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

90%

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

92%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 high-quality, actionable skill body with executable code, a well-sequenced incremental workflow with validation and error-recovery feedback loops, and clean progressive disclosure to verified reference files. The only meaningful weakness is deliberate-but-trimmable repetition of critical rules across multiple sections and the pre-flight checklist.

Suggestions

Consolidate the repeated atomicity and setCurrentPageAsync guidance into one canonical location and cross-reference it, rather than restating full explanations in the rules, section 7, the error table, and the pre-flight checklist.

Trim the pre-flight checklist to items not already enumerated as numbered Critical Rules, or explicitly label it as a recap so the redundancy is intentional and bounded.

Dimension	Reasoning	Score
Conciseness	Dense and information-rich with no concept over-explanation, but several critical points are repeated across multiple locations (atomicity/error-recovery in rule 14, section 7, and the error table; setCurrentPageAsync in rule 9, section 2, the error table, and the pre-flight checklist), and the pre-flight checklist re-lists rules already stated — trimmable redundancy that keeps it just below a clean 5.	4 / 5
Actionability	Fully executable, copy-paste-ready JavaScript throughout — query-selector examples, node.set/createAutoLayout/screenshot snippets, QueryResult method table, and concrete inspection scripts — covering the common cases directly.	5 / 5
Workflow Clarity	Section 6 gives a clear incremental workflow (inspect → skeleton → fill → return IDs → validate → fix) with a validation table and a suggested step order, and section 7 adds explicit STOP/read-error/fix/retry feedback loops for a destructive/batch context, satisfying the validation requirement rather than triggering the cap.	5 / 5
Progressive Disclosure	The body is an overview with a well-signaled reference table (section 10) pointing one level deep to 11 distinct reference files, all verified present in references/, with content appropriately split (rules/workflow/efficient APIs inline; deep API surface and patterns delegated) for easy navigation.	5 / 5
	Total	19 / 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 strong, concrete description that covers both what the skill does and when to trigger it, with low conflict risk. Its main weakness is the second-person imperative voice (penalized on specificity) and trigger phrasing that favors API-action jargon over natural user synonyms and file extensions.

Suggestions

Rewrite the mandatory-prerequisite framing in third person ('Invoke this skill before every use_figma tool call') to avoid the second-person specificity penalty.

Add natural user-facing trigger terms and file extensions (e.g. 'Figma files, .fig, design files') alongside the API-action keywords to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple 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') for comprehensive coverage, but the second-person voice ('you MUST invoke', 'NEVER call') triggers the rubric's -1 specificity penalty, dropping it from 5 to 4.	4 / 5
Completeness	Explicitly answers both 'what' (perform write or unique read actions requiring JS execution in a Figma file) 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	Strong concrete-action keywords ('nodes', 'variables or tokens', 'components and variants', 'auto-layout or fills', 'Figma file') but the phrasing leans toward API-action jargon and omits the simpler synonyms and file extensions a lay user would naturally say, so it falls just below the comprehensive-coverage anchor.	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to the `use_figma` tool and the Figma Plugin API context with operation-specific triggers, and the mandatory-prerequisite framing binds it to a single tool, giving a clear niche with minimal conflict risk.	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, 2 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: novuhq/novu
Path: .agents/skills/figma-use/SKILL.md
Commit: dc9caee

Reviewed: 3 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.