figma-pencil-fsd-tailwind4

figma-pencil-fsd-tailwind4 is a skill for Claude Code, Codex from JohnWayneeee/ai-agent-skills. It costs 79 tokens per session (1,994 once invoked), scanned A, original, MIT.

A workflow for turning Figma or Pencil interface designs into frontend code using Feature-Sliced Design and Tailwind CSS. Feature-Sliced Design is a way to organise code into layers such as shared components, features, pages, and application structure.

In plain words
What is it for?
Use it to implement screens from design files, extract visual tokens, place code in the correct architectural layers, reuse an existing component library, and keep responsive and accessible frontend behaviour consistent.
Why use it?
It connects the visual design to the existing codebase without ignoring its architecture, design tokens, reusable components, or accessibility needs. It also accounts for projects that separate server-side and browser-side code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to implement screens from design files, extract visual tokens, place code in the correct architectural layers, reuse an existing component library, and keep responsive and accessible frontend behaviour consistent.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/johnwayneeee/ai-agent-skills/figma-pencil-fsd-tailwind4
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 JohnWayneeee/ai-agent-skills --skill figma-pencil-fsd-tailwind4
Clone the repo
git clone --depth 1 https://github.com/JohnWayneeee/ai-agent-skills

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 figma-pencil-fsd-tailwind4

README.md
[![agentmods](https://agentmods.dev/badge/skills/johnwayneeee/ai-agent-skills/figma-pencil-fsd-tailwind4/github.svg)](https://agentmods.dev/skills/johnwayneeee/ai-agent-skills/figma-pencil-fsd-tailwind4)
Your own site
<a href="https://agentmods.dev/skills/johnwayneeee/ai-agent-skills/figma-pencil-fsd-tailwind4"><img src="https://agentmods.dev/badge/skills/johnwayneeee/ai-agent-skills/figma-pencil-fsd-tailwind4/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 figma-pencil-fsd-tailwind4

Your own site · 80×15
<a href="https://agentmods.dev/skills/johnwayneeee/ai-agent-skills/figma-pencil-fsd-tailwind4"><img src="https://agentmods.dev/badge/skills/johnwayneeee/ai-agent-skills/figma-pencil-fsd-tailwind4.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,994 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 $0.00079 $0.01994
Opus 5 $0.00039 $0.00997
Sonnet 5 $0.00016 $0.00399
Haiku 4.5 $0.00008 $0.00199

Measured 10d ago against content hash 03e856c98952, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

figma-pencil-fsd-tailwind4 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 10d 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.

skills/figma-pencil-fsd-tailwind4/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Figma / Pencil to FSD + Tailwind 4

Turn design files into code without breaking the host repository's architecture, design system, or accessibility guarantees. This skill is framework-agnostic; the rules below apply equally to any modern React stack and degrade gracefully when optional pieces (RSC, primitive library, FSD linter) are missing.

Assumptions

This skill works in any frontend repository that satisfies:

  • A modern component-based framework (React, or any framework with a comparable component model).
  • Tailwind CSS. Token rules target v4 (CSS-first, @theme, OKLCH). For v3 projects, fall back to the project's existing config and skip v4-only sections.
  • Feature-Sliced Design (or a comparable layered architecture). Layer names may vary by repository; the canonical names are app, pages, widgets, features, entities, shared.
  • A primitive component library is optional. When one is present (shadcn/ui, Radix, Mantine, Headless UI, or any in-house design system), reuse it instead of re-implementing primitives.
  • Server / Client component split is optional. The RSC guidance applies only when the project uses a framework with that distinction.

If any assumption does not hold, defer to the host repository's contract first.

Workflow

  1. Check for a repository contract before generating code. See references/project-contracts.md. Local rules override every default in this skill.
  2. Scope the work to one frame, screen, or component. Refuse "translate the whole file".
  3. Analyze the design: tokens, components, layout intent, repeated patterns, states.
  4. Decompose into FSD layers on paper before writing code. Decide Server vs Client boundaries only if the host framework uses them. See references/fsd-mapping.md and references/rsc-boundaries.md.
  5. Reconcile design variables with project tokens. Do not silently add new tokens. See references/tailwind-tokens.md.
  6. Reuse existing primitives from the project's component library before creating new ones in shared/ui.
  7. Generate code layer by layer: shared primitives → entitiesfeatureswidgetspagesapp-shell (when present) → app. Keep route entries thin.
  8. Implement every state shown in the design plus the standard ones: default, hover, focus-visible, active, disabled, loading, empty, error.
  9. Verify accessibility against references/accessibility-checklist.md.
  10. Run the validation checklist below before reporting the task complete.

Read the full file on GitHub · 139 lines

Files

What ships with it

8 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. 10d ago First seen · 139 lines · 79 tokens per session scan A 03e856c98952

Subscribe to this mod's changes

figma-pencil-fsd-tailwind4 is a skill published in the GitHub repository JohnWayneeee/ai-agent-skills (1 stars, last pushed 3mo ago), licensed MIT. It adds 79 tokens to every session and 1,994 once invoked, about $0.0004 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

frontend-design

Design and build production-ready frontend interfaces with design systems, responsive layouts, accessible components, and dark mode support. Use when the user requests frontend design or provides relevant inputs for this workflow.

seb1n/awesome-ai-agent-skills · 40 tokens

antigravity-design-expert

Core UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmorphism-based web interfaces using GSAP and 3D CSS.

sickn33/agentic-awesome-skills · 39 tokens

shopify-theme-optimization

Theme speed and UX optimization — Core Web Vitals, Liquid code, image loading, mobile responsiveness.

nexscope-ai/eCommerce-Skills · 25 tokens

color-palette-generator

Create an HTML color palette from a mood, description, or image, with swatches, color codes, pairings, and contrast checks. Use for color schemes or brand colors.

AlpacaLabsLLC/skills-for-architects · 41 tokens

slop-eval

Objectively evaluate a UI/web design against the pols.dev anti-slop design law: detect catalogued slop tells with cited evidence, score 8 weighted axes (color, type, components, layout, motion, execution, signature, cohesion), and emit a Slop Report with a 0–100 Slop Index and grade. Use when the user asks to…

fabricioctelles/skills · 142 tokens

brand-visual-language

A brand's visual tone — playful or serious, rounded or angular — should be consistent across all UI elements. Shape language in typography, border-radius, and iconography communicates personality before a single word is read. Use when establishing a design system, choosing icon libraries, setting border-radius tokens…

dembrandt/dembrandt-skills · 68 tokens