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

85%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.

The body is highly actionable, well-structured, and exemplifies progressive disclosure with verified references, but it carries repeated content across rules, tables, and checklists that inflates token cost.

Suggestions

Consolidate the layoutSizingHorizontal/Vertical HUG/FILL material: state the rule once (e.g. in Rule 12) and have the error-recovery table and pre-flight checklist reference gotchas.md rather than re-explaining the same errors.

The error-recovery table (Section 7) duplicates several rules already enumerated in Section 1 — cross-reference instead of restating to trim length.

Trim the verbose inline annotations on Rules 8 and 18; move extended rationale to gotchas.md and keep the rule line to the actionable constraint.

Dimension	Reasoning	Score
Conciseness	Dense and mostly efficient, but ~435 lines with notable redundancy — the layoutSizing HUG/FILL rules reappear verbatim across Rule 12/12a/12b, the error-recovery table, and the pre-flight checklist, padding the body without new information.	3 / 5
Actionability	Fully executable, copy-paste-ready code throughout — query selectors, node.set, createAutoLayout, screenshot options, and ready-to-run inspection scripts — covering the common cases concretely.	5 / 5
Workflow Clarity	Section 6 lays out an explicitly sequenced incremental workflow with validation checkpoints, Section 7 supplies fix->revalidate feedback loops, and Section 8 provides a pre-flight checklist for these destructive/batch operations.	5 / 5
Progressive Disclosure	Clear overview body with a Section 10 reference table, all referenced files verified to exist, one level deep, well-signaled, with bulk detail appropriately pushed into references/.	5 / 5
	Total	18 / 20 Passed

Description

92%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.

The description is concrete, comprehensive, and explicitly pairs a clear what with explicit when-trigger guidance anchored to a distinct tool. Minor improvement would come from softer, less imperative phrasing and broader user-facing synonyms.

Suggestions

Soften the all-caps imperative framing (MANDATORY/NEVER/MUST) which reads as instruction-to-Claude rather than a user-facing capability description; state the capability in third person.

Add a couple of plain user-facing synonyms (e.g. 'Figma plugin scripts', 'automate Figma edits') alongside the technical API terms to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — create/edit/delete nodes, set up variables/tokens, build components and variants, modify auto-layout/fills, bind variables to properties, inspect file structure — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (invoke skill before use_figma for JS execution in Figma files) 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 natural terms like Figma, nodes, variables, components, variants, auto-layout, fills appear, but the set leans technical and omits some user-facing synonyms a requester might say.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche as the mandatory prerequisite for the specific use_figma tool, with triggers tied to that tool's context, leaving minimal overlap with unrelated skills.	5 / 5
	Total	19 / 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: openai/plugins
Path: plugins/figma/skills/figma-use/SKILL.md
Commit: 1e28582

Reviewed: 8 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.