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

50%

Does it follow best practices?

Impact

96%

2.34x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/all-skills/skills/figma-automation/SKILL.md

Quality

Discovery

50%

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 reasonably specific about capabilities and clearly distinctive due to the Figma + Rube MCP niche. However, it critically lacks a 'Use when...' clause, which means Claude may not reliably select this skill when users need it. The trigger terms could also be expanded to include more natural user language around design workflows.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Figma automation, design file management, extracting design tokens, or exporting assets from Figma.'

Include more natural trigger terms users might say, such as 'design', 'UI', 'mockups', 'prototypes', 'Figma plugin', or 'design system'.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: files, components, design tokens, comments, exports. Also includes a procedural instruction ('Always search tools first for current schemas'), which adds operational specificity.	3 / 3
Completeness	The description answers 'what' (automate Figma tasks) but has no explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'when' is entirely absent (not even implied beyond the domain), this scores at 1.	1 / 3
Trigger Term Quality	Includes relevant keywords like 'Figma', 'components', 'design tokens', 'comments', 'exports', and 'Rube MCP (Composio)'. However, it misses common user-facing variations like 'design', 'UI', 'mockups', 'prototypes', or file extensions that users might naturally say.	2 / 3
Distinctiveness Conflict Risk	The combination of 'Figma' and 'Rube MCP (Composio)' creates a very clear niche. It is unlikely to conflict with other skills given the specific tool and platform references.	3 / 3
	Total	9 / 12 Passed

Implementation

50%

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

This is a solid reference skill that covers Figma automation workflows comprehensively with good structure, specific tool names, and documented pitfalls. Its main weaknesses are the lack of executable examples (tool calls are described but not shown with actual invocation syntax), some content redundancy between sections, and missing validation/error-recovery checkpoints in workflows that could fail (like oversized payloads or failed renders).

Suggestions

Add executable tool invocation examples showing actual RUBE_SEARCH_TOOLS and FIGMA_GET_FILE_JSON calls with realistic parameters and expected response shapes.

Add explicit validation checkpoints to workflows—e.g., 'Check response for data_preview vs data field', 'If 413 error: reduce ids list to ≤5 nodes and retry', 'Verify image URLs are non-null before downloading'.

Consolidate the duplicated pitfalls (node ID format, file type support) into the single 'Known Pitfalls' section and reference it from workflows instead of repeating.

Consider moving the quick reference table and detailed per-workflow pitfalls into a separate REFERENCE.md to keep SKILL.md as a concise overview.

Dimension	Reasoning	Score
Conciseness	The skill is generally well-structured but includes some redundancy—pitfalls are repeated (node ID format appears in both workflow sections and a dedicated 'Known Pitfalls' section), and the quick reference table partially duplicates information already covered in the workflow sections. The prerequisite reminder to 'always call RUBE_SEARCH_TOOLS first' is stated multiple times. However, it avoids explaining basic concepts Claude already knows.	2 / 3
Actionability	Tool sequences are clearly named with specific parameter details and pitfalls, which is valuable. However, there are no executable code examples or copy-paste-ready commands—the 'Common Patterns' section uses pseudocode-style numbered lists rather than actual tool invocation syntax. The guidance is concrete enough to follow but not fully executable.	2 / 3
Workflow Clarity	Multi-step workflows are clearly sequenced with labeled steps (Prerequisite, Required, Optional), and pitfalls are documented per workflow. However, there are no explicit validation checkpoints or error recovery feedback loops—for example, no guidance on what to do if FIGMA_GET_FILE_JSON returns a 413 error beyond 'narrow scope or reduce depth', and no verify-then-proceed pattern after exports or renders.	2 / 3
Progressive Disclosure	The content is well-organized with clear sections and a useful quick reference table. However, at ~170 lines with detailed per-workflow pitfalls and parameters, some content (like the full quick reference table or detailed pitfalls) could be split into separate reference files. There are no bundle files to offload to, and the single external link is to Composio docs rather than structured sub-documents.	2 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: davepoon/buildwithclaude
Commit: d065ead

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.