claude

A research-journal aesthetic printed on warm stone — authoritative, editorial, almost achromatic. Pages live on warm ivory parchment (never pure white), with near-black slate as the dominant ink.

Quality

32%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/claude/SKILL.md

Quality

Content

57%

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

The content is a well-structured, self-contained instruction skill with concrete design tokens, a clear authoring workflow, and explicit quality gates. Its main gaps are a lack of worked examples and explicit validation checkpoints, plus minor verbosity in the typography scale and some redundancy across guidance sections.

Suggestions

Add one concise worked example (e.g. a sample button guideline showing anatomy, states, tokens, and accessibility criteria) so the abstract directives become copy-paste concrete.

Turn the QA checklist and Quality Gates into explicit gating steps inside the workflow ('validate against gates; fix and re-check before finalizing') to add a real feedback loop.

Trim the font-weight list to the weights actually used and de-duplicate 'Expected Behavior' against 'Quality Gates' to recover tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and never explains basics Claude already knows, but it pads the typography scale with every weight (100–900) and lets 'Expected Behavior' and 'Quality Gates' overlap, so it could be tightened further.	2 / 3
Actionability	It gives concrete tokens (#141413, spacing 4/8/12/16/24/32), a required output structure, and must/should language, but several directives stay abstract ('preserve visual hierarchy', 'keep interaction states explicit') and no worked example demonstrates a finished component guideline.	2 / 3
Workflow Clarity	The six-step 'Guideline Authoring Workflow' is clearly sequenced and ends with a QA checklist plus 'Quality Gates', but there are no explicit validate→fix→retry checkpoints gating progression, so checkpoints are implicit rather than enforced.	2 / 3
Progressive Disclosure	No bundle files exist and the skill is self-contained, so the well-organized section structure (Mission, Brand, Style Foundations, Workflow, Output Structure, Quality Gates) satisfies progressive disclosure for a single-file skill without external references.	3 / 3
	Total	9 / 12 Passed

Description

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 frontmatter description reads as an evocative brand statement rather than a skill description: it conveys the aesthetic vividly but never states the skill's purpose or when to invoke it. It lacks action verbs, natural trigger terms, and any 'Use when' guidance, leaving Claude little basis to select this skill.

Suggestions

Rewrite the description to lead with the skill's function in third person, e.g. 'Authors implementation-ready design-system guidelines for Claude interfaces...', naming concrete actions like defining tokens, component rules, and accessibility criteria.

Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g. 'Use when creating or updating a Claude UI design system, brand guidelines, component styling rules, or design tokens').

Keep the aesthetic as a brief qualifier rather than the whole description so the skill's purpose and triggers are not buried under prose.

Dimension	Reasoning	Score
Specificity	The description names no actions the skill performs; it paints an aesthetic in poetic terms ('research-journal aesthetic printed on warm stone', 'near-black slate as the dominant ink') rather than stating what the skill does, matching the 'vague or no actions; abstract language' anchor.	1 / 3
Completeness	It answers neither what the skill does (design-system guideline authoring) nor when to use it, and there is no 'Use when...' clause or equivalent trigger guidance, so both the 'what' and 'when' are missing.	1 / 3
Trigger Term Quality	Phrases like 'warm ivory parchment', 'clay accent', and 'almost achromatic' are not words a user would naturally say when needing this skill; natural triggers such as 'design system', 'brand guidelines', or 'UI style guide' are absent.	1 / 3
Distinctiveness Conflict Risk	It is anchored to one specific visual aesthetic, so it is unlikely to fire for unrelated skills (PDF, git, etc.), but it gives no functional signal to distinguish it from other general design or brand-skills, so overlap remains possible.	2 / 3
	Total	5 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: bergside/awesome-design-skills
Path: skills/claude/SKILL.md
Commit: f631a09

Reviewed: 1 day 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.