figma-prototype
Skill7 starsChanged 4 months agoMITView on GitHub
Build interactive Figma prototypes with flows, transitions, and user journey mapping
In this repository95 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessibility-auditSkill
- agent-memory-profilesSkill
- agent-messaging-gatewaySkill
- agent-session-checkpointsSkill
- agent-skill-migrationSkill
- ai-interaction-designSkill
- animation-craftSkill
- animation-vocabularySkill
- apple-designSkill
- apple-desktop-automationSkill
- approval-sandbox-policiesSkill
- atomic-designSkill
- better-colorsSkill
- better-typographySkill
- better-uiSkill
- browser-research-agentSkill
- codex-opsSkill
- competitive-intelSkill
- component-catalogSkill
- content-designSkill
- creative-rendering-auditSkill
- cron-agent-workflowsSkill
- dashboard-from-researchSkill
- data-synthesisSkill
- design-extractSkill
- design-measurement-and-experimentationSkill
- design-sandbox-proofSkill
- design-system-referenceSkill
- design-systemsSkill
- design-to-code-handoffSkill
- dialkitSkill
- docker-environmentsSkill
- emil-design-engSkill
- figma-auditSkill
- figma-code-connectSkill
- figma-create-fileSkill
- figma-design-systemsSkill
- figma-ds-rulesSkill
- figma-generate-designSkill
- figma-generate-librarySkill
- figma-implement-designSkill
- figma-library-builderSkill
- figma-plugin-apiSkill
- figma-syncSkill
- figma-useSkill
- figma-web-captureSkill
- find-animation-opportunitiesSkill
- flutter-genSkill
- gateway-ops-observabilitySkill
- hermes-agent-bridgeSkill
- hyperframes-videoSkill
- improve-animationsSkill
- information-architectureSkill
- interaction-designSkill
- interface-craft-gateSkill
- interview-researchSkill
- ios-app-intentsSkill
- ios-performance-debuggingSkill
- linear-syncSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 93
Run the self-healing loop from /figma-use for each screen.
- Distinctive: line 137
Not generating the HTML prototype for stakeholder review
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/figma-prototype — Create Interactive Prototypes
Build interactive prototypes in Figma with flows, transitions, and user journey mapping. Generates prototype HTML for testing. Requires /figma-use.
Freedom Level: High
Full creative freedom for interactions and flows. Must use existing components and follow atomic structure.
When to Use
- Creating clickable prototypes for user testing
- Demonstrating user flows (onboarding, checkout, auth)
- Building interactive presentations for stakeholders
- Generating standalone HTML prototypes via
memi prototype
Workflow
Step 1: Define the User Journey
Map the flow as screens + transitions:
Onboarding Flow:
Welcome → Feature 1 → Feature 2 → Feature 3 → Dashboard
Auth Flow:
Login → [success] → Dashboard
Login → [forgot] → ForgotPassword → ResetEmail → Login
Login → [signup] → Signup → VerifyEmail → Dashboard
Checkout Flow:
Cart → Shipping → Payment → Review → ConfirmationStep 2: Create Screens
For each screen in the flow:
1. Check if the page spec exists → read specs/pages/
2. If exists → use_figma to create from spec
3. If new → plan atomic decomposition, build bottom-up
4. Create all screens on the same Figma page
5. Arrange in a flow layout (horizontal, spaced)Step 3: Add Interactions
// Navigate on click
button.reactions = [{
action: { type: 'NODE', destinationId: nextScreenId, navigation: 'NAVIGATE' },
trigger: { type: 'ON_CLICK' }
}];
// Smart animate between states
button.reactions = [{
action: {
type: 'NODE',
destinationId: nextScreenId,
navigation: 'NAVIGATE',
transition: {
type: 'SMART_ANIMATE',
easing: { type: 'EASE_IN_OUT' },
duration: 0.3
}
},
trigger: { type: 'ON_CLICK' }
}];
// Overlay (modal, dropdown)
trigger.reactions = [{
action: {
type: 'NODE',
destinationId: overlayId,
navigation: 'OVERLAY',
overlayRelativePosition: { x: 0, y: 0 }
},
trigger: { type: 'ON_CLICK' }
}];Step 4: Transition Types
| Transition | Use Case | Duration |
DISSOLVE | Page navigation | 0.2s |
SMART_ANIMATE | State changes, morphing | 0.3s |
MOVE_IN | Sheets, side panels | 0.25s |
SLIDE_IN | Page push transitions | 0.3s |
PUSH | Stack navigation (mobile) | 0.3s |
Step 5: Self-Healing Validation
Run the self-healing loop from /figma-use for each screen. Additionally: verify all interactions connect, no dead-end screens, consistent transition types within each flow.
Step 6: Generate Prototype HTML
memi prototype → generates prototype/prototype.htmlThis creates a standalone HTML file with all screens and click-through navigation, viewable in any browser.
Flow Layout in Figma
Arrange screens in a clear flow:
Section "User Flow: Onboarding"
├── [Welcome] ──→ [Feature 1] ──→ [Feature 2] ──→ [Dashboard]
│ ↗
├── [Login] ──→ [Dashboard]
│ ↓
├── [ForgotPwd] ──→ [ResetEmail] ──→ [Login]
│ ↓
└── [Signup] ──→ [VerifyEmail] ──→ [Dashboard]
Spacing: 200px between screens (horizontal)
Connection lines: use FigJam connectors or annotation arrowsSpec Integration
Each screen in the prototype should have a PageSpec:
memi spec page Welcome
memi spec page FeatureHighlight
memi spec page DashboardThe prototype flow itself is captured in an IA spec:
memi ia create OnboardingFlowAnti-Patterns
- Dead-end screens with no navigation
- Inconsistent transition types within the same flow
- Missing back/cancel actions
- Screens not built from reusable components
- Floating screens outside the flow Section
- Not generating the HTML prototype for stakeholder review
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

