agentmods.dev

sk-design

sk-design is a skill for Claude Code, OpenCode from MichelKerkmeester/skilled-agent-harness_spec-driven-loops. It costs 31 tokens per session (2,489 once invoked), scanned A, original, MIT.

A set of rules for designing and reviewing user interfaces, including visual scales, interaction behavior, animation, and accessibility checks.

In plain words
What is it for?
Use it when building, fixing, or reviewing screens, components, CSS, interactions, and motion.
Why use it?
It replaces arbitrary design choices with consistent values and checks whether the interface behaves clearly and meets WCAG accessibility guidance.

Skill for Claude CodeOpenCode

Written for Claude Code and OpenCode: allowed-tools in frontmatter, but also installed under .opencode/. Also seen: mentions OpenCode.

not rated 35repo +1 changed 3d ago A scan SkillSpector: pass 31 tokens original MIT

Good fit Use it when building, fixing, or reviewing screens, components, CSS, interactions, and motion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-design
View source ↗ MichelKerkmeester/skilled-agent-harness_spec-driven-loops
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add MichelKerkmeester/skilled-agent-harness_spec-driven-loops --skill sk-design
Clone the repo
git clone --depth 1 https://github.com/MichelKerkmeester/skilled-agent-harness_spec-driven-loops

Made for: Claude Code, OpenCode.

Wrote this? Show the measurements

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

agentmods badge for sk-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-design/github.svg)](https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-design)
Your own site
<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-design"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-design/github.svg" alt="Measured on agentmods" height="20"></a>

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

agentmods 80×15 button for sk-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-design"><img src="https://agentmods.dev/badge/skills/michelkerkmeester/skilled-agent-harness_spec-driven-loops/sk-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,489 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

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

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.02489
Opus 5 $0.00015 $0.01244
Sonnet 5 $0.00006 $0.00498
Haiku 4.5 $0.00003 $0.00249

Measured 3d ago against content hash 274e97db5e03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sk-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (shared/scripts/render-screenshots.cjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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

Nothing flagged

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

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.opencode/skills/sk-design/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design (parent hub)

sk-design is a parent hub. It carries no procedure of its own: it decides which mode owns the decision in front of you and hands over. The work lives in the modes.

1. WHEN TO USE

Use this hub when the question is what a surface should look like, why it looks wrong, or what visual artifact answers it: spacing, type, colour, contrast, hierarchy, a review of an existing surface against design criteria, a data chart, or a process diagram. The surface can be screen UI, a slide deck, a printed page or a document layout.

When NOT to Use

  • Measuring a surface that already exists into a written specification. That is this hub's EXTRACT mode, reached by naming the source; it is not the values path.
  • Authoring documentation prose. sk-doc owns that, including READMEs, changelogs and playbooks.
  • Implementing the values once decided. sk-code owns the code that renders them; this hub decides what they should be and never writes the component.
  • A canvas question that names its own form. A chart or diagram request goes to its mode directly rather than through the values mode.

2. SMART ROUTING

Routing is registry-driven at runtime and mode-authored at source, in two stages. Stage 1 (hub → mode): the advisor scores this hub as one identity, then mode-registry.json and hub-router.json pick the mode without re-deriving mappings during a request. Stage 2 (mode → leaves): the root ROUTER.md maps the design intent to the exact mode-local resources that mode loads. The two layers stay separate: the hub never emits leaf paths, and the surface router never re-decides the mode.

Compiled routing: not yet. The other five hubs resolve through a compiled router contract first (node .opencode/bin/compiled-route.cjs --hub <id> --prompt "<task>"). This hub is not in that closure: the same call returns {"servingAuthority":"legacy","hubId":"sk-design"}, so the routing below is the only path. Joining needs a rollout package mirroring the five that exist plus registration in the engine's hub table and the guard's hub list. Until then, do not quote a compiled decision for this hub, because there is not one.

Read the full file on GitHub · 205 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

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

  1. 3d ago Changed · +127 lines 274e97db5e03
  2. 4d ago Changed · -424 lines · +4 tokens per session 6bbb2cf14d43
  3. 8d ago First seen · 502 lines · 27 tokens per session scan A 02b052080540

Subscribe to this mod's changes

sk-design is a skill published in the GitHub repository MichelKerkmeester/skilled-agent-harness_spec-driven-loops (35 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 2,489 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

CSS and stylingDesign and UXFrontend
Related

Other skills, from other repositories

chakra-ui-builder

Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…

chakra-ui/chakra-ui · 214 tokens

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 50 tokens

frontend-ui-dark-ts

Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.

microsoft/skills · 48 tokens

reveal-hover-effect

Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…

MengTo/Skills · 66 tokens

frontend-visual-qa

Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…

daymade/claude-code-skills · 145 tokens

prototype-web

A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.

nexu-io/html-anything · 24 tokens