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.
84
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 what the skill does (generate structure specs for component dimensions and variants) and when to use it (with explicit trigger terms). It uses third person voice, is concise without being vague, and occupies a distinct niche that minimizes conflict risk with other skills.
| 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 scenarios). | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger terms: 'structure', 'structure spec', 'dimensions', 'spacing', 'density', 'sizing', and 'dimensional properties'. These cover natural variations a user would say when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around structure specifications and dimensional properties of components with density/size/shape variants. This is highly specific and unlikely to conflict with other skills like general documentation or styling 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 skill is exceptionally actionable with fully executable code and a well-structured multi-step workflow with proper validation checkpoints. However, it is severely over-length — the inline JavaScript code blocks are enormous and contain significant duplication (utility functions repeated across scripts). The content would benefit dramatically from extracting the large code blocks into separate referenced files, which would also improve progressive disclosure.
Suggestions
Extract the large JavaScript code blocks (Steps 4b, 4d, 4e, 11b, 11c) into separate referenced files (e.g., `scripts/extract-structure.js`, `scripts/cross-variant-compare.js`) and reference them from the main skill file, dramatically reducing token count.
Deduplicate shared utility functions (resolveBinding, collapsePadding, collapseCornerRadius, measureNode, loadAllFonts) into a single shared utilities section or file, referenced by each script that needs them.
Trim the MCP adapter table — Claude doesn't need explanations of what each operation does; a concise mapping table with just the two provider columns would suffice.
Move the detailed data shape documentation (the bullet lists explaining extraction return values) to the instruction file or a separate reference doc, keeping only a brief summary in the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~800+ lines. It contains massive inline JavaScript code blocks that are duplicated (e.g., resolveBinding, collapsePadding, collapseCornerRadius appear in both Step 4b and 4d scripts). Much of this could be extracted to separate files. The MCP adapter table and extensive inline code bloat the token budget significantly. | 1 / 3 |
Actionability | The skill provides fully executable JavaScript code blocks with specific placeholder patterns, concrete decision tables for preview parameters, deterministic rules for section planning, and copy-paste ready figma_execute scripts. Every step has precise, executable guidance. | 3 / 3 |
Workflow Clarity | The 13-step workflow is clearly sequenced with an explicit checklist, validation checkpoints (Step 8 audit, Step 12 visual validation with up to 3 fix iterations), feedback loops for truncated responses, and clear dependencies between steps. Each step specifies exactly what data feeds into subsequent steps. | 3 / 3 |
Progressive Disclosure | The skill references an external instruction file (agent-structure-instruction.md) and config file (uspecs.config.json), which is good progressive disclosure. However, the main file itself is a monolithic wall of content with massive inline code blocks that should be in separate files. The extraction scripts (Steps 4b, 4d, 4e) and rendering scripts (Steps 11b, 11c) could each be separate referenced files. | 2 / 3 |
Total | 9 / 12 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1592 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- redongreen/uSpec
- Commit
4eae941
- 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.