pitch-ui-skills

Pitch's UI design system. Use when building interfaces inspired by Pitch's aesthetic - light mode, Inter font, 4px grid.

Quality

68%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/pitch/SKILL.md

Quality

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 is concise and well-structured with a clear 'Use when' clause and distinctive brand-specific triggers. Its main weakness is the lack of concrete actions—it describes what the system is but not what specific tasks it enables (e.g., creating components, applying styles, building layouts). Adding specific capabilities would strengthen the description.

Suggestions

Add concrete actions the skill performs, e.g., 'Creates UI components, applies consistent spacing, and generates styled layouts following Pitch's design system.'

Include additional trigger terms users might naturally say, such as 'design tokens', 'component library', 'Pitch-style UI', or 'clean minimal interface'.

Dimension	Reasoning	Score
Specificity	Names the domain (UI design system) and mentions some specific elements (light mode, Inter font, 4px grid), but doesn't list concrete actions like 'create components', 'apply spacing', or 'generate layouts'.	2 / 3
Completeness	Clearly answers both what ('Pitch's UI design system') and when ('Use when building interfaces inspired by Pitch's aesthetic - light mode, Inter font, 4px grid') with an explicit 'Use when' clause and trigger conditions.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'Pitch', 'UI design system', 'light mode', 'Inter font', and '4px grid', but misses common user-facing terms like 'design tokens', 'components', 'styling', 'theme', or 'Pitch-style'.	2 / 3
Distinctiveness Conflict Risk	Very specific to Pitch's design system with distinct identifiers (Pitch brand, Inter font, 4px grid, light mode), making it unlikely to conflict with other design system skills.	3 / 3
	Total	10 / 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 solid design system reference skill with clear semantic tokens, well-defined constraints using MUST/SHOULD/NEVER language, and good tabular organization. Its main weaknesses are the lack of executable implementation examples (no CSS/Tailwind code snippets) and some verbosity in raw data dumps (font size lists, count columns). Some color/token values seem inconsistent with the stated 'light mode' purpose (e.g., #000000 as page background, purple text colors in heading-1).

Suggestions

Add executable code examples showing implementation, e.g., a CSS custom properties block defining the semantic tokens, or a Tailwind config snippet with the spacing/border-radius scales.

Remove low-value data like the 'Count' column in text styles, the raw font size enumeration (already visible in the table), and consolidate duplicate information between tables and reference sections.

Review apparent inconsistencies: the skill says 'light-mode interfaces' and 'light backgrounds for primary surfaces' but defines surface-base as #000000 (black) and uses purple/lavender text colors in the typography table—clarify or correct these.

Dimension	Reasoning	Score
Conciseness	The skill contains useful design tokens and constraints but is overly verbose in places—the typography reference section lists every detected font size and repeats information already in the text styles table. The 'Count' column (all showing '1') adds no value. Some sections like 'Detected Layout Patterns' include raw data that could be trimmed.	2 / 3
Actionability	The skill provides concrete values (hex codes, pixel sizes, specific CSS properties) which is good, but lacks executable code examples showing how to implement these constraints in practice (e.g., Tailwind config, CSS custom properties setup, or component snippets). The MUST/SHOULD/NEVER rules are specific but remain declarative rather than demonstrating implementation.	2 / 3
Workflow Clarity	This is a reference/constraint skill rather than a multi-step workflow, so the single-task scoring note applies. The content is well-organized into clear sections (Colors, Typography, Spacing, etc.) with unambiguous rules using MUST/SHOULD/NEVER conventions, making it easy to follow when building UI components.	3 / 3
Progressive Disclosure	The content is reasonably well-structured with clear section headers and tables, but it's a monolithic file that could benefit from splitting detailed reference tables (all text styles, all font sizes) into a separate reference file. No external references are provided for deeper exploration of any topic.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ihlamury/design-skills
Commit: 126714e

Reviewed: 8 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.