CtrlK
BlogDocsLog inGet started
Tessl Logo

figma-automation

Automate Figma tasks via Rube MCP (Composio): files, components, design tokens, comments, exports. Always search tools first for current schemas.

52

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/figma-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a competent reference skill for Figma automation via Rube MCP, with good coverage of workflows, parameters, and pitfalls. Its main weaknesses are redundancy across sections (node ID format, pitfalls repeated), lack of executable examples (pseudocode patterns instead of concrete tool calls), and a monolithic structure that could benefit from splitting. The 'When to Use' footer adds no value.

Suggestions

Replace the pseudocode in 'Common Patterns' with concrete tool invocation examples showing actual parameter values (e.g., a real FIGMA_DISCOVER_FIGMA_RESOURCES call with a sample URL and its expected response structure).

Consolidate the duplicated pitfalls—remove the 'Known Pitfalls' section and keep pitfalls only within their respective workflow sections, or vice versa.

Remove the empty 'When to Use' section at the bottom, which adds no information beyond restating the description.

Add a brief validation step to workflows involving multi-step operations (e.g., after rendering images, check that returned URLs are non-null before passing to download).

DimensionReasoningScore

Conciseness

The skill is reasonably efficient but includes some redundancy—pitfalls are repeated (node ID format appears in both workflow sections and a dedicated 'Known Pitfalls' section), and the 'When to Use' section at the bottom is vacuous. The quick reference table duplicates information already covered in the workflows. However, most content is genuinely useful and not over-explaining basic concepts.

3 / 5

Actionability

The skill provides specific tool names, parameter names, and key details like format constraints, but lacks executable code examples—the 'Common Patterns' sections use pseudocode-style numbered lists rather than actual tool invocation examples with concrete parameters. The guidance is specific enough to follow but not copy-paste ready.

3 / 5

Workflow Clarity

Workflows are clearly sequenced with labeled steps (Prerequisite, Required, Optional), and pitfalls sections serve as implicit validation guidance. However, there are no explicit validation/verification checkpoints or error recovery feedback loops—e.g., no step to verify that rendered image URLs are non-null before proceeding to download, or to check connection status after auth. Since these aren't destructive operations, the missing feedback loops don't trigger the cap at 3.

4 / 5

Progressive Disclosure

The content is well-structured with clear sections and a quick reference table, but everything is in a single monolithic file with no bundle files. The quick reference table and detailed workflow sections could benefit from being split—the file is quite long. There are no references to external files, which is appropriate given no bundle exists, but the volume of content suggests splitting would improve navigation.

3 / 5

Total

13

/

20

Passed

Description

58%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.

The description identifies a clear domain (Figma automation) and lists several capability areas, making it reasonably specific and distinctive. However, it lacks an explicit 'Use when...' clause, which limits Claude's ability to reliably select this skill, and the trigger terms could be expanded to include more natural user language around design workflows.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'Use when the user asks about Figma designs, design tokens, Figma components, or exporting assets from Figma.'

Expand trigger terms to include natural user language such as 'design file', 'Figma project', 'styles', 'prototype', or 'UI design' to improve matching.

DimensionReasoningScore

Specificity

Lists several specific actions (files, components, design tokens, comments, exports) and names the domain (Figma) and tooling (Rube MCP/Composio). Minor gaps in that the actions are listed as nouns rather than verbs describing concrete operations, but coverage is good.

4 / 5

Completeness

The 'what' is reasonably clear (automate Figma tasks via specific tooling with listed capabilities). However, there is no explicit 'when' clause — no 'Use when...' guidance for Claude to know when to select this skill. The instruction to 'always search tools first' is operational guidance, not a trigger condition.

3 / 5

Trigger Term Quality

Includes 'Figma', 'components', 'design tokens', 'comments', 'exports' which are relevant keywords. However, it misses natural user phrases like 'design file', 'prototype', 'inspect', 'styles', or file-related terms users might say. 'Rube MCP (Composio)' is technical jargon unlikely to appear in user requests.

3 / 5

Distinctiveness Conflict Risk

Naming 'Figma' and 'Rube MCP (Composio)' makes this fairly distinct and unlikely to conflict with other skills. Minor overlap risk with generic design or MCP-related skills, but the Figma specificity reduces conflict significantly.

4 / 5

Total

14

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.