Things's UI design system. Use when building interfaces inspired by Things's aesthetic - light mode, Inter font, 8px grid.
70
62%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/things/SKILL.mdQuality
Discovery
75%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 clearly identifies its niche (Things-inspired UI design) and provides explicit trigger conditions, making it strong on completeness and distinctiveness. However, it lacks concrete action verbs describing what the skill actually does (e.g., generate components, apply styles, create layouts) and could benefit from additional trigger terms users might naturally use.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Generates UI components, applies color tokens, and creates layouts following Things's design system.'
Include additional natural trigger terms users might say, such as 'Things app style', 'minimal task manager UI', 'clean productivity app design', or 'Things-like interface'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (UI design system for Things) and mentions some specific elements (light mode, Inter font, 8px grid), but doesn't list concrete actions like 'create layouts', 'style components', or 'generate color palettes'. | 2 / 3 |
Completeness | Answers both 'what' (Things's UI design system) and 'when' explicitly ('Use when building interfaces inspired by Things's aesthetic - light mode, Inter font, 8px grid'), providing clear trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'Things', 'UI design system', 'light mode', 'Inter font', '8px grid', but misses common variations users might say such as 'task manager UI', 'clean minimal design', 'Things app style', or 'design tokens'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Things app's aesthetic with distinct identifiers (Inter font, 8px grid, light mode). Unlikely to conflict with generic UI or design system skills. | 3 / 3 |
Total | 10 / 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 reasonably well-structured design system reference with specific, concrete values (colors, typography, spacing) and clear constraint language (MUST/SHOULD/NEVER). Its main weaknesses are the lack of executable code examples showing how to implement these tokens, some raw-audit-output artifacts that could be cleaned up, and an empty Components section that suggests incompleteness. Adding code snippets and splitting detailed reference tables into separate files would improve it significantly.
Suggestions
Add at least one executable code example (e.g., a CSS custom properties block or Tailwind config) showing how to apply the design tokens
Remove or complete the empty '## Components' section, and clean up raw audit artifacts like '(used 7x)' and the duplicate `text-14px` entries
Consider extracting the detailed reference tables (Semantic Tokens, Text Styles) into a separate REFERENCE.md file and linking to it, keeping SKILL.md as a concise overview
Add a brief workflow or checklist for applying the design system to a new component (e.g., 1. Set base tokens → 2. Apply typography scale → 3. Verify contrast ratios → 4. Check spacing grid alignment)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with well-structured tables and clear MUST/SHOULD/NEVER constraints. However, some redundancy exists (e.g., `text-primary` and `accent` both map to #729AE0, duplicate `text-14px` entries, 'Count' column adds little value). The 'Detected Layout Patterns' section and some metadata like '(used 7x)' feel like raw audit output rather than curated guidance. | 2 / 3 |
Actionability | The skill provides specific values (hex codes, pixel sizes, font weights) which are concrete and actionable for implementation. However, it lacks any executable code examples — no CSS snippets, no Tailwind config, no component templates. For a UI design system skill, at least one concrete code example showing how to apply these tokens would significantly improve actionability. | 2 / 3 |
Workflow Clarity | The content is organized as a reference document with clear categorical sections, which is appropriate for a design system. However, there's no guidance on the workflow of applying these constraints — no sequence for building a component, no validation steps to check compliance. The 'When to Apply' section is minimal and doesn't guide through a process. | 2 / 3 |
Progressive Disclosure | The content is well-sectioned with clear headers and tables, making it scannable. However, it's a fairly long monolithic document (~130 lines of dense reference material) with no references to external files for detailed topics like component patterns or examples. The empty '## Components' section suggests incomplete organization. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
126714e
Table of Contents
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.