions 'harden' alongside design / UI / frontend work.

    Raw SKILL.md
  • heuristic

    .agents/skills/heuristic/SKILL.md

    Produce a scored heuristic critique of the UI using Nielsen's 10 + 6 design laws + optional persona walkthroughs. Outputs a machine-parseable scorecard plus a 0-100 UsabilityScore (the judged companion to the deterministic UICraftScore). Invoke when the user asks for heuristic on their UI, or mentions 'heuristic' alongside design / UI / frontend work.

    Raw SKILL.md
  • polish

    .agents/skills/polish/SKILL.md

    Final craft pass applying the compound details from the polish checklist — micro-typography, spacing rhythm, hover states, and a signature detail — directly to code. Use when the surface is functionally complete but feels unfinished, or when the user says \"polish this\" / \"it looks generic\" / \"add the final touches\". Invoke when the user asks for polish on their UI, or mentions 'polish' alongside design / UI / frontend work.

    Raw SKILL.md
  • quieter

    .agents/skills/quieter/SKILL.md

    Tone down visual noise — lowers variance and motion, simplifies layout and color weight, keeps hierarchy clear. Use when the UI feels loud, busy, or over-designed, or when the user says \"quieter\", \"more restrained\", \"simpler\", or \"tone it down\". Invoke when the user asks for quieter on their UI, or mentions 'quieter' alongside design / UI / frontend work.

    Raw SKILL.md
  • redesign

    .agents/skills/redesign/SKILL.md

    Redesign an existing site or app without losing what already works — audits the current surface first, classifies what to preserve (brand, IA, SEO, content), picks a refresh/reskin/rebuild scope, then modernizes deliberately. Use when the user says \"redesign\", \"modernize this site\", \"refresh the UI\", \"make this look current\", or points at an existing page/URL they want improved rather than rebuilt from scratch. Invoke when the user asks for redesign on their UI, or mentions 'redesign' alongside design / UI / frontend work.

    Raw SKILL.md
  • remember

    .agents/skills/remember/SKILL.md

    Record a learned design constraint from a correction into the project brief. Invoke when the user asks for remember on their UI, or mentions 'remember' alongside design / UI / frontend work.

    Raw SKILL.md
  • sddesign

    .agents/skills/sddesign/SKILL.md

    Full spec-driven pipeline — walks brief → tokens → shape (spec) → craft (build) → converge → ship in one guided run. Writes `.ui-craft/spec.md`. Run when starting a net-new surface from scratch. Invoke when the user asks for sddesign on their UI, or mentions 'sddesign' alongside design / UI / frontend work.

    Raw SKILL.md
  • shape

    .agents/skills/shape/SKILL.md

    Wireframe-first pass — outputs an ASCII layout + state list + content inventory + question list before any code. Use when starting a new screen from scratch or when the user's brief is still ambiguous. Invoke when the user asks for shape on their UI, or mentions 'shape' alongside design / UI / frontend work.

    Raw SKILL.md
  • start

    .agents/skills/start/SKILL.md

    Front door. Reads the current project (framework, tokens, brief, spec, harness) and reports what ui-craft can do right now, then routes you to the right next step. Run this first if you're new or unsure where to begin. No code changes. Invoke when the user asks for start on their UI, or mentions 'start' alongside design / UI / frontend work.

    Raw SKILL.md
  • tokens

    .agents/skills/tokens/SKILL.md

    Audit or establish the project's 3-layer token spine. Invoke when the user asks for tokens on their UI, or mentions 'tokens' alongside design / UI / frontend work.

    Raw SKILL.md
  • typeset

    .agents/skills/typeset/SKILL.md

    Typography pass covering font choice, modular scale, tracking, leading, weight hierarchy, and micro-typography details. Use when fonts feel generic (default Inter with no reason), the scale is ad hoc, hierarchy is flat, or the user says \"fix the typography\" / \"the text doesn't feel right\". Invoke when the user asks for typeset on their UI, or mentions 'typeset' alongside design / UI / frontend work.

    Raw SKILL.md
  • ui-craft-dense-dashboard

    .agents/skills/ui-craft-dense-dashboard/SKILL.md

    Dense dashboard / admin / Bloomberg / Retool / data-heavy internal tools. Locked knobs: CRAFT=7, MOTION=3, DENSITY=9. IBM Plex + mono numbers, semantic palette, 4/8px grid, sparklines, tabular-nums. Trigger on: dashboard, admin panel, data-dense, analytics, Bloomberg-like, Retool-like.

    Raw SKILL.md
  • ui-craft-editorial

    .agents/skills/ui-craft-editorial/SKILL.md

    Editorial / magazine / long-form / Medium / Substack / content-heavy UIs. Locked knobs: CRAFT=9, MOTION=4, DENSITY=3. Serif display + humanist body, wide reading column, drop caps, OpenType. Trigger on: editorial, magazine, long-form, blog, Medium-like, Substack-like.

    Raw SKILL.md
  • ui-craft-minimal

    .agents/skills/ui-craft-minimal/SKILL.md

    Minimal / clean / Linear / Notion / Vercel / whitespace-heavy UIs. Locked knobs: CRAFT=8, MOTION=3, DENSITY=2. Monochrome + one accent, Inter/Geist, hairline borders over shadows. Trigger on: minimal, clean, Linear-like, Notion-like, Vercel-like, whitespace-heavy.

    Raw SKILL.md
  • ui-craft

    .agents/skills/ui-craft/SKILL.md

    Use for UI design and implementation work to avoid generic AI-looking interfaces. Provides anti-slop rules, a required discovery phase before coding, and guidance for layout, typography, color, motion, accessibility, dashboards, tables, landing pages, theming, and polish. Trigger when editing UI code or reviewing and refining components, pages, screens, layouts, animations, responsive behavior, or design systems.

    Raw SKILL.md
  • unhappy

    .agents/skills/unhappy/SKILL.md

    State-first design pass — inventories and implements all non-happy states (loading, empty, error, partial, conflict, offline) before the happy path, and refactors impossible boolean state to proper state machines. Use when starting a new screen, reviewing an existing one for edge-case gaps, or when the user says \"handle the error state\" / \"add loading states\" / \"what happens when data is missing\". Invoke when the user asks for unhappy on their UI, or mentions 'unhappy' alongside design / UI / frontend work.

    Raw SKILL.md
  • friction-log

    .claude/skills/friction-log/SKILL.md

    >

    Raw SKILL.md
  • adapt

    .codex/skills/adapt/SKILL.md

    Responsive layout pass covering breakpoints, touch targets, safe areas, and fluid type. Use when the UI has layout or touch issues on mobile/tablet, when adding a new screen that hasn't been tested across viewports, or when the user says \"make it responsive\" / \"fix mobile layout\". Invoke when the user asks for adapt on their UI, or mentions 'adapt' alongside design / UI / frontend work.

    Raw SKILL.md
  • animate

    .codex/skills/animate/SKILL.md

    Motion design pass — adds purposeful animations or removes excessive ones, respecting MOTION_INTENSITY and the project's animation stack. Use when the user asks to add animation, \"make it feel smoother\", fix janky transitions, or trim motion that's distracting. Invoke when the user asks for animate on their UI, or mentions 'animate' alongside design / UI / frontend work.

    Raw SKILL.md
  • audit

    .codex/skills/audit/SKILL.md

    Technical UI audit — a11y, performance, responsive. Produces a prioritized findings table. Invoke when the user asks for audit on their UI, or mentions 'audit' alongside design / UI / frontend work.

    Raw SKILL.md
  • bolder

    .codex/skills/bolder/SKILL.md

    Amplify personality — raises layout variance and motion, strengthens typography and one signature detail, without slop. Use when the UI works but feels safe, flat, or \"template-y\", or when the user says \"bolder\", \"more personality\", \"more creative\", or \"make it pop\" (still professional). Invoke when the user asks for bolder on their UI, or mentions 'bolder' alongside design / UI / frontend work.

    Raw SKILL.md
  • brief

    .codex/skills/brief/SKILL.md

    Write or update the project's durable design brief at .ui-craft/brief.md. Invoke when the user asks for brief on their UI, or mentions 'brief' alongside design / UI / frontend work.

    Raw SKILL.md
  • clarify

    .codex/skills/clarify/SKILL.md

    UX copy review across buttons, errors, empty states, and form hints — critiques by default, applies only on request. Use when copy feels vague, generic, or AI-sounding, or when the user says \"fix the labels\", \"improve error messages\", or \"review the copy\". Invoke when the user asks for clarify on their UI, or mentions 'clarify' alongside design / UI / frontend work.

    Raw SKILL.md
  • colorize

    .codex/skills/colorize/SKILL.md

    Color strategy pass — introduces a single accent at 3-5 intentional placements, or reduces an over-colored UI back to 90% neutral. Use when the UI has no color identity, uses blue by default, or is shouting with too many competing accents. Invoke when the user asks for colorize on their UI, or mentions 'colorize' alongside design / UI / frontend work.

    Raw SKILL.md
  • craft

    .codex/skills/craft/SKILL.md

    One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface (\"build me a dashboard\", \"hazme un dashboard\") and expects a shippable result, not component-level help. Invoke when the user asks for craft on their UI, or mentions 'craft' alongside design / UI / frontend work.

    Raw SKILL.md
  • critique

    .codex/skills/critique/SKILL.md

    Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says \"what's wrong with this UI\", or needs a second opinion before a handoff or presentation. Invoke when the user asks for critique on their UI, or mentions 'critique' alongside design / UI / frontend work.

    Raw SKILL.md
  • delight

    .codex/skills/delight/SKILL.md

    Delight pass — adds one or two memorable micro-interactions (copy specificity, hover choreography, state transitions, one signature detail) without decoration or confetti. Use when the UI works but feels generic, or when the user says \"make it feel special\" / \"add some personality\". Invoke when the user asks for delight on their UI, or mentions 'delight' alongside design / UI / frontend work.

    Raw SKILL.md
  • distill

    .codex/skills/distill/SKILL.md

    Reduction pass — cuts content, structure, visuals, and dead code that doesn't answer a user question or drive an action, respecting CRAFT_LEVEL. Use when the UI feels cluttered, has too many CTAs, walls of text, or decorative noise, or when the user says \"simplify this\" / \"it feels too busy\". Invoke when the user asks for distill on their UI, or mentions 'distill' alongside design / UI / frontend work.

    Raw SKILL.md
  • extract

    .codex/skills/extract/SKILL.md

    Refactoring pass — extracts repeated Tailwind class combos and markup into components, and lifts magic values into design tokens. Use when the codebase has obvious duplication, hardcoded hex values or pixel sizes, or when the user says \"clean this up\" / \"extract components\" / \"tokenize styles\". Invoke when the user asks for extract on their UI, or mentions 'extract' alongside design / UI / frontend work.

    Raw SKILL.md
  • finalize

    .codex/skills/finalize/SKILL.md

    Pre-ship gate — runs detector, verifies brief and tokens, applies the 10-pass finish bar, ranks findings by feedback hierarchy. Use when the user wants to ship, merge, or finalize a surface and needs a verdict (READY / NOT READY / BLOCKED) before committing. Invoke when the user asks for finalize on their UI, or mentions 'finalize' alongside design / UI / frontend work.

    Raw SKILL.md
  • harden

    .codex/skills/harden/SKILL.md

    Production-readiness pass — audits and implements the full non-happy-path matrix: loading skeletons, empty states, error messages, partial data, i18n, offline, permissions, and first-run guidance. Use when preparing a surface for production or when the user says \"it crashes on empty data\" / \"there's no loading state\" / \"harden this\". Invoke when the user asks for harden on their UI, or mentions 'harden' alongside design / UI / frontend work.

    Raw SKILL.md
  • heuristic

    .codex/skills/heuristic/SKILL.md

    Produce a scored heuristic critique of the UI using Nielsen's 10 + 6 design laws + optional persona walkthroughs. Outputs a machine-parseable scorecard plus a 0-100 UsabilityScore (the judged companion to the deterministic UICraftScore). Invoke when the user asks for heuristic on their UI, or mentions 'heuristic' alongside design / UI / frontend work.

    Raw SKILL.md
  • polish

    .codex/skills/polish/SKILL.md

    Final craft pass applying the compound details from the polish checklist — micro-typography, spacing rhythm, hover states, and a signature detail — directly to code. Use when the surface is functionally complete but feels unfinished, or when the user says \"polish this\" / \"it looks generic\" / \"add the final touches\". Invoke when the user asks for polish on their UI, or mentions 'polish' alongside design / UI / frontend work.

    Raw SKILL.md
  • quieter

    .codex/skills/quieter/SKILL.md

    Tone down visual noise — lowers variance and motion, simplifies layout and color weight, keeps hierarchy clear. Use when the UI feels loud, busy, or over-designed, or when the user says \"quieter\", \"more restrained\", \"simpler\", or \"tone it down\". Invoke when the user asks for quieter on their UI, or mentions 'quieter' alongside design / UI / frontend work.

    Raw SKILL.md
  • redesign

    .codex/skills/redesign/SKILL.md

    Redesign an existing site or app without losing what already works — audits the current surface first, classifies what to preserve (brand, IA, SEO, content), picks a refresh/reskin/rebuild scope, then modernizes deliberately. Use when the user says \"redesign\", \"modernize this site\", \"refresh the UI\", \"make this look current\", or points at an existing page/URL they want improved rather than rebuilt from scratch. Invoke when the user asks for redesign on their UI, or mentions 'redesign' alongside design / UI / frontend work.

    Raw SKILL.md
  • remember

    .codex/skills/remember/SKILL.md

    Record a learned design constraint from a correction into the project brief. Invoke when the user asks for remember on their UI, or mentions 'remember' alongside design / UI / frontend work.

    Raw SKILL.md
  • sddesign

    .codex/skills/sddesign/SKILL.md

    Full spec-driven pipeline — walks brief → tokens → shape (spec) → craft (build) → converge → ship in one guided run. Writes `.ui-craft/spec.md`. Run when starting a net-new surface from scratch. Invoke when the user asks for sddesign on their UI, or mentions 'sddesign' alongside design / UI / frontend work.

    Raw SKILL.md
  • shape

    .codex/skills/shape/SKILL.md

    Wireframe-first pass — outputs an ASCII layout + state list + content inventory + question list before any code. Use when starting a new screen from scratch or when the user's brief is still ambiguous. Invoke when the user asks for shape on their UI, or mentions 'shape' alongside design / UI / frontend work.

    Raw SKILL.md
  • start

    .codex/skills/start/SKILL.md

    Front door. Reads the current project (framework, tokens, brief, spec, harness) and reports what ui-craft can do right now, then routes you to the right next step. Run this first if you're new or unsure where to begin. No code changes. Invoke when the user asks for start on their UI, or mentions 'start' alongside design / UI / frontend work.

    Raw SKILL.md
  • tokens

    .codex/skills/tokens/SKILL.md

    Audit or establish the project's 3-layer token spine. Invoke when the user asks for tokens on their UI, or mentions 'tokens' alongside design / UI / frontend work.

    Raw SKILL.md
  • typeset

    .codex/skills/typeset/SKILL.md

    Typography pass covering font choice, modular scale, tracking, leading, weight hierarchy, and micro-typography details. Use when fonts feel generic (default Inter with no reason), the scale is ad hoc, hierarchy is flat, or the user says \"fix the typography\" / \"the text doesn't feel right\". Invoke when the user asks for typeset on their UI, or mentions 'typeset' alongside design / UI / frontend work.

    Raw SKILL.md
  • ui-craft-dense-dashboard

    .codex/skills/ui-craft-dense-dashboard/SKILL.md

    Dense dashboard / admin / Bloomberg / Retool / data-heavy internal tools. Locked knobs: CRAFT=7, MOTION=3, DENSITY=9. IBM Plex + mono numbers, semantic palette, 4/8px grid, sparklines, tabular-nums. Trigger on: dashboard, admin panel, data-dense, analytics, Bloomberg-like, Retool-like.

    Raw SKILL.md
  • ui-craft-editorial

    .codex/skills/ui-craft-editorial/SKILL.md

    Editorial / magazine / long-form / Medium / Substack / content-heavy UIs. Locked knobs: CRAFT=9, MOTION=4, DENSITY=3. Serif display + humanist body, wide reading column, drop caps, OpenType. Trigger on: editorial, magazine, long-form, blog, Medium-like, Substack-like.

    Raw SKILL.md
  • ui-craft-minimal

    .codex/skills/ui-craft-minimal/SKILL.md

    Minimal / clean / Linear / Notion / Vercel / whitespace-heavy UIs. Locked knobs: CRAFT=8, MOTION=3, DENSITY=2. Monochrome + one accent, Inter/Geist, hairline borders over shadows. Trigger on: minimal, clean, Linear-like, Notion-like, Vercel-like, whitespace-heavy.

    Raw SKILL.md
  • ui-craft

    .codex/skills/ui-craft/SKILL.md

    Use for UI design and implementation work to avoid generic AI-looking interfaces. Provides anti-slop rules, a required discovery phase before coding, and guidance for layout, typography, color, motion, accessibility, dashboards, tables, landing pages, theming, and polish. Trigger when editing UI code or reviewing and refining components, pages, screens, layouts, animations, responsive behavior, or design systems.

    Raw SKILL.md
  • unhappy

    .codex/skills/unhappy/SKILL.md

    State-first design pass — inventories and implements all non-happy states (loading, empty, error, partial, conflict, offline) before the happy path, and refactors impossible boolean state to proper state machines. Use when starting a new screen, reviewing an existing one for edge-case gaps, or when the user says \"handle the error state\" / \"add loading states\" / \"what happens when data is missing\". Invoke when the user asks for unhappy on their UI, or mentions 'unhappy' alongside design / UI / frontend work.

    Raw SKILL.md
  • friction-log

    .cursor/skills/friction-log/SKILL.md

    >

    Raw SKILL.md
  • adapt

    .gemini/skills/adapt/SKILL.md

    Responsive layout pass covering breakpoints, touch targets, safe areas, and fluid type. Use when the UI has layout or touch issues on mobile/tablet, when adding a new screen that hasn't been tested across viewports, or when the user says \"make it responsive\" / \"fix mobile layout\". Invoke when the user asks for adapt on their UI, or mentions 'adapt' alongside design / UI / frontend work.

    Raw SKILL.md
  • animate

    .gemini/skills/animate/SKILL.md

    Motion design pass — adds purposeful animations or removes excessive ones, respecting MOTION_INTENSITY and the project's animation stack. Use when the user asks to add animation, \"make it feel smoother\", fix janky transitions, or trim motion that's distracting. Invoke when the user asks for animate on their UI, or mentions 'animate' alongside design / UI / frontend work.

    Raw SKILL.md
  • audit

    .gemini/skills/audit/SKILL.md

    Technical UI audit — a11y, performance, responsive. Produces a prioritized findings table. Invoke when the user asks for audit on their UI, or mentions 'audit' alongside design / UI / frontend work.

    Raw SKILL.md
  • bolder

    .gemini/skills/bolder/SKILL.md

    Amplify personality — raises layout variance and motion, strengthens typography and one signature detail, without slop. Use when the UI works but feels safe, flat, or \"template-y\", or when the user says \"bolder\", \"more personality\", \"more creative\", or \"make it pop\" (still professional). Invoke when the user asks for bolder on their UI, or mentions 'bolder' alongside design / UI / frontend work.

    Raw SKILL.md
  • brief

    .gemini/skills/brief/SKILL.md

    Write or update the project's durable design brief at .ui-craft/brief.md. Invoke when the user asks for brief on their UI, or mentions 'brief' alongside design / UI / frontend work.

    Raw SKILL.md
  • clarify

    .gemini/skills/clarify/SKILL.md

    UX copy review across buttons, errors, empty states, and form hints — critiques by default, applies only on request. Use when copy feels vague, generic, or AI-sounding, or when the user says \"fix the labels\", \"improve error messages\", or \"review the copy\". Invoke when the user asks for clarify on their UI, or mentions 'clarify' alongside design / UI / frontend work.

    Raw SKILL.md
  • colorize

    .gemini/skills/colorize/SKILL.md

    Color strategy pass — introduces a single accent at 3-5 intentional placements, or reduces an over-colored UI back to 90% neutral. Use when the UI has no color identity, uses blue by default, or is shouting with too many competing accents. Invoke when the user asks for colorize on their UI, or mentions 'colorize' alongside design / UI / frontend work.

    Raw SKILL.md
  • craft

    .gemini/skills/craft/SKILL.md

    One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface (\"build me a dashboard\", \"hazme un dashboard\") and expects a shippable result, not component-level help. Invoke when the user asks for craft on their UI, or mentions 'craft' alongside design / UI / frontend work.

    Raw SKILL.md
  • critique

    .gemini/skills/critique/SKILL.md

    Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says \"what's wrong with this UI\", or needs a second opinion before a handoff or presentation. Invoke when the user asks for critique on their UI, or mentions 'critique' alongside design / UI / frontend work.

    Raw SKILL.md
  • delight

    .gemini/skills/delight/SKILL.md

    Delight pass — adds one or two memorable micro-interactions (copy specificity, hover choreography, state transitions, one signature detail) without decoration or confetti. Use when the UI works but feels generic, or when the user says \"make it feel special\" / \"add some personality\". Invoke when the user asks for delight on their UI, or mentions 'delight' alongside design / UI / frontend work.

    Raw SKILL.md
  • distill

    .gemini/skills/distill/SKILL.md

    Reduction pass — cuts content, structure, visuals, and dead code that doesn't answer a user question or drive an action, respecting CRAFT_LEVEL. Use when the UI feels cluttered, has too many CTAs, walls of text, or decorative noise, or when the user says \"simplify this\" / \"it feels too busy\". Invoke when the user asks for distill on their UI, or mentions 'distill' alongside design / UI / frontend work.

    Raw SKILL.md
  • extract

    .gemini/skills/extract/SKILL.md

    Refactoring pass — extracts repeated Tailwind class combos and markup into components, and lifts magic values into design tokens. Use when the codebase has obvious duplication, hardcoded hex values or pixel sizes, or when the user says \"clean this up\" / \"extract components\" / \"tokenize styles\". Invoke when the user asks for extract on their UI, or mentions 'extract' alongside design / UI / frontend work.

    Raw SKILL.md
  • finalize

    .gemini/skills/finalize/SKILL.md

    Pre-ship gate — runs detector, verifies brief and tokens, applies the 10-pass finish bar, ranks findings by feedback hierarchy. Use when the user wants to ship, merge, or finalize a surface and needs a verdict (READY / NOT READY / BLOCKED) before committing. Invoke when the user asks for finalize on their UI, or mentions 'finalize' alongside design / UI / frontend work.

    Raw SKILL.md
  • harden

    .gemini/skills/harden/SKILL.md

    Production-readiness pass — audits and implements the full non-happy-path matrix: loading skeletons, empty states, error messages, partial data, i18n, offline, permissions, and first-run guidance. Use when preparing a surface for production or when the user says \"it crashes on empty data\" / \"there's no loading state\" / \"harden this\". Invoke when the user asks for harden on their UI, or mentions 'harden' alongside design / UI / frontend work.

    Raw SKILL.md
  • heuristic

    .gemini/skills/heuristic/SKILL.md

    Produce a scored heuristic critique of the UI using Nielsen's 10 + 6 design laws + optional persona walkthroughs. Outputs a machine-parseable scorecard plus a 0-100 UsabilityScore (the judged companion to the deterministic UICraftScore). Invoke when the user asks for heuristic on their UI, or mentions 'heuristic' alongside design / UI / frontend work.

    Raw SKILL.md
  • polish

    .gemini/skills/polish/SKILL.md

    Final craft pass applying the compound details from the polish checklist — micro-typography, spacing rhythm, hover states, and a signature detail — directly to code. Use when the surface is functionally complete but feels unfinished, or when the user says \"polish this\" / \"it looks generic\" / \"add the final touches\". Invoke when the user asks for polish on their UI, or mentions 'polish' alongside design / UI / frontend work.

    Raw SKILL.md
  • quieter

    .gemini/skills/quieter/SKILL.md

    Tone down visual noise — lowers variance and motion, simplifies layout and color weight, keeps hierarchy clear. Use when the UI feels loud, busy, or over-designed, or when the user says \"quieter\", \"more restrained\", \"simpler\", or \"tone it down\". Invoke when the user asks for quieter on their UI, or mentions 'quieter' alongside design / UI / frontend work.

    Raw SKILL.md
  • redesign

    .gemini/skills/redesign/SKILL.md

    Redesign an existing site or app without losing what already works — audits the current surface first, classifies what to preserve (brand, IA, SEO, content), picks a refresh/reskin/rebuild scope, then modernizes deliberately. Use when the user says \"redesign\", \"modernize this site\", \"refresh the UI\", \"make this look current\", or points at an existing page/URL they want improved rather than rebuilt from scratch. Invoke when the user asks for redesign on their UI, or mentions 'redesign' alongside design / UI / frontend work.

    Raw SKILL.md
  • remember

    .gemini/skills/remember/SKILL.md

    Record a learned design constraint from a correction into the project brief. Invoke when the user asks for remember on their UI, or mentions 'remember' alongside design / UI / frontend work.

    Raw SKILL.md
  • sddesign

    .gemini/skills/sddesign/SKILL.md

    Full spec-driven pipeline — walks brief → tokens → shape (spec) → craft (build) → converge → ship in one guided run. Writes `.ui-craft/spec.md`. Run when starting a net-new surface from scratch. Invoke when the user asks for sddesign on their UI, or mentions 'sddesign' alongside design / UI / frontend work.

    Raw SKILL.md
  • shape

    .gemini/skills/shape/SKILL.md

    Wireframe-first pass — outputs an ASCII layout + state list + content inventory + question list before any code. Use when starting a new screen from scratch or when the user's brief is still ambiguous. Invoke when the user asks for shape on their UI, or mentions 'shape' alongside design / UI / frontend work.

    Raw SKILL.md
  • start

    .gemini/skills/start/SKILL.md

    Front door. Reads the current project (framework, tokens, brief, spec, harness) and reports what ui-craft can do right now, then routes you to the right next step. Run this first if you're new or unsure where to begin. No code changes. Invoke when the user asks for start on their UI, or mentions 'start' alongside design / UI / frontend work.

    Raw SKILL.md
  • tokens

    .gemini/skills/tokens/SKILL.md

    Audit or establish the project's 3-layer token spine. Invoke when the user asks for tokens on their UI, or mentions 'tokens' alongside design / UI / frontend work.

    Raw SKILL.md
  • typeset

    .gemini/skills/typeset/SKILL.md

    Typography pass covering font choice, modular scale, tracking, leading, weight hierarchy, and micro-typography details. Use when fonts feel generic (default Inter with no reason), the scale is ad hoc, hierarchy is flat, or the user says \"fix the typography\" / \"the text doesn't feel right\". Invoke when the user asks for typeset on their UI, or mentions 'typeset' alongside design / UI / frontend work.

    Raw SKILL.md
  • ui-craft-dense-dashboard

    .gemini/skills/ui-craft-dense-dashboard/SKILL.md

    Dense dashboard / admin / Bloomberg / Retool / data-heavy internal tools. Locked knobs: CRAFT=7, MOTION=3, DENSITY=9. IBM Plex + mono numbers, semantic palette, 4/8px grid, sparklines, tabular-nums. Trigger on: dashboard, admin panel, data-dense, analytics, Bloomberg-like, Retool-like.

    Raw SKILL.md
  • ui-craft-editorial

    .gemini/skills/ui-craft-editorial/SKILL.md

    Editorial / magazine / long-form / Medium / Substack / content-heavy UIs. Locked knobs: CRAFT=9, MOTION=4, DENSITY=3. Serif display + humanist body, wide reading column, drop caps, OpenType. Trigger on: editorial, magazine, long-form, blog, Medium-like, Substack-like.

    Raw SKILL.md
  • ui-craft-minimal

    .gemini/skills/ui-craft-minimal/SKILL.md

    Minimal / clean / Linear / Notion / Vercel / whitespace-heavy UIs. Locked knobs: CRAFT=8, MOTION=3, DENSITY=2. Monochrome + one accent, Inter/Geist, hairline borders over shadows. Trigger on: minimal, clean, Linear-like, Notion-like, Vercel-like, whitespace-heavy.

    Raw SKILL.md
  • ui-craft

    .gemini/skills/ui-craft/SKILL.md

    Use for UI design and implementation work to avoid generic AI-looking interfaces. Provides anti-slop rules, a required discovery phase before coding, and guidance for layout, typography, color, motion, accessibility, dashboards, tables, landing pages, theming, and polish. Trigger when editing UI code or reviewing and refining components, pages, screens, layouts, animations, responsive behavior, or design systems.

    Raw SKILL.md
  • unhappy

    .gemini/skills/unhappy/SKILL.md

    State-first design pass — inventories and implements all non-happy states (loading, empty, error, partial, conflict, offline) before the happy path, and refactors impossible boolean state to proper state machines. Use when starting a new screen, reviewing an existing one for edge-case gaps, or when the user says \"handle the error state\" / \"add loading states\" / \"what happens when data is missing\". Invoke when the user asks for unhappy on their UI, or mentions 'unhappy' alongside design / UI / frontend work.

    Raw SKILL.md
  • adapt

    .opencode/skills/adapt/SKILL.md

    Responsive layout pass covering breakpoints, touch targets, safe areas, and fluid type. Use when the UI has layout or touch issues on mobile/tablet, when adding a new screen that hasn't been tested across viewports, or when the user says \"make it responsive\" / \"fix mobile layout\". Invoke when the user asks for adapt on their UI, or mentions 'adapt' alongside design / UI / frontend work.

    Raw SKILL.md
  • animate

    .opencode/skills/animate/SKILL.md

    Motion design pass — adds purposeful animations or removes excessive ones, respecting MOTION_INTENSITY and the project's animation stack. Use when the user asks to add animation, \"make it feel smoother\", fix janky transitions, or trim motion that's distracting. Invoke when the user asks for animate on their UI, or mentions 'animate' alongside design / UI / frontend work.

    Raw SKILL.md
  • audit

    .opencode/skills/audit/SKILL.md

    Technical UI audit — a11y, performance, responsive. Produces a prioritized findings table. Invoke when the user asks for audit on their UI, or mentions 'audit' alongside design / UI / frontend work.

    Raw SKILL.md
  • bolder

    .opencode/skills/bolder/SKILL.md

    Amplify personality — raises layout variance and motion, strengthens typography and one signature detail, without slop. Use when the UI works but feels safe, flat, or \"template-y\", or when the user says \"bolder\", \"more personality\", \"more creative\", or \"make it pop\" (still professional). Invoke when the user asks for bolder on their UI, or mentions 'bolder' alongside design / UI / frontend work.

    Raw SKILL.md
  • brief

    .opencode/skills/brief/SKILL.md

    Write or update the project's durable design brief at .ui-craft/brief.md. Invoke when the user asks for brief on their UI, or mentions 'brief' alongside design / UI / frontend work.

    Raw SKILL.md
  • clarify

    .opencode/skills/clarify/SKILL.md

    UX copy review across buttons, errors, empty states, and form hints — critiques by default, applies only on request. Use when copy feels vague, generic, or AI-sounding, or when the user says \"fix the labels\", \"improve error messages\", or \"review the copy\". Invoke when the user asks for clarify on their UI, or mentions 'clarify' alongside design / UI / frontend work.

    Raw SKILL.md
  • colorize

    .opencode/skills/colorize/SKILL.md

    Color strategy pass — introduces a single accent at 3-5 intentional placements, or reduces an over-colored UI back to 90% neutral. Use when the UI has no color identity, uses blue by default, or is shouting with too many competing accents. Invoke when the user asks for colorize on their UI, or mentions 'colorize' alongside design / UI / frontend work.

    Raw SKILL.md
  • craft

    .opencode/skills/craft/SKILL.md

    One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface (\"build me a dashboard\", \"hazme un dashboard\") and expects a shippable result, not component-level help. Invoke when the user asks for craft on their UI, or mentions 'craft' alongside design / UI / frontend work.

    Raw SKILL.md
  • critique

    .opencode/skills/critique/SKILL.md

    Design lens critique covering visual hierarchy, clarity, and anti-slop patterns — produces a findings table, no code edits unless asked. Use when the user wants a design review, says \"what's wrong with this UI\", or needs a second opinion before a handoff or presentation. Invoke when the user asks for critique on their UI, or mentions 'critique' alongside design / UI / frontend work.

    Raw SKILL.md
  • delight

    .opencode/skills/delight/SKILL.md

    Delight pass — adds one or two memorable micro-interactions (copy specificity, hover choreography, state transitions, one signature detail) without decoration or confetti. Use when the UI works but feels generic, or when the user says \"make it feel special\" / \"add some personality\". Invoke when the user asks for delight on their UI, or mentions 'delight' alongside design / UI / frontend work.

    Raw SKILL.md
  • distill

    .opencode/skills/distill/SKILL.md

    Reduction pass — cuts content, structure, visuals, and dead code that doesn't answer a user question or drive an action, respecting CRAFT_LEVEL. Use when the UI feels cluttered, has too many CTAs, walls of text, or decorative noise, or when the user says \"simplify this\" / \"it feels too busy\". Invoke when the user asks for distill on their UI, or mentions 'distill' alongside design / UI / frontend work.

    Raw SKILL.md

File inventory

.agents/skills/adapt/SKILL.md

skill

3,086 bytes

5861243d8b0c0211…

.agents/skills/animate/SKILL.md

skill

2,453 bytes

aa58997e1c07657f…

.agents/skills/audit/SKILL.md

skill

3,892 bytes

f8fbfd748efd3d23…

.agents/skills/bolder/SKILL.md

skill

2,464 bytes

69b985c31df16ab1…

.agents/skills/brief/SKILL.md

skill

4,604 bytes

874dcc6608bebaa1…

.agents/skills/clarify/SKILL.md

skill

2,826 bytes

52e5b229ca040da1…

.agents/skills/colorize/SKILL.md

skill

3,276 bytes

22f12b7297fb4f8b…

.agents/skills/craft/SKILL.md

skill

6,528 bytes

a6db8454a8482df1…

.agents/skills/critique/SKILL.md

skill

4,615 bytes

53b3014230a8d836…

.agents/skills/delight/SKILL.md

skill

2,768 bytes

1b95c69b8997a532…

.agents/skills/distill/SKILL.md

skill

3,196 bytes

958c3ce6a3c72de3…

.agents/skills/extract/SKILL.md

skill

2,920 bytes

31c80d52df9c8d73…

.agents/skills/finalize/SKILL.md

skill

7,883 bytes

6b7ab59c54333e06…

.agents/skills/harden/SKILL.md

skill

4,529 bytes

2273e4c62d92212e…

.agents/skills/heuristic/SKILL.md

skill

4,179 bytes

3e5dddcb6bcc515d…

.agents/skills/polish/SKILL.md

skill

2,482 bytes

9b4efbc577cdd243…

.agents/skills/quieter/SKILL.md

skill

2,102 bytes

4b29eb67400c0e69…

.agents/skills/redesign/SKILL.md

skill

4,058 bytes

6de04099438cbf60…

.agents/skills/remember/SKILL.md

skill

2,350 bytes

6ce04af8b57b0a49…

.agents/skills/sddesign/SKILL.md

skill

6,313 bytes

20fd12ad5e2f9699…

.agents/skills/shape/SKILL.md

skill

7,144 bytes

36e90f8de8d64620…

.agents/skills/start/SKILL.md

skill

5,885 bytes

3bc48d436214856d…

.agents/skills/tokens/SKILL.md

skill

5,692 bytes

eefb8d59d4b739b4…

.agents/skills/typeset/SKILL.md

skill

4,368 bytes

f6bdfe8c6544473f…

.agents/skills/ui-craft-dense-dashboard/SKILL.md

skill

5,634 bytes

55e9131a3aa2dab4…

.agents/skills/ui-craft-editorial/SKILL.md

skill

5,266 bytes

05500a88dba4a20c…

.agents/skills/ui-craft-minimal/SKILL.md

skill

4,822 bytes

71c09ea690441189…

.agents/skills/ui-craft/references/accessibility.md

file

5,751 bytes

e647d68d051d4260…

.agents/skills/ui-craft/references/agents.md

file

3,494 bytes

0678f51fcf6ed06e…

.agents/skills/ui-craft/references/ai-chat.md

file

10,867 bytes

2892b19a3ab2fdfe…

.agents/skills/ui-craft/references/brief.md

file

10,806 bytes

5ec247b71c8250f7…

.agents/skills/ui-craft/references/color.md

file

11,083 bytes

812013aba70d1a87…

.agents/skills/ui-craft/references/components.md

file

9,101 bytes

46a895d84e848ec2…

.agents/skills/ui-craft/references/copy.md

file

15,886 bytes

218582b5cde8d38d…

.agents/skills/ui-craft/references/coverage.md

file

42,703 bytes

b4543434311a60f8…

.agents/skills/ui-craft/references/craft-intent.md

file

10,914 bytes

dcd4a1e1844f53c0…

.agents/skills/ui-craft/references/dashboard.md

file

12,194 bytes

b1167163bb2bcee5…

.agents/skills/ui-craft/references/dataviz.md

file

11,765 bytes

b44b78e2ff035139…

.agents/skills/ui-craft/references/finish-bar.md

file

17,408 bytes

f9f0c9795e4598c6…

.agents/skills/ui-craft/references/forms.md

file

15,322 bytes

bb24e7cd3492dd5e…

.agents/skills/ui-craft/references/heuristics.md

file

18,707 bytes

bd90d71658e8a047…

.agents/skills/ui-craft/references/inspiration.md

file

14,132 bytes

7f2b8833e658d98a…

.agents/skills/ui-craft/references/layout.md

file

13,311 bytes

f92040b67d43de5e…

.agents/skills/ui-craft/references/loops.md

file

9,975 bytes

d76cc01cd1f85849…

.agents/skills/ui-craft/references/metadata.md

file

4,929 bytes

fa7f36915660de20…

.agents/skills/ui-craft/references/modern-css.md

file

16,962 bytes

adc2512778a20e2b…

.agents/skills/ui-craft/references/motion.md

file

23,952 bytes

5da3ce5ed0d4d581…

.agents/skills/ui-craft/references/personas.md

file

10,224 bytes

92af0ad1c9ae1f92…

.agents/skills/ui-craft/references/principles-catalog.md

file

32,316 bytes

db6459e0d468bb5d…

.agents/skills/ui-craft/references/recipe-auth.md

file

6,541 bytes

225ca94d236824dd…

.agents/skills/ui-craft/references/recipe-dashboard.md

file

9,542 bytes

0900100bf066f806…

.agents/skills/ui-craft/references/recipe-landing.md

file

13,991 bytes

9db79a40d1d34c82…

.agents/skills/ui-craft/references/responsive.md

file

5,706 bytes

658094521d0df690…

.agents/skills/ui-craft/references/review.md

file

18,561 bytes

360e32f7ef7bf3aa…

.agents/skills/ui-craft/references/sound.md

file

5,122 bytes

ef1587775b3ec062…

.agents/skills/ui-craft/references/spec.md

file

5,421 bytes

2c1664f1b92f5fbf…

.agents/skills/ui-craft/references/stack.md

file

21,787 bytes

69b7900527c9d390…

.agents/skills/ui-craft/references/state-design.md

file

8,886 bytes

3c1311c839cb05ab…

.agents/skills/ui-craft/references/themes.md

file

11,208 bytes

9570474567c3694c…

.agents/skills/ui-craft/references/tokens.md

file

14,433 bytes

0d4de718dc0c28f6…

.agents/skills/ui-craft/references/typography.md

file

14,550 bytes

f827718d0d7bb227…

.agents/skills/ui-craft/SKILL.md

skill

38,442 bytes

581bce5c1772929b…

.agents/skills/unhappy/SKILL.md

skill

3,686 bytes

ab8d6a0cd93b504d…

.claude-plugin/marketplace.json

file

798 bytes

2d72966e2621ac80…

.claude-plugin/plugin.json

file

704 bytes

950c75e3e21a6fc5…

.claude/skills/friction-log/SKILL.md

skill

6,505 bytes

45728dde97fe1d00…

.codex-plugin/plugin.json

plugin-manifest

1,651 bytes

8ad30464ff6f24fc…

.codex/skills/adapt/SKILL.md

skill

3,086 bytes

5861243d8b0c0211…

.codex/skills/animate/SKILL.md

skill

2,453 bytes

aa58997e1c07657f…

.codex/skills/audit/SKILL.md

skill

3,892 bytes

f8fbfd748efd3d23…

.codex/skills/bolder/SKILL.md

skill

2,464 bytes

69b985c31df16ab1…

.codex/skills/brief/SKILL.md

skill

4,604 bytes

874dcc6608bebaa1…

.codex/skills/clarify/SKILL.md

skill

2,826 bytes

52e5b229ca040da1…

.codex/skills/colorize/SKILL.md

skill

3,276 bytes

22f12b7297fb4f8b…

.codex/skills/craft/SKILL.md

skill

6,528 bytes

a6db8454a8482df1…

.codex/skills/critique/SKILL.md

skill

4,615 bytes

53b3014230a8d836…

.codex/skills/delight/SKILL.md

skill

2,768 bytes

1b95c69b8997a532…

.codex/skills/distill/SKILL.md

skill

3,196 bytes

958c3ce6a3c72de3…

.codex/skills/extract/SKILL.md

skill

2,920 bytes

31c80d52df9c8d73…

.codex/skills/finalize/SKILL.md

skill

7,883 bytes

6b7ab59c54333e06…

.codex/skills/harden/SKILL.md

skill

4,529 bytes

2273e4c62d92212e…

.codex/skills/heuristic/SKILL.md

skill

4,179 bytes

3e5dddcb6bcc515d…

.codex/skills/polish/SKILL.md

skill

2,482 bytes

9b4efbc577cdd243…

.codex/skills/quieter/SKILL.md

skill

2,102 bytes

4b29eb67400c0e69…

.codex/skills/redesign/SKILL.md

skill

4,058 bytes

6de04099438cbf60…

.codex/skills/remember/SKILL.md

skill

2,350 bytes

6ce04af8b57b0a49…

.codex/skills/sddesign/SKILL.md

skill

6,313 bytes

20fd12ad5e2f9699…

.codex/skills/shape/SKILL.md

skill

7,144 bytes

36e90f8de8d64620…

.codex/skills/start/SKILL.md

skill

5,885 bytes

3bc48d436214856d…

.codex/skills/tokens/SKILL.md

skill

5,692 bytes

eefb8d59d4b739b4…

.codex/skills/typeset/SKILL.md

skill

4,368 bytes

f6bdfe8c6544473f…

.codex/skills/ui-craft-dense-dashboard/SKILL.md

skill

5,634 bytes

55e9131a3aa2dab4…

.codex/skills/ui-craft-editorial/SKILL.md

skill

5,266 bytes

05500a88dba4a20c…

.codex/skills/ui-craft-minimal/SKILL.md

skill

4,822 bytes

71c09ea690441189…

.codex/skills/ui-craft/references/accessibility.md

file

5,751 bytes

e647d68d051d4260…

.codex/skills/ui-craft/references/agents.md

file

3,494 bytes

0678f51fcf6ed06e…

.codex/skills/ui-craft/references/ai-chat.md

file

10,867 bytes

2892b19a3ab2fdfe…

.codex/skills/ui-craft/references/brief.md

file

10,806 bytes

5ec247b71c8250f7…

.codex/skills/ui-craft/references/color.md

file

11,083 bytes

812013aba70d1a87…

.codex/skills/ui-craft/references/components.md

file

9,101 bytes

46a895d84e848ec2…

Browse all 664 files

ui-craft — Frequently asked questions

What is ui-craft?
ui-craft is an AI plugin in the HOL registry. Design engineering skill collection for AI coding agents with slash commands, review agents, and MCP quality gates.
How do I install ui-craft?
Install ui-craft in your harness: Claude Code — /plugin marketplace add educlopez/ui-craft; Cursor — npx [email protected] add educlopez/ui-craft; MCP — git clone https://github.com/educlopez/ui-craft. Full step-by-step guidance is on the HOL plugin page.
How do I install ui-craft in HOL Guard?
To install ui-craft in HOL Guard, start with hol-guard plugin install eduardo-calvo/ui-craft --apply. The complete step-by-step install guide for HOL Guard is on the HOL plugin page.
How do I install ui-craft in Claude Code?
To install ui-craft in Claude Code, start with /plugin marketplace add educlopez/ui-craft. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How do I install ui-craft in Cursor?
To install ui-craft in Cursor, start with npx [email protected] add educlopez/ui-craft. The complete step-by-step install guide for Cursor is on the HOL plugin page.
How is the Trust Score for ui-craft computed?
ui-craft has a HOL Trust Score of 79 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/eduardo-calvo%2Fui-craft/trust
Who publishes ui-craft?
ui-craft is published by Eduardo Calvo and listed on HOL.

Directory acceptance

Listed in 0 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

Install signal

HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.

Install commands issued here
<5
HOL Guard install commands issued from this listing, last 28 days.
Opt-in install reports
<10
Machines that reported installing it through HOL Guard in week 2026-W46. Reporting is opt-in, so most installs are not counted.
HOL Guard workspaces
<5
Workspaces that approved it or include it in an approved-plugin feed, as of today.

Reviews and similar plugins