figma-implement

A workflow for turning downloaded Figma design data into a working Tailwind CSS interface. Figma is a design tool, while Tailwind CSS is a system of reusable styling classes.

In plain words
What is it for?
Implementing Figma frames, converting designs to Tailwind classes, mapping design layers to components, and validating reusable UI components.
Why use it?
It helps developers translate exact design layers, fonts, colors, borders, and spacing into code and check the result in Storybook and a live page.

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/p2ergmbh/agentic-coding/figma-implement
Any agent
npx skills add P2ERGmbH/agentic-coding --skill figma-implement
Clone the repo
git clone --depth 1 https://github.com/P2ERGmbH/agentic-coding

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,746 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 $0.00041 $0.04746
Opus 5 $0.00020 $0.02373
Sonnet 5 $0.00008 $0.00949
Haiku 4.5 $0.00004 $0.00475

Measured 2d ago against content hash 4f5c96795eda, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

figma-implement 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 2d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/compile-component-map.mjs, scripts/generate-figma-css.mjs, scripts/parse-figma-vars.mjs), 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.

.agents/skills/figma-implement/SKILL.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Figma Layout Implementation Workflow

This skill guides you through implementing precise Figma designs by parsing Figma design tokens (JSON + CSS) into Tailwind utility classes, building a component-to-layer map, and verifying via Storybook and live page testing.

Trigger

Use this skill when the user asks to "implement a Figma design", "convert Figma to Tailwind", "use the reusable figma implementation solution", or "build a component from a Figma frame".


Phase 1: Requirements Gathering

Before any download or implementation work, gather the following using ask_user_question:

1.1 Figma Source

Ask the user for:

  • Figma URL or file key + node ID — the exact frame/layer to implement.
  • Component name — the kebab-case name for the React component (e.g., product-card).

1.2 Search for Existing Matching Components

After receiving the component name, search the codebase for existing components that might correspond:

  • Search for files/components matching the name (glob for **/[ComponentName]*.tsx)
  • Search for existing Figma references in .stories.tsx files that reference a similar URL/node
  • Search for existing @figma-layer annotations that mention the layer name

If matches are found, you MUST explicitly present the exact matching component files that were found to the user in the chat interface. Propose updating the existing component rather than creating a new one.

1.3 Implementation Mode

When an existing component is found, you MUST explicitly ask the user if they want a pixel-perfect design or an incremental layout improvement (e.g., "Do you want a pixel-perfect match or an incremental layout improvement?"). Do not make this decision without seeking their explicit choice.

Mode Description
New component The component doesn't exist yet — create from scratch.
Improve existing layout The component exists; adjust spacing, colors, typography to better match the design while keeping the current structure.
Pixel-perfect replacement The component exists but should be rewritten entirely to match the Figma frame exactly, discarding the current layout in favor of the figma design.

Read the full file on GitHub · 294 lines

Files

What ships with it

4 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. 2d ago First seen · 294 lines · 41 tokens per session scan A 4f5c96795eda

Subscribe to this mod's changes

figma-implement is a skill published in the GitHub repository P2ERGmbH/agentic-coding (9 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 4,746 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 2026-08-31.

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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens