Install
$ agentstack add skill-renfei-design-figma-ai-bridge-figma-doc ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Figma Documentation Page
Build a structured documentation page in Figma using a standard layout format. One command — generate content, call create_doc_page, done.
Prerequisites
- figma-ai-bridge plugin running in Figma and connected
- The
create_doc_pagecommand registered incode.js - Helper:
scripts/figma_cmd.mjs create_doc_page ''
Workflow
1. Generate Content
Read the user's topic, spec, or description. Organize content into sections:
{
"title": "Document Title",
"width": 1600,
"x": 0,
"y": 0,
"sections": [
{ "heading": "Section Title", "body": "Paragraph text..." },
{ "heading": "Comparison", "columns": [{"text": "Left col"}, {"text": "Right col"}] },
{ "heading": "Feature Matrix", "table": {
"headers": ["Requirement", "Option A", "Option B"],
"rows": [
["Goal-oriented workflows", "✅ Native", "❌ Not core"],
["Multi-step execution", "✅ First-class", "⚠️ Limited"]
]
}
}
]
}
Each section has ONE of these content types:
- body — paragraph text with
\nfor line breaks - columns — array of
{text}objects (for side-by-side comparison) - table —
{headers: [...], rows: [[...], ...]}(for structured data, feature matrices)
Information Design Guidelines
| Content type | Best format | Example | |---|---|---| | Narrative explanation | body | Executive summary, background, recommendations | | Pros/cons, either/or | columns | "Follow this" vs "Don't follow that" | | Feature comparison matrix | table | Requirements × options with ✅/❌ | | Structured criteria list | table | Dimensions with ratings or status | | Side-by-side analysis | columns | Two approaches described in prose | | Action items / bullet lists | body | Numbered steps, bullet points | | Visual reference with description | columns + imageNodeId | Component screenshot + explanation text |
Cloning Visuals from Source
Columns and body sections support imageNodeId to clone an existing Figma node into the new doc:
columns[].imageNodeId— clone into that column (image above text)section.imageNodeId— clone into the body section (image above text)
IMPORTANT — Never clone table widgets. If the source design contains Figma table widgets (WIDGET type), extract the data and use the table format instead.
2. Build in Figma (ONE call)
node scripts/figma_cmd.mjs create_doc_page '{
"title": "...",
"width": 1600,
"sections": [
{"heading": "Executive Summary", "body": "..."},
{"heading": "Background", "body": "..."},
{"heading": "Comparison", "columns": [{"text": "Left"}, {"text": "Right"}]}
]
}'
This single command builds the entire page: root frame, title, documentation container, all sections with headers/body, separators between sections.
Returns: { id, name, width, height, sectionCount, sections: [{id, heading, type}] }
3. Post-Creation Adjustments (optional)
Use individual MCP tools to tweak:
set_text_contentto edit a specific text nodecreate_frame/create_textto add more contentmove_node/resize_nodefor repositioning
Content Guidelines
Typical Section Patterns
- Executive Summary — one paragraph framing the problem and approach
- Overview / Background — context and setup
- Analysis / Case Study — detailed breakdown
- Design Implications — actionable takeaways with bold lead-in keywords
- Comparison — side-by-side using
columns
Text Formatting
- Use
\nfor line breaks within body text - For bullet lists, use
\nwith bullet characters (•) or numbered prefixes - For bold sub-headings within body, put them on their own line
- Keep section bodies focused — one concept per section
Section Count
- Aim for 3–7 sections per document
- Start with summary/overview, end with implications/next steps
What Gets Built
(FRAME, white, cornerRadius:20, width:1600, VERTICAL auto-layout)
├── Title (TEXT, Inter Bold 40px, #424242)
└── Documentation (FRAME, cornerRadius:20, VERTICAL, spacing:64)
├── Section (FRAME, VERTICAL)
│ ├── Header (TEXT, Inter Semibold 28px)
│ └── Body (TEXT, Inter Regular 20px)
├── Separator (1px, #e0e0e0)
├── Section ...
└── ...
Typography
| Element | Font | Weight | Size | Color | |---------|------|--------|------|-------| | Title | Inter | Bold 700 | 40 | #424242 | | Section heading | Inter | Semibold 600 | 28 | #424242 | | Body text | Inter | Regular 400 | 20 | #424242 |
Width Options
- 1600 — standard documentation (default)
- 2087 — wide format (specs with diagrams)
Notes
- Avoid overlapping existing content — query
get_canvas_boundsto find existing frames, then setx/yaccordingly - Separators are auto-inserted between sections
- The entire page builds in a single WebSocket roundtrip (~2-5 seconds)
- Never clone Figma table widgets — always extract data and use the
tableformat
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: renfei-design
- Source: renfei-design/Figma-AI-Bridge
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.