Borrowing it
Nothing to install: this file belongs to renfei-design/Figma-AI-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.
curl -O https://raw.githubusercontent.com/renfei-design/Figma-AI-Bridge/main/.github/skills/figma-slides/SKILL.mdgit clone --depth 1 https://github.com/renfei-design/Figma-AI-BridgeWrote 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.
[](https://agentmods.dev/skills/renfei-design/figma-ai-bridge/figma-slides)<a href="https://agentmods.dev/skills/renfei-design/figma-ai-bridge/figma-slides"><img src="https://agentmods.dev/badge/skills/renfei-design/figma-ai-bridge/figma-slides/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.
<a href="https://agentmods.dev/skills/renfei-design/figma-ai-bridge/figma-slides"><img src="https://agentmods.dev/badge/skills/renfei-design/figma-ai-bridge/figma-slides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00058 | $0.01903 |
| Opus 5 | $0.00029 | $0.00951 |
| Sonnet 5 | $0.00012 | $0.00381 |
| Haiku 4.5 | $0.00006 | $0.00190 |
Grade A, and why
figma-slides 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.
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma Slides
Build presentation slides in Figma. One command per slide via create_slide, or batch multiple slides. Combine with online-research skill for data-driven decks.
MANDATORY: Every deck must be organized into logical sections. Each section = one row on the canvas, starting with a cover slide cloned from an existing template. The agent must autonomously decide how to divide content into sections — do NOT ask the user for section structure.
Prerequisites
- figma-ai-bridge plugin running in Figma and connected
- The
create_slidecommand registered incode.js - Helper:
scripts/figma_cmd.mjs <channel> create_slide '<paramsJSON>'
Slide Types
Type 1: title — Section Cover / Title Slide
Clone an existing slide template via templateNodeId to get the decorative background, then update text.
{
"type": "title",
"templateNodeId": "<node-id>",
"header": "Project Name",
"title": "Presentation Title",
"x": 0, "y": 0
}
- Always use
templateNodeId— cover slides must clone a template for visual style - Discover the template autonomously: Use
get_selection, or scan withget_document_infoandget_node_infoto find an INSTANCE named "Slide templates". Only ask the user if no template exists.
Type 2: content — Title + Body + Key Points (Two-Column)
Left column has body text, right column has bold heading + description pairs.
{
"type": "content",
"title": "Key Findings",
"body": "Our research across three verticals revealed...",
"points": [
{"heading": "Finding One", "description": "Details about the first finding..."},
{"heading": "Finding Two", "description": "Details about the second finding..."}
],
"x": 0, "y": 0
}
Type 3: visual — Title + Body + Cloned Visual
Left side has title and body. Right side clones an existing Figma node (UI mockup, screenshot, diagram).
{
"type": "visual",
"title": "Feature Preview",
"body": "This shows the new user onboarding flow...",
"imageNodeId": "<node-id>",
"x": 0, "y": 0
}
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.
- 10d ago First seen · 230 lines · 58 tokens per session scan A e0c7759bc08f
figma-slides is a skill published in the GitHub repository renfei-design/Figma-AI-Bridge (16 stars, last pushed 6mo ago), licensed MIT. It adds 58 tokens to every session and 1,903 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 2026-08-31.
Other skills, from other repositories
poster-example
Optional editable poster workflow for Layntra. Use only when the user explicitly invokes $layntra and explicitly requests a poster, event card, speaker portrait, or event template.
image-authoring
Author images and diagrams as code — SVG, Pillow, Excalidraw, mermaid. Load when asked to draw, illustrate, or make an image, icon, logo, poster, or diagram.
bento-slides
Create and edit Bento presentations — self-contained .bento.html decks whose document is JSON. Use whenever the user wants a slide deck or presentation: from scratch, from source material, or by improving an existing file.
moai-domain-svg-infographic
Author editable SVG technical infographics — architecture, flow, comparison, hierarchy — by computing the layout numerically before writing markup, then rendering a 2x PNG via headless Chromium. Carries a CJK-first font stack, a deterministic source lint, and mermaid-vs-SVG selection rules.
motion-graphics
Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s…
illustration-style
Define an illustration style guide — visual language, colour usage, and application rules. Use when commissioning or standardising illustration. For icons, use icon-system (design-systems).