figma-local-bridge: Skill for Claude Code

.claude/skills/talk-to-figma-design/SKILL.md

talk-to-figma-design is a skill for Claude Code from Takeaki0817/figma-local-bridge. It costs 164 tokens per session (6,489 once invoked), scanned A, original, MIT.

A skill for creating and editing Figma designs through the TalkToFigma MCP bridge, which connects an agent to the Figma design canvas.

In plain words
What is it for?
Use it when generating screens, landing pages, wireframes or layouts, or when editing text, nodes and Auto Layout in Figma.
Why use it?
It defines the connection checks and operating rules needed to avoid editing the wrong file or losing communication with the Figma plugin.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Takeaki0817/figma-local-bridge's own configuration. It tells Claude Code how to work on figma-local-bridge 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 figma-local-bridge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Takeaki0817/figma-local-bridge. 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/Takeaki0817/figma-local-bridge/main/.claude/skills/talk-to-figma-design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Takeaki0817/figma-local-bridge

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 talk-to-figma-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/takeaki0817/figma-local-bridge/talk-to-figma-design/github.svg)](https://agentmods.dev/skills/takeaki0817/figma-local-bridge/talk-to-figma-design)
Your own site
<a href="https://agentmods.dev/skills/takeaki0817/figma-local-bridge/talk-to-figma-design"><img src="https://agentmods.dev/badge/skills/takeaki0817/figma-local-bridge/talk-to-figma-design/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 talk-to-figma-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/takeaki0817/figma-local-bridge/talk-to-figma-design"><img src="https://agentmods.dev/badge/skills/takeaki0817/figma-local-bridge/talk-to-figma-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,489 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 $0.00164 $0.06489
Opus 5 $0.00082 $0.03245
Sonnet 5 $0.00033 $0.01298
Haiku 4.5 $0.00016 $0.00649

Measured 11d ago against content hash 71a7d9a04bcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

talk-to-figma-design 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 11d 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.

.claude/skills/talk-to-figma-design/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TalkToFigma デザイン生成スキル

TalkToFigma MCP は Figma Plugin API を WebSocket 経由で叩く。ツールは薄いラッパーなので、 呼び出し順序と Plugin API の制約を知っているかどうかが成果物の品質を決める。

0. 接続(毎回最初に)

  1. join_channel でプラグインUIのチャンネル名に接続する。デフォルトは figma-local-bridge(プラグインUIのConnectionタブで変更・永続化できる)。既定値と異なる名前を使っている場合はタスク指示に含まれる。
  2. 接続確認のために get_document_info 等の全体read系を呼ばない(トークン浪費)。join成功メッセージで十分。
  3. 注意: プラグインのウィンドウが閉じられると即切断される。しかも join_channel はプラグイン不在でも成功する(サーバーがチャンネルを作るだけ)ため、切断に気づけない。ツール呼び出しがタイムアウトしたら、リトライを重ねる前に「プラグインウィンドウが開いているか・チャンネル名が一致しているか」の確認をユーザーに依頼する。
    • プラグインはアクティブタブでしか通信できない。対象ファイルのタブが背面に回る(別タブ・別アプリへ切替)と通信は止まる。作業ウィンドウの確保(対象タブを前面に保つ時間帯)を段取りに織り込む。
    • 接続確認はログでなく TCP 実体で行う。リレーログの「join / broadcast 成功」は自分のクライアント(MCP・診断プローブ)を peer として数えるため誤検出する。lsof -nP -iTCP:3055 でプラグイン由来の接続(プロセス名・ポート)が実在するかを確認するのが唯一確実。
  4. 書き込み前に get_document_info でページ名(対象ファイルの識別子)を確認してから着手する。複数エージェントで並行作業する場合は、座標バンドを事前に割り当てて衝突を防ぐ。ただしメッセージ到着順序は前後し得るため、重複作成の防止は「作業前のページ実態照合(トップレベル名の突き合わせ)」で担保する。
    • 複製ファイルは node ID を継承するため、node ID の一致はファイル同一性の証拠にならない。ファイル識別は「ページ名+内容の照合」で行う(get_document_info はファイル名を返せない)。

0.5 運用標準(キャンバス設計)

  1. 新規デザインは Figma の「ドラフト」に作成する(左上ロゴ → ファイル → 新規デザイン)。既存ファイルに相乗りしない。
  2. コンポーネントのマスターは専用の「Components」ページに置く。無料プランは1ファイル3ページ制限があるため、ページ構成は3枚以内で計画する(例: Cover+Screens / Components / 予備)。
  3. デザインカンプの標準フレームは モバイル 375×667 / デスクトップ 1366×768(幅は厳守。fullPage カンプでは高さのみコンテンツに従って拡張してよい)。
  4. キャンバスの並び順は「モバイル各ページ → デスクトップ各ページ」。
  5. フレーム間の間隔は 100px で統一する。

1. ビルドの基本形(Auto Layout ファースト)

絶対座標で並べると後の修正が全滅する。すべてのコンテナは Auto Layout フレームにする

推奨ビルド順序

  1. ルートフレームを create_frame で作成。この時点で layout 系パラメータを同時に指定する (layoutMode / padding* / itemSpacing / primaryAxisAlignItems / counterAxisAlignItems)。 後から set_layout_modeset_padding → … と分けるより呼び出し回数が半分以下になる。
    • padding の暗黙既定値に注意(必須): create_frame / create_component は padding 4辺の既定値が 10 であり、layoutMode を指定して padding を省略すると全辺 10px が黙って入る(「未指定=0」ではない)。Auto Layout を指定する呼び出しでは padding 4辺と itemSpacing を必ず明示する(0 にしたい時も 0 を書く)。blog-cms では省略箇所28件に謎の10pxが混入した実績がある。
  2. 子フレーム・テキストは必ず parentId を指定して親に直接生やす(後からの move_node は座標系がズレやすい)。
  3. 子を親に入れたset_layout_sizing で FILL を当てる。

Read the full file on GitHub · 187 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. 11d ago First seen · 187 lines · 164 tokens per session scan A 71a7d9a04bcd

Subscribe to this mod's changes

talk-to-figma-design is a skill published in the GitHub repository Takeaki0817/figma-local-bridge (0 stars, last pushed 1mo ago), licensed MIT. It adds 164 tokens to every session and 6,489 once invoked, about $0.0008 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

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

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

visual-ralph

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Yeachan-Heo/oh-my-codex · 52 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens

make-resume

A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.

Hisn00w/ASu-skills · 86 tokens