A guide for turning Figma designs into working user interfaces and comparing an implementation with the design. Figma is a collaborative design tool that stores layouts, styles, components, and design values.

Use it for Figma-based frontend implementation, design gap analysis, visual comparison, and planning UI work from Figma files or node links.

It helps reduce guesswork when matching an interface to its design and provides a structured way to find visual differences. It relies on a working Figma connection.

using-figma — Skill for Claude Code and Codex by vladolaru: A guide for turning Figma designs into working user…

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/vladolaru/claude-code-plugins/using-figma

Any agent

npx skills add vladolaru/claude-code-plugins --skill using-figma

Clone the repo

git clone --depth 1 https://github.com/vladolaru/claude-code-plugins

Made for: Claude Code, Codex.

Or install pirategoat-tools, the plugin that ships this one along with the rest of its 22 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vladolaru/claude-code-plugins/using-figma.svg)](https://agentmods.dev/skills/vladolaru/claude-code-plugins/using-figma)

Your own site

<a href="https://agentmods.dev/skills/vladolaru/claude-code-plugins/using-figma"><img src="https://agentmods.dev/badge/skills/vladolaru/claude-code-plugins/using-figma.svg" alt="Measured on agentmods" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,862 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.

Model	Per session	Once invoked
Fable 5	$0.00070	$0.03862
Opus 5	$0.00035	$0.01931
Sonnet 5	$0.00014	$0.00772
Haiku 4.5	$0.00007	$0.00386

Measured yesterday against content hash 84b3b80b3de9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

using-figma 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 yesterday.

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.

plugins/pirategoat-tools/skills/using-figma/SKILL.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Directory

Resolve SKILL_DIR to the absolute directory containing this SKILL.md, as shown by the current host, before using any bundled path below. Before a shell command uses $SKILL_DIR, assign it in that command or replace it with the resolved path. It is not a host-exported environment variable.

Using Figma for Implementation

You are a design-to-code specialist. Your job: translate Figma designs into production code with high fidelity by building a structured specification before writing any code.

Why this workflow matters — measured across 4 real sessions:

Survey-first: 0 factual corrections, 6% call waste
No survey (reactive): 17 user corrections, 18% call waste
Screenshot-only implementation: 100% of guessed values were wrong
Sessions without get_variable_defs: 4/4 had repeated token mismatches

When to Use

Implementing UI from Figma designs (new features or design polish)
Comparing live implementation against Figma (gap analysis)
Planning implementation of Figma-based designs
Any task where a Figma URL or node ID is referenced

When NOT to Use

Pure codebase exploration with no Figma reference

Figma URL Parsing

Extract fileKey and nodeId from Figma URLs:

URL format: https://figma.com/design/:fileKey/:fileName?node-id=1-2

fileKey: segment after /design/
nodeId: value of node-id query param (use as-is, with the hyphen)

Example: https://figma.com/design/kL9xQn2VwM8pYrTb4ZcHjF/DesignSystem?node-id=42-15 → fileKey=kL9xQn2VwM8pYrTb4ZcHjF, nodeId=42-15

Asset Handling

All assets come from Figma MCP's built-in endpoint:

Use localhost URLs from Figma MCP responses directly as image/SVG sources
Source all icons and images exclusively from the Figma payload
Use the actual asset URL immediately — a localhost source is a ready asset, not a placeholder

Iron Rules

Foundation (violations derail the entire session)

RULE 0: Call get_variable_defs at session start and cache the result. Without it, tokens are discovered ad-hoc → hardcoded values → 2+ user corrections.

Read the full file on GitHub · 316 lines

Files

What ships with it

1 file 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.

references/design-spec-template.md 3.4 KB

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.

yesterday First seen · 316 lines · 70 tokens per session scan A 84b3b80b3de9

Subscribe to this mod's changes

using-figma is a skill published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 3,862 once invoked, about $0.0003 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.

Design and UX Frontend

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

hallmark

Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.

Nutlope/hallmark · 61 tokens

using-figma