Tessl • The package manager for agent skills

SkillPublic

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.

An exceptionally well-engineered operational contract: executable code, exact error-message mappings, explicit validation/retry rules, and exemplary one-level-deep reference navigation. The only real cost is token weight — roughly 380 lines with deliberate duplication between the critical rules, the pre-flight checklist, and the sizing/enum rules, which could be consolidated without losing coverage.

Dimension	Reasoning	Score
Conciseness	Nearly every token captures non-obvious, environment-specific contract details (async-only setters, 0–1 colors, HUG/FILL value restrictions, font-load recipe) with no explanation of concepts Claude already knows — but there is real duplication: Section 8's pre-flight checklist restates Section 1's rules, Rules 12/12b repeat error messages, and Rule 5 and Rule 8 are long single-paragraph walls that could be tightened, matching anchor 4 rather than 5.	4 / 5
Actionability	Guidance is fully executable: copy-paste-ready JS snippets ("figma.currentPage.query('FRAME[name^=Card] TEXT').set({...})", "await figma.setCurrentPageAsync(page)"), exact error strings to recognize ("Expected 'FIXED' \| 'AUTO', received 'FILL'", "Cannot write to node with unloaded font"), and concrete recovery actions tied to each — matching the anchor-5 fully-executable example.	5 / 5
Workflow Clarity	The incremental workflow gives a numbered sequence (inspect → skeleton → retry-safe batches → return IDs → validate → fix before moving on), a per-step validation table, explicit error-recovery feedback loops keyed to `safeToRetryWithoutCanvasRead`, a pre-flight checklist, and validation-evidence requirements on writes — matching anchor 5 including the batch-operation validation guidance.	5 / 5
Progressive Disclosure	The body stays an operational overview with critical rules, while detail is split across 12 one-level-deep reference files (all verified present, including references/working-with-design-systems/wwds.md), each clearly signaled via a "Doc \| When to load \| What it covers" table plus targeted anchors like "references/gotchas.md#canonical-text-edit-recipe..." — matching the anchor-5 clear-overview example.	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, highly specific description with an explicit trigger clause and comprehensive action coverage. Its main weaknesses are the second-person imperative voice ("you MUST", "NEVER call"), which costs a specificity point under the guidelines, and slightly padded framing ("MANDATORY prerequisite", "common, hard-to-debug failures") that adds tokens without adding capability information.

Suggestions

Rewrite in third person (e.g., "Executes JavaScript in Figma files via the Plugin API before every `use_figma` call") instead of the second-person "you MUST invoke / NEVER call" framing, which the guidelines penalize on specificity.

Add a few natural user-side synonyms such as "design file", "frames", "styles", and "screens" alongside the existing action terms to broaden trigger-term coverage.

Trim emphasis filler like "Skipping it causes common, hard-to-debug failures" — it adds no capability or trigger information.

Dimension	Reasoning	Score
Specificity	The description 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" — which is comprehensive for the domain and would anchor at 5, but the opening uses second-person voice ("you MUST invoke this skill", "NEVER call `use_figma` directly"), which the judging guidelines explicitly penalize by reducing specificity by 1.	4 / 5
Completeness	Both "what" and "when" are explicit: the prerequisite role is stated directly, and an explicit trigger clause — "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. ..." — gives concrete trigger phrases, matching the anchor-5 example structure.	5 / 5
Trigger Term Quality	Natural terms users would say are present ("create/edit/delete nodes", "components and variants", "auto-layout", "fills", "variables or tokens", "Figma file"), matching anchor 4; a few common variations are missing (e.g., "design file", "styles", "frames", "screens", "tokens" standalone).	4 / 5
Distinctiveness Conflict Risk	The description is tightly bound to the `use_figma` tool and JavaScript execution in the Figma file context — a clear niche with distinct triggers and minimal conflict risk against unrelated skills, matching anchor 5.	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, 4 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: figma/mcp-server-guide
Path: skills/figma-use/SKILL.md
Revision: 056adaf

Reviewed: 18 hours ago

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.

figma-use

Table of Contents

Is this your skill?