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.

65

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/figma-use/SKILL.md
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 body is highly actionable with executable code, a clearly sequenced validated workflow, and excellent one-level-deep progressive disclosure; its only weakness is conciseness, where the checklist and error tables duplicate rules already stated earlier.

Suggestions

De-duplicate the Section 8 pre-flight checklist against Sections 1-7 — reference those rules instead of restating each (e.g. colors 0-1, await every promise, FILL-after-append) to reclaim tokens.

Fold the Section 7 self-correction table's repeated rules into a pointer to Section 1's Critical Rules, keeping only the genuinely new error-message mappings.

Consider trimming the Editor Mode node-type listings (Section 4) into a reference doc unless they are needed at decision time in the main body.

DimensionReasoningScore

Conciseness

Mostly efficient with actionable rules and code, but the 22-item pre-flight checklist (Section 8) and the self-correction table (Section 7) restate rules already given in Sections 1-7 (colors 0-1, FILL-after-append, await every promise), so it could be tightened — not the verbose score-1 case (no basic-concept padding), short of the lean score-3 bar.

2 / 3

Actionability

Provides fully executable, copy-paste-ready code throughout — query/set selectors, createAutoLayout, screenshot, setCurrentPageAsync, and inspection scripts — with concrete WRONG/CORRECT comparisons, matching the score-3 anchor.

3 / 3

Workflow Clarity

Section 6 gives a clear sequenced incremental workflow (inspect → skeleton → fill → return IDs → validate → fix) with explicit validation checkpoints, Section 7 adds validate→fix→retry feedback loops for the batch/destructive writes, and Section 8 supplies a pre-flight checklist.

3 / 3

Progressive Disclosure

The body is a concise overview pointing to 12 well-signaled one-level-deep references via a 'when to load' table (Section 10); all referenced files were verified to exist, and large material (the .d.ts typings) correctly lives in references rather than inline.

3 / 3

Total

11

/

12

Passed

Description

75%

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, explicitly triggers on write/JS-execution actions, and occupies a distinct niche, but it leans on API jargon over natural user phrasings and uses second-person voice which caps specificity at 2.

Suggestions

Add natural-language trigger terms users would actually say (e.g. 'design in Figma', 'build a Figma screen', 'edit a Figma file') alongside the API-jargon ones to improve trigger_term_quality.

Rewrite in third person ('Executes JavaScript in Figma files via the use_figma tool...') to remove the second-person voice and recover the specificity penalty.

Consider trimming the mandatory-prerequisite framing ('MANDATORY prerequisite — you MUST invoke this skill BEFORE every use_figma tool call') which is directive padding rather than capability description.

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 would score 3, but the second-person voice ('you MUST invoke this skill BEFORE every use_figma tool call') triggers the rubric's -1 specificity penalty, bringing it to 2.

2 / 3

Completeness

Explicitly answers both what ('execute JavaScript in Figma file context') and when ('Trigger whenever the user wants to perform a write action or a unique read action...'), matching the score-3 anchor with explicit triggers rather than implied usage.

3 / 3

Trigger Term Quality

Includes relevant Figma-domain keywords ('variables or tokens', 'components and variants', 'auto-layout', 'fills', 'bind variables') but they skew toward API jargon rather than phrasings a user would naturally say (e.g. 'design in Figma', 'make a Figma button'), and common variations are missing.

2 / 3

Distinctiveness Conflict Risk

Tightly scoped to the use_figma tool and Figma Plugin API JavaScript execution — a clear niche with distinct triggers unlikely to conflict with unrelated skills.

3 / 3

Total

10

/

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, 2 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
novuhq/novu
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.