Name: figma-use
Rating: 68 (1 reviews)
Author: figma

figma-use

**MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call. NEVER call `use_figma` directly without loading this skill first. Skipping it causes common, hard-to-debug failures. Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in the Figma file context — e.g. create/edit/delete nodes, set up variables or tokens, build components and variants, modify auto-layout or fills, bind variables to properties, or inspect file structure programmatically.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

83%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.

An excellent, highly actionable skill body with a clear multi-step workflow, validation feedback loops, and well-structured progressive disclosure to a real reference bundle. The main weakness is repetition of the auto-layout sizing rules across multiple sections, which inflates token cost without adding clarity.

Suggestions

Consolidate the layoutSizing HUG/FILL guidance — currently repeated across Rule 12, 12a, 12b, the pre-flight checklist, and the error-recovery table — into one canonical location and cross-reference it.

Tighten the Efficient APIs section's prose (e.g. the placeholder/screenshot subsections) by trimming explanatory sentences that restate what the code already shows.

Move the full Editor Mode node-type availability/blocked lists into a reference file, keeping only the design-vs-FigJam-vs-Slides URL rule and createPage caveat inline.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and mostly assumes Claude's API knowledge, but several rules and tables restate the same pitfall multiple times (the HUG/FILL auto-layout rules appear in rules 12, 12a, 12b, the checklist, and the error-recovery table) and some passages re-explain basic mechanics Claude already knows.	3 / 5
Actionability	It provides copy-paste-ready executable JavaScript for the common cases (page switching, query/set, createAutoLayout, screenshot, inspection scripts) plus concrete error-message-to-fix tables, covering the common cases with specific, runnable examples.	5 / 5
Workflow Clarity	The incremental workflow is explicitly sequenced with validation checkpoints (inspect → skeleton → fill → validate with get_metadata/get_screenshot → fix before moving on) and a destructive/atomic-error feedback loop (STOP, read error, fix, retry) that matches the rubric's best anchor.	5 / 5
Progressive Disclosure	The SKILL.md is a clear overview with well-signaled, one-level-deep references into real files (gotchas.md, common-patterns.md, etc., all present in references/), plus a 'When to load / What it covers' reference-doc table that makes navigation easy.	5 / 5
	Total	18 / 20 Passed

Description

83%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, specific description that clearly states what the skill does and when to trigger it, with concrete Figma API actions and natural trigger terms. Minor over-claiming via the MANDATORY-prerequisite capitalization and slightly jargon-heavy phrasing keep it just short of a clean 5 across the board.

Dimension	Reasoning	Score
Specificity	It names the domain (Figma Plugin API / use_figma) and several concrete actions — 'create/edit/delete nodes, set up variables or tokens, build components and variants, modify auto-layout or fills, bind variables to properties, or inspect file structure programmatically' — giving strong but not exhaustive action coverage.	4 / 5
Completeness	It explicitly answers both what ('execute JavaScript in Figma files via the Plugin API' plus enumerated write/unique-read actions) and when ('Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in the Figma file context'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('use_figma', 'create/edit/delete nodes', 'variables or tokens', 'components and variants', 'auto-layout', 'fills'), though it leans on the tool name and API jargon rather than the full range of synonyms a user might say (e.g. 'design file', 'styles').	4 / 5
Distinctiveness Conflict Risk	The Figma-specific tool name and Plugin-API framing give it a clear niche with minimal conflict risk, but the MANDATORY-prerequisite framing and broad 'inspect file structure' phrasing create minor overlap with sibling figma-generate-* skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 deeper-than-1-level, 4 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: figma/mcp-server-guide
Path: skills/figma-use/SKILL.md
Commit: 72fcf1f

Reviewed: 4 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.