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

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

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.

The content is highly actionable and well-structured, with a clear multi-step workflow, validation checkpoints, error-recovery feedback loops, and a clean progressive-disclosure reference table. Its only weakness is repetition of a few key rules across sections, which inflates the token budget without adding new information.

Suggestions

Consolidate the `setCurrentPageAsync` rule so it is stated once in Page Rules and only referenced (not restated) from the Critical Rules list, the error table, and the Pre-Flight Checklist.

Apply the same single-source treatment to the canonical font-load recipe and the layoutSizing value rules to reduce cross-section redundancy.

Consider trimming or collapsing Rules 12/12a/12b into one rule plus a gotchas link, since the error table and checklist already restate the failure messages.

DimensionReasoningScore

Conciseness

The body is dense with genuinely non-obvious environment-specific gotchas, but several rules are repeated across multiple locations — the `setCurrentPageAsync` rule appears in Critical Rules, Page Rules, the error table, and the checklist; the font-load recipe and layoutSizing rules are likewise restated — which keeps it just below 'every token earns its place'.

2 / 3

Actionability

It provides abundant executable, copy-paste-ready code (e.g. `figma.currentPage.query('FRAME[name^=Card] TEXT').set({...})`, `await figma.setCurrentPageAsync(targetPage)`, `findAllWithCriteria({types:[...]})`) with concrete selectors, property values, and a canonical recipe.

3 / 3

Workflow Clarity

The incremental workflow is clearly sequenced (Inspect → skeleton → fill → return IDs → validate → fix) with explicit validation checkpoints per step, a Pre-Flight Checklist, and a full error-recovery feedback loop (stop → read error → fix → retry).

3 / 3

Progressive Disclosure

The body is an overview that points to a well-organized one-level-deep `references/` set (11 docs plus the wwds subfolder) via a clear Reference Docs table mapping each doc to when-to-load and coverage; all referenced paths were verified to exist.

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.

The description is strong: concrete capabilities, an explicit trigger clause, and a clear niche tied to the `use_figma` tool. Its main weakness is the second-person voice ('you MUST invoke'), which the rubric penalizes, and the somewhat tool-jargon framing of the trigger.

Suggestions

Rewrite in third-person voice ('Invokes the `use_figma` skill before every `use_figma` tool call to execute JavaScript in Figma files') to satisfy the rubric's voice requirement and recover the specificity point.

Lead with what the skill does rather than the mandatory-prerequisite framing, so the description reads as a capability statement first and an invocation rule second.

Add a couple of the most common user phrasings ('create a Figma component', 'set up Figma variables/tokens') alongside the technical trigger terms to strengthen natural-language trigger coverage.

DimensionReasoningScore

Specificity

The description lists many concrete actions ('create/edit/delete nodes, set up variables or tokens, build components and variants, modify auto-layout or fills') which on their own merit a 3, but the heavy second-person voice ('you MUST invoke', 'NEVER call') triggers the rubric's voice penalty of -1.

2 / 3

Completeness

It explicitly answers both what (execute JavaScript / perform write and unique-read actions in Figma) and when ('Trigger whenever the user wants to perform a write action or a unique read action...') with an explicit trigger clause.

3 / 3

Trigger Term Quality

It surfaces natural task keywords users would say — 'variables or tokens', 'build components and variants', 'auto-layout or fills' — giving good coverage even though some framing leans on the tool name and 'JavaScript execution'.

3 / 3

Distinctiveness Conflict Risk

It is tightly niched to the `use_figma` tool and specific Figma Plugin API operations, making it unlikely to trigger for the wrong skill.

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
figma/mcp-server-guide
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.