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.

63

Quality

76%

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 ./examples/plugin-packages/figma/.opencode/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 and well-structured with explicit validation checkpoints and clean one-level-deep reference navigation pointing to real bundle files. Its main weakness is length and some repetition of the same rules across multiple sections, which taxes the context window.

Suggestions

Consolidate the layoutSizing/page-setter/font-load rules that recur across Critical Rules, Page Rules, the Pre-Flight Checklist, and the error table into a single canonical statement with cross-links.

Consider moving the long Pre-Flight Checklist into a reference file and summarizing the top checks inline to reduce body length.

Trim repeated rationale sentences where the rule itself already conveys the constraint.

DimensionReasoningScore

Conciseness

The body is dense and mostly high-signal (rules, executable snippets, tables), but it is very long and occasionally re-explains near-identical rules across the Critical Rules, Page Rules, Pre-Flight Checklist, and error-recovery table, which could be tightened to respect the token budget.

2 / 3

Actionability

It provides fully executable JavaScript snippets (setCurrentPageAsync, createAutoLayout, query/set, return-ID patterns, inspection scripts) and a concrete error-message → fix table, all copy-paste ready with exact API calls and value ranges.

3 / 3

Workflow Clarity

Multi-step work is explicitly sequenced (inspect → skeleton → fill → return IDs → validate → fix) with validation checkpoints, a step-order table mapping each step to get_metadata/get_screenshot checks, and a clear validate→fix→retry feedback loop for atomic failures.

3 / 3

Progressive Disclosure

SKILL.md is an overview pointing one level deep to real reference files (gotchas.md, common-patterns.md, api-reference.md, plugin-api-standalone.d.ts, the working-with-design-systems/ set), with a Reference Docs table giving 'when to load / what it covers' navigation; all referenced paths exist in the bundle.

3 / 3

Total

11

/

12

Passed

Description

67%

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 specific and action-rich, naming many concrete Figma operations, but it is written as an internal mandate rather than a user-need trigger and borrows vocabulary from the tool/API surface rather than natural user phrasing. Its heavy policy framing also blurs the distinctiveness against sibling figma skills.

Suggestions

Add a concise user-need 'Use when...' clause with natural phrasing (e.g. 'Use when the user asks to create or edit Figma components, change colors/fills, set up variables, or build layouts').

Reword the mandatory-prerequisite framing so the trigger reflects what the user wants, not the internal 'invoke before use_figma' requirement.

Sharpen distinctiveness by stating in one line how this skill differs from figma-generate-design and figma-generate-library (API rules vs. screen/component workflows).

DimensionReasoningScore

Specificity

Lists multiple concrete write/read 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"), matching the score-3 anchor.

3 / 3

Completeness

It clearly answers "what" (execute JavaScript in Figma via the Plugin API for write/unique-read actions) and gives a trigger clause, but the trigger is policy-laden ("you MUST invoke this skill BEFORE every use_figma tool call") rather than a clean explicit "Use when..." user-need clause, so the 'when' is present but somewhat muddled.

2 / 3

Trigger Term Quality

Terms like "variables or tokens", "auto-layout", "variants", and "use_figma" are relevant, but the natural phrasing a user would say (e.g. "make a Figma component", "change a color in Figma", "create a variant") is largely absent; triggers are framed as internal tool/API actions rather than user-facing vocabulary.

2 / 3

Distinctiveness Conflict Risk

The mandatory-prerequisite framing scopes it to use_figma calls and the listed Figma actions give it a niche, but it overlaps conceptually with the sibling figma-generate-design and figma-generate-library skills it cross-references, so it is distinguishable yet not cleanly separated.

2 / 3

Total

9

/

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
Devin-AXIS/iPolloWork
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.