webkit: Skill for Claude Code

.claude/skills/code-connect-write/SKILL.md

code-connect-write is a skill for Claude Code from aziontech/webkit. It costs 32 tokens per session (1,331 once invoked), scanned A, original, MIT.

A guide for creating a Figma Code Connect file, which links designs in Figma to their Vue component code. It maps design variants and content areas to component props and children.

In plain words
What is it for?
Use it after creating a component when the project has the Figma Code Connect package installed and the component needs a Figma-to-code mapping.
Why use it?
It removes the need to manually explain how a Figma design corresponds to the implementation. The mapping can also provide the code example shown in Figma's developer view.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is aziontech/webkit's own configuration. It tells Claude Code how to work on webkit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything webkit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aziontech/webkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aziontech/webkit/main/.claude/skills/code-connect-write/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aziontech/webkit

Made for: Claude Code.

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 code-connect-write

README.md
[![agentmods](https://agentmods.dev/badge/skills/aziontech/webkit/code-connect-write/github.svg)](https://agentmods.dev/skills/aziontech/webkit/code-connect-write)
Your own site
<a href="https://agentmods.dev/skills/aziontech/webkit/code-connect-write"><img src="https://agentmods.dev/badge/skills/aziontech/webkit/code-connect-write/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 code-connect-write

Your own site · 80×15
<a href="https://agentmods.dev/skills/aziontech/webkit/code-connect-write"><img src="https://agentmods.dev/badge/skills/aziontech/webkit/code-connect-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,331 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.
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 $0.00032 $0.01331
Opus 5.5 $0.00013 $0.00532
Sonnet 5.5 $0.00006 $0.00266
Haiku 4.5 $0.00003 $0.00133

Measured today against content hash 1ec4dbc9000d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-connect-write 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 today.

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.

.claude/skills/code-connect-write/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: code-connect-write

Purpose

Map Figma variants (kind / size / state) → Vue props, Figma slots → Vue children, and emit the snippet Dev Mode shows in the Figma file. The file lives next to the .vue at packages/webkit/src/components/<category>/<name>/<name>.figma.ts.

When to invoke

  • Step 6 of /component-create, after the scaffolder and storybook-write succeeded.

Inputs

  • The full text of .specs/<name>.md (Props, Events, Slots, States).
  • The spec's figma.node_id (frontmatter).
  • The orchestrator's confirmation that @figma/code-connect is installed (check packages/webkit/package.json).

Workflow

  1. Pre-flight. If @figma/code-connect is not in packages/webkit/package.json devDependencies, emit SKIPPED: @figma/code-connect not installed and exit. The orchestrator records this as a pending item.

  2. Load prerequisite skill. Invoke figma:figma-code-connect (mandatory before any Code Connect tool call).

  3. Read the Figma properties. Call get_context_for_code_connect on the spec's figma.node_id. It must be a COMPONENT or COMPONENT_SET; a frame id is a spec defect → BLOCKED: figma.node_id is not a component. Property names are case-sensitive and are copied verbatim. Webkit Figma properties mirror the code: names are lowerCamelCase (showIcon, state, modelValue) and variant options are lowercase (size=large, disabled=true). A capitalized or spaced name in Figma is a library defect to report, not a name to copy.

  4. Write <name>.figma.ts as a parserless template — never figma.connect(), never @figma/code-connect/html, never a .vue import:

    // url=https://www.figma.com/design/<fileKey>/<FileName>?node-id=<X-Y>
    // source=https://github.com/aziontech/webkit/blob/main/packages/webkit/src/components/<category>/<name>/<name>.vue
    // component=<PascalName>
    import figma from 'figma'
    
    const instance = figma.selectedInstance
    
    const label = instance.getString('label')
    const kind = instance.getEnum('kind', {
      primary: 'primary',
      secondary: 'secondary'
    })
    const disabled = instance.getEnum('disabled', {
      false: false,
      true: true
    })
    
    export default {
      example: figma.code`<<PascalName>
      label="${label}"${kind === 'primary' ? '' : figma.code`
      kind="${kind}"`}${disabled ? figma.code`
      disabled` : ''}
    />`,
      imports: ["import <PascalName> from '@aziontech/webkit/<name>'"],
      id: '<name>',
      metadata: { nestable: true }
    }
    

Read the full file on GitHub · 94 lines

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. today Changed · +11 lines 1ec4dbc9000d
  2. 2mo ago First seen · 83 lines · 32 tokens per session scan A 68d87e7b07c6

Subscribe to this mod's changes

code-connect-write is a skill published in the GitHub repository aziontech/webkit (3 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,331 once invoked, about $0.0001 per session on Opus 5.5. 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

shadcn-vue

Manages shadcn-vue components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn-vue, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for…

unovue/shadcn-vue · 97 tokens

design-component

Design a UI component spec to the house quality bar (anatomy, variants, sizes, the 8 states, token mapping, and accessibility). Use when the user wants to design or document a component (button, input, tabs, toast, combobox, date picker, modal, etc.) at the spec level before or alongside code. For generating framework…

plugin87/ux-ui-agent-skills · 81 tokens

design-doctrine

The house rules for ANY design or UI work - the verification protocol (run the gate, never claim a number), the absolute no-emoji rule, token by intent, one shared theme, the eight states, one thing leads, and output completeness. Load this FIRST whenever building, reviewing, or theming a screen, component, or token…

plugin87/ux-ui-agent-skills · 92 tokens

design-screen

Design or build a page, screen, landing page, website, app or UI from a request - the whole job, end to end. Use this for "design a landing page", "build a settings screen", "make me a website", "design the onboarding", "ออกแบบหน้าเว็บ", "ทำหน้า landing", "ออกแบบ UI", "ทำแอป". It runs the pipeline no single skill…

plugin87/ux-ui-agent-skills · 151 tokens

critique

Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.

plugin87/ux-ui-agent-skills · 37 tokens

scaffold-project

Scaffold a new design-product project that matches the recommended Claude Code layout (the reference structure). Use when starting a fresh product/app that will be built with this design system.

plugin87/ux-ui-agent-skills · 39 tokens