Design Skill

Design Skill is a skill for Claude Code, Codex from WyvernCW/Monich. It costs 25 tokens per session (9,003 once invoked), scanned A, original, MIT.

A routing guide for design-related HTML work that chooses the appropriate design, reference, generation, or export guidance. HTML is the markup used to structure web pages.

In plain words
What is it for?
Use it when a request involves designing an HTML artifact, selecting a design system, generating reusable design guidance, or exporting the result.
Why use it?
It helps an agent decide which design instructions apply before creating or packaging an artifact. It also keeps generated HTML organized for later edits.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/wyverncw/monich/web-template
Any agent
npx skills add WyvernCW/Monich --skill web-template
Clone the repo
git clone --depth 1 https://github.com/WyvernCW/Monich

Made for: Claude Code, Codex.

Wrote this? Show the measurements

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

agentmods badge for Design Skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/wyverncw/monich/web-template.svg)](https://agentmods.dev/skills/wyverncw/monich/web-template)
Your own site
<a href="https://agentmods.dev/skills/wyverncw/monich/web-template"><img src="https://agentmods.dev/badge/skills/wyverncw/monich/web-template.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,003 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00025 $0.09003
Opus 5 $0.00013 $0.04501
Sonnet 5 $0.00005 $0.01801
Haiku 4.5 $0.00003 $0.00900

Measured 5d ago against content hash 1f90a7380207, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Design Skill 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 5d ago.

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

Nothing flagged

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

installable/monich/assets/templates/web-template/SKILL.md · 594 lines

How it starts

The opening of the file, as written. The whole thing — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Skill

Design Skill is the router for design-related HTML artifact work.

It decides:

  • whether the task is design-related
  • which artifact skill should be primary
  • whether the task should use design-system-reference.md
  • whether the task should use design-system-generation.md
  • whether the task should use export.md
  • how much clarification is needed before acting
  • how to read the request quickly before routing (see "Before generating")
  • how to apply built-in design quality defaults
  • how to keep generated HTML structured for future edits

Design Skill should stay small.

Artifact-specific structure rules belong in artifact skill files. Business judgment for a scenario lives inside that scenario skill. Cross-cutting craft rules belong in horizontal-craft/. Reference selection belongs in design-system-reference.md. DESIGN.md import / extraction / persistence belongs in design-system-generation.md. Export / package / handoff belongs in export.md.

The default first-stage deliverable is a design artifact, usually HTML unless the selected artifact skill or export target requires a fixed-image, deck, package, or design-system spec. Export is invoked when the user asks to package, download, convert, or hand off the current artifact.

The flow (read this once; it governs everything below)

The whole skill is one flow. Most of it is internal and instant — it only pauses when a request is genuinely ambiguous. Do not turn any step into a form to fill or a file you must read first.

USER REQUEST
   │
   ▼
1. UNDERSTAND (internal, silent for obvious requests) — resolve three axes in parallel:
     • content  — subject, information, goal
     • scenario — form + intent  → which scenario skill   (see Routing)
     • style    — what kind of style cue, if any           (see Style Routing)
   Obvious on all three → proceed. Only ONE axis genuinely unclear → ask one focused question.
   For open-ended / creative requests, understanding also includes a creative read, not just these
   operational axes — complete the creative context + Design Read (see §Creative Context Completion).
   │
   ▼
1.5 CHECK TEMPLATES (do this by default, not only when asked)
   Scan `design-templates/INDEX.md` by carrier + scenario for a match to the request.
     • Clear match  → adopt it as the starting point; read that template's SKILL.md. Using a
                      matching template usually raises quality — prefer it over designing from scratch.
     • No good match → proceed with the scenario skill directly. Never force a template that doesn't fit.
   A template is a starting structure/skeleton, not a page to clone — keep the user's real content,
   apply the scenario skill + horizontal craft, do not copy the reference's exact layout fingerprint.
   │
   ▼
2. FILL STYLE BY PRIORITY (per dimension: color · type · layout · icons · spacing tokens)
   For each dimension, take it from the highest-priority source that covers it:
     1) user's immediate description   ← highest; dimensions it touches are locked
     2) design system (DESIGN.md)      ← fills dimensions the user didn't speak to
     3) template / seed                ← fills what's left (esp. layout scaffold)
     4) parallel constraints           ← fallback for any still-empty dimension
        (load only the ones you need: type / icons / color / a11y …)
   Sources combine — e.g. design-system tokens + a template's layout is normal.
   Style cue is a vague mood word, not a named system ("清新/简约/高级/科技感/复古/温暖/极简/
   赛博" etc.): do NOT just free-associate a look — match it to the library. Read
   `design-systems/style-skills` index (and brand `index.json`) and pick the entry whose `mood` /
   `formality` / `scheme` tags best fit the words, then use it as the base. The style tags are the
   bridge from a user's adjective to a concrete system (e.g. 清新简约 → 极简/克制 → `minimal`/`clean`;
   高级 → 奢华/克制 → `luxury`/`refined`; 科技感 → 技术感/未来 → `futuristic`/`hud`). Only design
   from scratch if nothing in the library fits the mood.
   No style cue at all + scene is restrained / not creativity-driven (tool, dashboard, admin,
   form, report, notice, generic SaaS/corporate page): do NOT design a style from scratch —
   actively pick a mature baseline from `design-systems/` (see Mature System Fallback) so the
   result is professional and consistent. (Expressive scenes that want a distinct look skip this
   and go bold per §Creative Context.)
   Conflict: if the user's description contradicts the design system on a dimension,
   the user wins on that dimension — AND say so in one line
   ("Built it <X> as you asked; note this differs from the attached design system —
    tell me if you'd rather keep the system's direction.")
   │
   ▼
3. BUILD using the scenario skill's judgment + the filled style.
   │
   ▼
4. QUALITY GATE — run quality-gate.md as a thin final checklist before delivering.

Read the full file on GitHub · 594 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. 5d ago First seen · 594 lines · 25 tokens per session scan A 1f90a7380207

Subscribe to this mod's changes

Design Skill is a skill published in the GitHub repository WyvernCW/Monich (3 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 9,003 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens