figma-analyze — how to use figma-analyze figma-analyze, Neha-Notes, NehaTanti-afk, community, how to use figma-analyze, ai agent skill, mcp server, agent automation, figma-analyze setup guide, figma component analysis, design-code parity validation, figma-analyze alternative

v1.0.0
GitHub

About this Skill

Perfect for Design Analysis Agents needing advanced Figma component validation and Nexus convention compliance. figma-analyze is a skill that analyzes existing Figma components against Nexus conventions, validating design-code parity, token usage, and AI readability.

Features

Validates design-code parity against Nexus conventions
Checks token usage in Figma components
Analyzes AI readability of Figma designs
Outputs a focused issues list with fixes
Supports input via Figma URL with node-id parameter
Generates reports on design-code inconsistencies

# Core Topics

NehaTanti-afk NehaTanti-afk
[0]
[0]
Updated: 2/22/2026

Quality Score

Top 5%
60
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
> npx killer-skills add NehaTanti-afk/Neha-Notes/figma-analyze
Supports 18+ Platforms
Cursor
Windsurf
VS Code
Trae
Claude
OpenClaw
+12 more

Agent Capability Analysis

The figma-analyze MCP Server by NehaTanti-afk is an open-source community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for how to use figma-analyze, figma-analyze setup guide, figma component analysis.

Ideal Agent Persona

Perfect for Design Analysis Agents needing advanced Figma component validation and Nexus convention compliance.

Core Value

Empowers agents to validate design-code parity, token usage, and AI readability in Figma components, providing a focused issues list with fixes using Figma URLs and Nexus conventions.

Capabilities Granted for figma-analyze MCP Server

Validating Figma components against Nexus conventions
Analyzing design-code parity for consistency
Debugging token usage and AI readability issues in Figma designs

! Prerequisites & Limits

  • Requires Figma URL with node-id
  • Limited to Nexus conventions and Figma components
Project
SKILL.md
9.2 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Figma Analyze

Purpose

Analyze an existing Figma component against Nexus conventions. Validates design-code parity, token usage, and AI readability. Outputs a focused issues list with fixes.

Input

FormatExampleDetection
Figma URLhttps://figma.com/design/:fileKey/:fileName?node-id=123-456URL pattern
Component name + URLButton https://figma.com/...Name + URL

Extract from URL:

  • fileKey — from path segment after /design/
  • nodeId — from node-id param, convert 123-456123:456

Data Sources

Figma (via MCP)

mcp__figma__get_design_context(fileKey, nodeId)  → Props, structure, generated code
mcp__figma__get_variable_defs(fileKey, nodeId)   → Tokens/variables used
mcp__figma__get_metadata(fileKey, nodeId)        → Frame names, hierarchy
mcp__figma__get_screenshot(fileKey, nodeId)      → Visual reference (optional)

Nexus Token System

Read: packages/tailwind/nexus.css           → Semantic tokens (source of truth)
Read: .claude/rules/shadcn-divergences.md   → shadcn → Nexus mapping rules

shadcn Reference (if applicable)

WebFetch: https://ui.shadcn.com/r/styles/default/{component}.json

Workflow

Phase 1: Gather All Context

In parallel:

  1. Figma Design — Call MCP tools to get:

    • Component properties (names, types, values)
    • Variables/tokens used
    • Frame names and layer hierarchy
  2. Nexus Tokens — Read:

    • packages/tailwind/nexus.css — actual semantic tokens available
    • .claude/rules/shadcn-divergences.md — divergence rules
  3. shadcn Reference (if base component identified):

    • Fetch from registry to compare props/variants

Phase 2: Run All Checks

Analyze Figma against Nexus conventions. Check each category and only note issues.

Check Categories

CategoryWhat to Check
Property NamesMatch code props exactly (variant not Style, size not Scale)
Property ValuesLowercase (sm, md not Small, Medium)
Boolean PropsUse has*/is* prefix (hasLeadingIcon not showIcon)
Layer NamesStandard names (Label, LeadingIcon, TrailingIcon, Spinner)
Token UsageSemantic Nexus tokens, no hardcoded values or primitives
Token NamingFollows Nexus patterns (see divergence checks below)
StatesComponent includes hover, focus, active, disabled states as needed
DescriptionComponent has AI-readable description
Compound StructureFrame names match code exports (PascalCase, no spaces)

Divergence-Specific Checks

Cross-reference Figma variables against shadcn-divergences.md:

Figma UsesShould BeRule
destructive/*error/*Nexus uses error naming
accent/*background-hover or mutedAccent removed in Nexus
card/*container/*Renamed in Nexus
primary (no suffix)primary-backgroundExplicit -background suffix
hover:*/90 or opacity*-background-hoverSemantic hover tokens
border-inputborder-defaultRenamed in Nexus

Token Existence Check

For each Figma variable, verify it exists in nexus.css:

Figma: color/primary-background → Check: --color-primary-background exists? ✓
Figma: color/accent-hover → Check: --color-accent-hover exists? ✗ (use background-hover)

Phase 3: Generate Report

Output a focused report with issues grouped by severity.


Output Format

markdown
1## Figma Analysis: {ComponentName} 2 3**Base:** {shadcn component or "Custom"} 4**Type:** {Simple | Compound} 5**Verdict:** {Ready | Needs Updates | Blocked} 6 7--- 8 9### Issues 10 11#### Blocking (Must Fix) 12 13{If none: "None"} 14 151. **{Issue Title}** 16 - Location: `{property/layer/token name}` 17 - Current: `{what Figma has}` 18 - Expected: `{what it should be}` 19 - Why: {brief reason} 20 21#### Should Fix 22 23{If none: "None"} 24 251. **{Issue Title}** 26 - Location: `{property/layer/token name}` 27 - Current: `{what Figma has}` 28 - Expected: `{what it should be}` 29 30--- 31 32### Token Mapping 33 34{Only show if there are token issues or divergences} 35 36| Figma Variable | Nexus Equivalent | Status | 37| --------------- | ---------------- | ------ | --- | --- | 38| `{figma token}` | `{nexus token}` | {✅ || ⚠️} | 39 40--- 41 42### Custom Additions 43 44{Only show if component has props/variants beyond shadcn base} 45 46| Addition | Type | Convention | Notes | 47| -------- | ------------------- | ---------- | ----- | ------------ | 48| `{name}` | {Prop/Variant/Slot} | {✅ | ❌} | {brief note} | 49 50--- 51 52### Checklist 53 54- [{x| }] Property names match code 55- [{x| }] Property values lowercase 56- [{x| }] Layer names standard 57- [{x| }] Tokens exist in Nexus 58- [{x| }] No divergence violations 59- [{x| }] States defined (hover, focus, active, disabled) 60- [{x| }] Has component description

Severity Guidelines

Blocking

Issues that break code generation or cause runtime errors:

  • Property name doesn't match code prop (case-sensitive)
  • Token doesn't exist in Nexus (will fail compilation)
  • Compound frame name doesn't match export
  • Required prop missing

Should Fix

Issues that degrade quality but don't break builds:

  • Non-standard layer names (affects AI readability)
  • Missing description
  • Using deprecated token names (still works but inconsistent)

Examples

Clean Report (No Issues)

markdown
1## Figma Analysis: Button 2 3**Base:** shadcn/button 4**Type:** Simple 5**Verdict:** Ready 6 7--- 8 9### Issues 10 11#### Blocking (Must Fix) 12 13None 14 15#### Should Fix 16 17None 18 19--- 20 21### Checklist 22 23- [x] Property names match code 24- [x] Property values lowercase 25- [x] Layer names standard 26- [x] Tokens exist in Nexus 27- [x] No divergence violations 28- [x] States defined (hover, focus, active, disabled) 29- [x] Has component description

Report with Issues

markdown
1## Figma Analysis: Button 2 3**Base:** shadcn/button 4**Type:** Simple 5**Verdict:** Needs Updates 6 7--- 8 9### Issues 10 11#### Blocking (Must Fix) 12 131. **Invalid token reference** 14 - Location: `color/destructive-background` 15 - Current: `destructive-background` 16 - Expected: `error-background` 17 - Why: Nexus uses `error` naming, `destructive` tokens don't exist 18 192. **Property name mismatch** 20 - Location: Property `Size` 21 - Current: `Size` (PascalCase) 22 - Expected: `size` (lowercase) 23 - Why: Code prop is `size`, case-sensitive matching required 24 25#### Should Fix 26 271. **Non-standard layer name** 28 - Location: Layer `Button Text` 29 - Current: `Button Text` 30 - Expected: `Label` 31 322. **Missing component description** 33 - Location: Component description field 34 - Current: (empty) 35 - Expected: Description following format: "{What} — {Use case}. Variants: {list}." 36 37--- 38 39### Token Mapping 40 41| Figma Variable | Nexus Equivalent | Status | 42| ------------------------------ | ---------------------------- | --------- | 43| `color/destructive-background` | `--color-error-background` | ❌ Rename | 44| `color/destructive-foreground` | `--color-error-foreground` | ❌ Rename | 45| `color/accent-hover` | `--color-background-hover` | ❌ Rename | 46| `color/primary-background` | `--color-primary-background` || 47 48--- 49 50### Checklist 51 52- [ ] Property names match code 53- [x] Property values lowercase 54- [ ] Layer names standard 55- [ ] Tokens exist in Nexus 56- [ ] No divergence violations 57- [ ] Has component description

Error Handling

ErrorAction
Figma MCP failsAsk user to verify connection and permissions
Component not in shadcn registryTreat as custom, check conventions only
No variables usedFlag as blocking — must use Figma variables
Can't identify base componentAsk user to specify

Key References

ReferencePurpose
packages/tailwind/nexus.cssSource of truth for available tokens
.claude/rules/shadcn-divergences.mdshadcn → Nexus mapping rules
.claude/rules/figma.mdFigma-code parity conventions
.claude/rules/components.mdComponent structure requirements

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is figma-analyze?

Perfect for Design Analysis Agents needing advanced Figma component validation and Nexus convention compliance. figma-analyze is a skill that analyzes existing Figma components against Nexus conventions, validating design-code parity, token usage, and AI readability.

How do I install figma-analyze?

Run the command: npx killer-skills add NehaTanti-afk/Neha-Notes/figma-analyze. It works with Cursor, Windsurf, VS Code, Claude Code, and 15+ other IDEs.

What are the use cases for figma-analyze?

Key use cases include: Validating Figma components against Nexus conventions, Analyzing design-code parity for consistency, Debugging token usage and AI readability issues in Figma designs.

Which IDEs are compatible with figma-analyze?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for figma-analyze?

Requires Figma URL with node-id. Limited to Nexus conventions and Figma components.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add NehaTanti-afk/Neha-Notes/figma-analyze. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use figma-analyze immediately in the current project.

Related Skills

Looking for an alternative to figma-analyze or building a community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

linear

Logo of lobehub
lobehub

Linear is a workflow management system that enables multi-agent collaboration, effortless agent team design, and introduces agents as the unit of work interaction.

73.4k
0
Communication

testing

Logo of lobehub
lobehub

Testing is a process for verifying AI agent functionality using commands like bunx vitest run and optimizing workflows with targeted test runs.

73.3k
0
Communication

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication