figma-automation

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

2.34x

Quality

—

Does it follow best practices?

Impact

96%

2.34x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

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 a well-structured, actionable reference with clear sequenced workflows and an explicit validation checkpoint in setup. Its main weakness is mild redundancy across the per-workflow pitfalls, the dedicated Known Pitfalls section, and the quick-reference table.

Suggestions

Consolidate the 'Known Pitfalls' section into the relevant per-workflow 'Pitfalls' blocks (or vice versa) to remove the node-ID and file-type duplication and tighten token usage.

Consider whether the 18-row 'Quick Reference' table, which re-lists tool slugs already shown in the workflow sequences, earns its tokens or could be trimmed to only non-obvious mappings.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes competence, but the 'Known Pitfalls' section restates node-ID format and file-type support already covered in the per-workflow 'Pitfalls' blocks, and the 'Quick Reference' table repeats tool slugs — tightening could remove redundancy without losing clarity.	2 / 3
Actionability	Guidance is concrete and copy-ready: named tool slugs, exact parameter values and formats (e.g., ids as 'comma-separated node IDs (NOT an array)', depth=2, dash-to-colon conversion), and specific failure modes — fully actionable instruction-only guidance.	3 / 3
Workflow Clarity	Each of the five workflows has a 'When to use' cue, a numbered tool sequence with Required/Optional/Prerequisite markers, and the Setup section includes an explicit validation checkpoint ('Confirm connection status shows ACTIVE before running any workflows').	3 / 3
Progressive Disclosure	No bundle files exist and the single SKILL.md is organized into clear, well-labeled sections (Prerequisites, Setup, numbered Core Workflows, Common Patterns, Known Pitfalls, Quick Reference) with no nested references, satisfying the no-external-refs organization bar.	3 / 3
	Total	11 / 12 Passed

Description

72%

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 well-scoped to Figma automation with strong natural trigger terms, but it omits an explicit "Use when..." clause and relies on a generic action verb, which cap completeness and specificity. Adding a trigger clause and concrete verbs would push it toward full marks.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user mentions Figma files, components, design tokens, comments, exports, or wants to automate Figma via Rube/Composio') to satisfy the completeness 'when' requirement.

Replace the generic 'Automate Figma tasks' with concrete verbs per capability (e.g., 'Extract files and components, render and export images, pull design tokens, manage comments') to lift specificity to 3.

Dimension	Reasoning	Score
Specificity	Names the Figma domain and enumerates capability areas ("files, components, design tokens, comments, exports"), but these are objects rather than concrete verbs, and the only action verb is the generic "Automate Figma tasks" — not the comprehensive multi-action list required for a 3.	2 / 3
Completeness	It states what the skill does but lacks any explicit "Use when..." trigger clause, so per the judging guidelines a missing trigger guidance caps completeness at 2.	2 / 3
Trigger Term Quality	Natural terms a user would say are well covered — "Figma", "design tokens", "components", "comments", "exports" — alongside the integrator names "Rube MCP" and "Composio", matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The niche is clearly scoped to Figma via Rube MCP/Composio with distinct Figma-specific triggers, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Commit: 366e45b

Reviewed: 2 days ago

Table of Contents

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.