create-structure

Generate structure specifications documenting component dimensions, spacing, padding, and how values change across density, size, and shape variants. Use when the user mentions "structure", "structure spec", "dimensions", "spacing", "density", "sizing", or wants to document a component's dimensional properties.

Quality

81%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a well-crafted skill description that clearly communicates its purpose, lists concrete actions, includes an explicit 'Use when...' clause with natural trigger terms, and occupies a distinct niche. It uses proper third-person voice and is concise without being vague. The description follows best practices closely and would allow Claude to reliably select this skill when appropriate.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Generate structure specifications', 'documenting component dimensions, spacing, padding', and 'how values change across density, size, and shape variants'. These are concrete, well-defined capabilities.	3 / 3
Completeness	Clearly answers both 'what' (generate structure specifications documenting component dimensions, spacing, padding, and variant changes) and 'when' (explicit 'Use when...' clause with specific trigger terms and a general condition about documenting dimensional properties).	3 / 3
Trigger Term Quality	Includes natural keywords users would say: 'structure', 'structure spec', 'dimensions', 'spacing', 'density', 'sizing', and 'dimensional properties'. Good coverage of terms a user working with design system components would naturally use.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche around structure specifications and dimensional properties of components. The combination of 'structure spec', 'density', 'sizing', and 'dimensional properties' is highly specific and unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

62%

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

This is a highly actionable and well-structured skill with excellent workflow clarity, complete executable code, and thorough validation steps. However, it suffers significantly from verbosity — duplicated utility functions across scripts, inline code that should be in separate files, and exhaustive inline documentation that inflates the token cost enormously. The progressive disclosure could be improved by extracting the large JavaScript blocks into referenced script files.

Suggestions

Extract the two large extraction scripts (Step 4b and 4d) into separate .js files and reference them, eliminating the duplicated collapsePadding/collapseCornerRadius/resolveBinding functions that appear in both scripts.

Move the MCP adapter table and figma-mcp page context explanation to a separate shared reference file (e.g., mcp-adapter.md) since this information likely applies across multiple skills.

Consolidate the rendering scripts (Steps 10, 11b, 11c) into referenced template files rather than inline code blocks, keeping only the placeholder substitution instructions inline.

Dimension	Reasoning	Score
Conciseness	This skill is extremely verbose at ~800+ lines. There is massive code duplication between the Step 4b extraction script and the Step 4d cross-variant comparison script (collapsePadding, collapseCornerRadius, resolveBinding are repeated nearly identically). Many sections contain exhaustive inline explanations that could be extracted to referenced files. The MCP adapter table, while useful, adds significant length that could be in a separate reference file.	1 / 3
Actionability	The skill provides fully executable JavaScript code for every step, with specific placeholder patterns (__NODE_ID__, __FRAME_ID__, etc.), concrete MCP tool names, complete data schemas, and detailed decision tables for preview parameters. Every step has copy-paste ready code with clear substitution instructions.	3 / 3
Workflow Clarity	The 13-step workflow is clearly sequenced with an explicit checklist at the top. It includes validation checkpoints (Step 8 audit against common mistakes, Step 12 visual validation with up to 3 fix iterations), error recovery guidance (truncation handling in 4b, MCP connection failures in Step 2), and explicit feedback loops. Each step clearly depends on outputs from previous steps.	3 / 3
Progressive Disclosure	The skill references external files appropriately (agent-structure-instruction.md, uspecs.config.json) and uses a checklist for navigation. However, the massive inline JavaScript code blocks (two 100+ line extraction scripts, multiple rendering scripts) should be in separate referenced files rather than inline. The skill is a monolithic wall of code and instructions that would benefit greatly from splitting the scripts into separate files.	2 / 3
	Total	9 / 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
skill_md_line_count	SKILL.md is long (1440 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: redongreen/uSpec
Commit: b1213ef

Reviewed: 3 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.