CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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 excellent workflow sequencing, error-recovery feedback loops, and well-structured progressive disclosure; the only meaningful weakness is redundancy of the critical layoutSizing/page rules across multiple sections.

Suggestions

Consolidate the layoutSizingHorizontal/Vertical rules into a single authoritative location (e.g., gotchas.md) and have the rules list, error-recovery table, and pre-flight checklist link to it rather than restating the full rule each time.

Do the same for the setCurrentPageAsync guidance — state it once in the Page Rules section and reference it from the rules list and checklist to cut repeated tokens.

Section 10's reference table duplicates some "what it covers" detail already present inline; consider trimming the inline restatements once the table is the canonical map.

DimensionReasoningScore

Conciseness

The body is dense, assumes Claude's competence, and conveys genuinely non-obvious Figma-specific rules — but the layoutSizing and setCurrentPageAsync rules are each repeated across four locations (rules list, dedicated section, error-recovery table, pre-flight checklist), so not every token earns its place.

2 / 3

Actionability

Abundant copy-paste-ready executable examples (node.query selectors, node.set batch updates, figma.createAutoLayout, node.screenshot, inspection scripts) give concrete, complete guidance rather than pseudocode.

3 / 3

Workflow Clarity

Section 6 gives an explicitly sequenced incremental workflow (inspect → skeleton → fill → return IDs → validate → fix), section 7 provides a STOP-read-fix-retry feedback loop, and section 8 is a validation checklist — all with explicit checkpoints for these risky batch/mutating operations.

3 / 3

Progressive Disclosure

SKILL.md is an overview with a section-10 reference table ("When to load / What it covers") pointing to one-level-deep references; all in-bundle referenced paths (gotchas.md, the pattern docs, plugin-api-standalone.*, the wwds tree) were verified to exist on disk.

3 / 3

Total

11

/

12

Passed

Description

90%

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, highly specific description with an explicit trigger clause and clear niche; its only weakness is second-person voice, which costs it the specificity point under the rubric's voice rule.

Suggestions

Rewrite the opening in third person (e.g., "Invoked before every `use_figma` tool call... Executes JavaScript in Figma files via the Plugin API") to avoid the second-person specificity penalty while preserving the mandatory-prerequisite intent.

Consider trimming the emphatic preamble ("MANDATORY prerequisite... NEVER call... Skipping it causes...") which is reinforcement rather than capability/trigger description, to tighten the description further.

DimensionReasoningScore

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"), which is anchor-3 caliber, but the second-person voice ("you MUST invoke this skill") triggers the rubric's -1 specificity penalty.

2 / 3

Completeness

Clearly answers both what (execute JavaScript in Figma files via the Plugin API for write/unique-read actions) and when (explicit "Trigger whenever..." clause with concrete examples), satisfying the explicit-trigger requirement that would otherwise cap this at 2.

3 / 3

Trigger Term Quality

"Trigger whenever the user wants to perform a write action or a unique read action that requires JavaScript execution in the Figma file context" plus natural terms (Figma, nodes, variables/tokens, components/variants, auto-layout) gives good coverage of phrasing users actually say.

3 / 3

Distinctiveness Conflict Risk

Niche is tightly bound to the specific `use_figma` tool and Figma Plugin API JavaScript execution, with triggers unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.