prototype-analysis — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited prototype-analysis (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Analyze prototype interactions in Figma files. Produces a directed flow graph, Mermaid diagram, and identifies navigation issues (dead ends, loops, missing back navigation). Can also batch-connect screens to fix flow gaps.
load_toolset("prototype") directly with add_reaction or connect_screens.ping → verify plugin connection
load_toolset("prototype") → enable prototype analysis toolsIf `ping` fails (plugin not connected): STOP. Do not fall back to other MCP servers. Tell user: open Figma → Plugins → FigCraft → wait for connection, then retry.
analyze_prototype_flow → scan current page for all interactionsOptional parameters:
nodeId — analyze a specific subtree instead of the full pageformat — "all" for complete output (graph + mermaid + markdown)Returns:
Report the flow health:
📊 Flow Summary:
- Screens: X total
- Interactions: Y connections
- Entry points: [list]
- Dead ends: [list] ⚠️
- Loops: [list]
- Trigger types: ON_CLICK (N), ON_HOVER (M), ...Present the Mermaid diagram for visual understanding of the navigation structure.
Flag navigation problems:
If the user wants to fix issues, use connect_screens to batch-wire missing connections:
connect_screens(connections: [
{ sourceId: "1:23", destinationId: "4:56", trigger: "ON_CLICK" },
{ sourceId: "4:56", destinationId: "1:23", trigger: "ON_CLICK" }
])After connecting, connect_screens automatically re-runs analyze_prototype_flow to validate the updated flow.
| Tool | Purpose |
|---|---|
analyze_prototype_flow | Full flow analysis with graph, mermaid, and docs |
get_reactions | Inspect interactions on a specific node or all nodes |
connect_screens | Batch-connect screens with prototype interactions |
add_reaction | Add a single interaction to a node |
remove_reaction | Remove interactions from a node |
set_reactions | Replace all interactions on a node |
Prototype analysis is typically used:
figma-create-ui~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.