Name: figma-use
Rating: 71.2 (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

88%

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 thorough, highly actionable skill body with strong workflow sequencing, validation checkpoints, and well-organized one-level-deep references. The main weakness is length and some repetition across rules, tables, and the checklist.

Suggestions

Consolidate the repeated layoutSizing error messages (Rules 12/12b, the error-recovery table, and the checklist) into a single canonical entry to reduce duplication.

Move the full query-selector syntax reference and editor-mode node-type lists into a dedicated reference file, keeping only a compact example inline.

Tighten the pre-flight checklist by cross-referencing rules instead of restating each one verbatim.

Dimension	Reasoning	Score
Conciseness	Dense with hard-won, non-obvious API knowledge and no explaining of concepts Claude already knows, but the body runs ~430 lines with some repetition (long error-message strings restated across rules, the error-recovery table, and the checklist) that could be trimmed.	4 / 5
Actionability	Abundant copy-paste-ready, executable JavaScript (createAutoLayout, query selectors, set batching, inspection scripts, screenshot calls) covering the common cases with specific syntax.	5 / 5
Workflow Clarity	Section 6 gives a clearly sequenced incremental workflow with explicit validation checkpoints (inspect, build skeleton, fill, return IDs, validate with get_metadata/get_screenshot, fix before proceeding) plus a pre-flight checklist and error-recovery feedback loops, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Good structure with a reference-docs table pointing one level deep to well-signaled files in references/, though some inline sections (the full query-selector syntax table, editor-mode node lists) are detailed enough they could live in a reference.	4 / 5
	Total	18 / 20 Passed

Description

87%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 specific, well-triggered description tied to a concrete tool, with comprehensive action coverage and explicit when-guidance. Its main weakness is the heavily second-person, imperative tone, which the rubric penalizes on specificity.

Suggestions

Rewrite in third person (e.g. 'Invokes before every use_figma tool call to execute JavaScript...') to avoid the second-person specificity penalty.

Trim the capitalized mandate framing ('MANDATORY prerequisite', 'NEVER', 'MUST') which reads as instruction-to-Claude rather than capability description.

Add a few user-natural synonyms (e.g. 'design file', 'Figma document') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions (create/edit/delete nodes, set up variables/tokens, build components and variants, modify auto-layout or fills, bind variables to properties, inspect file structure), which is comprehensive, but the heavy second-person voice ('you MUST invoke', 'NEVER call') triggers a 1-point specificity penalty per the rubric.	4 / 5
Completeness	Explicitly answers both what (invoke before use_figma to run JavaScript in the Figma file context) and when ('Trigger whenever the user wants to perform a write action or a unique read action...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers good natural terms (nodes, variables, tokens, components, variants, auto-layout, fills, Figma file) but is phrased around actions rather than the full range of user-spoken synonyms a user might say.	4 / 5
Distinctiveness Conflict Risk	Tightly bound to the specific use_figma tool and Figma Plugin API context, giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	18 / 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: 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.