Name: figma-generate-design
Rating: 73.6 (1 reviews)
Author: figma

figma-generate-design

Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the Figma screen to match code', 'convert this modal/dialog/drawer/panel to Figma'. This is the preferred workflow skill whenever the user wants to build or update a full page, modal, dialog, drawer, sidebar, panel, or any composed multi-section view in Figma from code or a description. Discovers design system components, variables, and styles from Code Connect files, existing screens, and library search, then imports them and assembles views incrementally section-by-section using design system tokens instead of hardcoded values.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced workflow skill with executable code, hard gates, and strong validation/feedback loops; its only real weakness is that it is long and inlines some API detail that could live in the referenced detail files, plus minor duplicated guidance.

Suggestions

Dedupe the 'search broadly, one intent per query' guidance that appears in both Step 2a-iii and Best Practices — keep it in one place and link from the other.

Move the longer discovery code blocks (2a-ii instance-walk, 2b boundVariables enumeration, 2c styles enumeration) into a referenced patterns file, keeping only a short inline example in SKILL.md.

Trim inline rationale comments like 'This is a logging parameter — it does not affect execution' where the surrounding context already conveys the point.

Dimension	Reasoning	Score
Conciseness	Dense with non-obvious API gotchas and executable code rather than padding about what Figma/libraries are, but it is long (~470 lines) with some duplicated guidance ('search broadly, one intent per query' appears in both 2a-iii and Best Practices) and a few minor rationale comments that could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready use_figma scripts for every phase (component discovery, variable/style binding, wrapper creation, section building, icon SVG import, font verification, image transfer) with concrete API calls and only parameter placeholders to substitute.	5 / 5
Workflow Clarity	A 'Required Workflow' with ordered Steps 1–6, hard gates ('Do not skip steps', explicit forbidden shortcuts), and explicit validation checkpoints (get_screenshot after each section, Step 5 full-view validation, mandatory font assertion) plus validate→fix→re-validate feedback loops.	5 / 5
Progressive Disclosure	SKILL.md acts as an overview with well-signaled one-level-deep references to two real local files (componentization.md, discover-product-font.md with anchors) and a clear Reference Docs section pointing to figma-use detail files; however a fair amount of API detail (2a-ii, 2b, 2c code blocks) remains inlined rather than split out.	4 / 5
	Total	18 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that explicitly states what the skill does and when to use it, with comprehensive verbatim trigger phrases and clear delineation from sibling Figma skills. Its only weakness is that the concrete actions are stated at a process level rather than as an exhaustive atomic action list.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Discovers design system components, variables, and styles', 'imports them and assembles views incrementally section-by-section using design system tokens instead of hardcoded values'), but these are process-level rather than an exhaustive atomic action list, leaving minor gaps.	4 / 5
Completeness	Explicitly answers both 'what' (translate an app page/view into Figma via design-system components and tokens) and 'when' (a dedicated Triggers list plus 'whenever the user wants to build or update a full page, modal, dialog, drawer, sidebar, panel...').	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases quoted verbatim ('write to Figma', 'push page to Figma', 'create a screen', 'build a landing page in Figma', 'convert this modal/dialog/drawer/panel to Figma'), covering synonyms and container types users would actually say.	5 / 5
Distinctiveness Conflict Risk	Clearly scoped niche (composed multi-section views built from design-system instances) and explicitly distinguished from sibling skills ('Use this skill alongside figma-use'), with distinct triggers and minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 16 suspicious	Warning

	Total	15 / 16 Passed

Repository: figma/mcp-server-guide
Path: skills/figma-generate-design/SKILL.md
Commit: ae7e5e5

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.