A compact, well-structured instructional skill that gives concrete MCP resource paths and clear boundaries. Its weakest area is workflow clarity — the operating sequence is implied by section order rather than stated, and validation is conditional with no feedback loop.

Suggestions

Convert the Rules section into an explicit ordered workflow (e.g., 1. Read relevant WPDS docs via the MCP, 2. Select components/tokens, 3. Implement, 4. Validate with lint scripts, 5. Recap), so the sequence and checkpoints are unambiguous.

Strengthen the Validation rule with a feedback loop: what to do when lint fails (fix and re-run until clean) rather than the vague 'use them to validate... when possible'.

Tighten conciseness by removing the 'etc etc' filler, deduplicating MCP setup info between frontmatter and Prerequisites, and shortening the synonyms list.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and imperative, but has minor trimmable material: the synonyms list, the prerequisites paragraph repeating MCP information already in the frontmatter, and sloppy filler like "etc etc".	4 / 5
Actionability	Provides mostly concrete guidance including exact MCP resource URIs ("wpds://components/:name", "wpds://design-tokens") and a default tech stack, but the validation rule ("use them to validate... when possible") and output rules lack specifics.	4 / 5
Workflow Clarity	The intended order (consult MCP docs, apply WPDS components/tokens, validate with lint scripts, summarize output) is present but only implicit in the section layout, with no explicit checkpoints or error-handling loop for the validation step.	3 / 5
Progressive Disclosure	This is a short, single-purpose skill with clean, well-organized sections and no bundle files; it needs no external references since the MCP server supplies the detailed documentation, which fits the simple-skill case.	5 / 5
	Total	16 / 20 Passed

Description

73%Weight 40%Scale 1-5

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

A concise, well-targeted description with an explicit "Use when" trigger and a clearly identifiable niche. Its main weakness is thin capability coverage — it names the domain and artifacts but only one action, and does not state what it does with them.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete action ("building UIs") but the remaining terms ("components, tokens, patterns, etc.") are objects rather than actions, so coverage of specific capabilities is not comprehensive.	3 / 5
Completeness	It explicitly answers "when" ("Use when building UIs leveraging the WordPress Design System") and gives a clear "what", but the "what" stops short of stating what is actually done with the components/tokens (e.g., apply, select, follow best practices), so it is not fully concrete.	4 / 5
Trigger Term Quality	Includes good natural keywords ("building UIs", "WordPress Design System", "WPDS", "components, tokens, patterns") with the WPDS synonym covered, but misses common variations a user might say such as "WordPress UI", "Gutenberg", or "design tokens".	4 / 5
Distinctiveness Conflict Risk	The WordPress Design System / WPDS niche is specific with distinct trigger terms (WPDS, design system components, tokens), creating minimal risk of firing for unrelated skills.	5 / 5
	Total	16 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: WordPress/agent-skills
Path: skills/wpds/SKILL.md
Commit: 3cf7f6f

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.