The body delivers real, current expertise (type-status tables, error checklists, error-handling guidance) but is undermined by broken reference paths, an unreferenced bundle file whose content it duplicates, and ~70 lines of boilerplate templates Claude could generate unaided. Fixing the reference wiring and offloading templates would raise both conciseness and progressive disclosure.

Suggestions

Fix the reference paths: point the 'Schema Type Status' section at the existing references/deprecated-types-2024-2026.md instead of the nonexistent ../seo/references/schema-types.md, and either create schema/templates.json or remove the pointer to it.

Move the three inline JSON-LD templates (Organization, LocalBusiness, Article) into a reference file (or the proposed templates.json) and keep only one exemplar in SKILL.md, since Claude already knows standard Schema.org templates.

Concretize the validation checkpoints: name the actual command or tool for 'Validate output before presenting' (e.g., the parse script or Rich Results Test) and add a fix-and-revalidate loop.

Dimension	Reasoning	Score
Conciseness	The workflow sections and type-status tables are lean and genuinely valuable (current deprecation dates), but roughly 70 lines are full JSON-LD templates for Organization/LocalBusiness/Article that Claude already knows how to produce, and the deprecated-type details duplicate content already in the references/deprecated-types-2024-2026.md file. Mostly efficient, but includes unnecessary material that could be trimmed or offloaded.	3 / 5
Actionability	Concrete guidance is present throughout: a specific parse command ("${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo" run parse_html.py --url <url> --json), an explicit common-errors checklist, complete placeholder-marked templates, and an error-handling table with per-scenario actions. It falls short of fully executable because the parse script path does not exist in the bundle and generation step 5 ("Validate output before presenting") names no command or tool for validating.	4 / 5
Workflow Clarity	Detection and Generation are clearly sequenced numbered steps with a named validation section and error-checklist; the Error Handling table covers failure modes with recovery actions. Minor gap: the "Validate output before presenting" checkpoint is asserted but has no mechanism or fix-and-revalidate loop, so it sits just below the explicit-validation anchor.	4 / 5
Progressive Disclosure	Section structure is clear, but reference wiring is broken: "Read ../seo/references/schema-types.md" and "See schema/templates.json" point to files that do not exist in the bundle, while the one actual reference file (references/deprecated-types-2024-2026.md) is never linked and instead has its content duplicated inline. References exist but are not correctly signaled to real files, and content that should live in the reference file is inline.	3 / 5
	Total	14 / 20 Passed

Description

92%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 strong description: third-person voice, three concrete capability verbs, and an explicit exclusivity trigger clause. The only gap is a few missing natural synonyms (e.g., "rich snippets") that users commonly say when requesting this work.

Dimension	Reasoning	Score
Specificity	"Detect, validate, or generate Schema.org JSON-LD for a supplied page or entity" lists three concrete, distinct actions that comprehensively cover the skill's workflow (detect, validate, generate), matching the top anchor; nothing is vague or padded.	5 / 5
Completeness	The description explicitly answers both questions: "Detect, validate, or generate Schema.org JSON-LD..." states what it does, and "Use only when structured data or rich-result markup is requested" states exactly when to use it with concrete trigger phrases.	5 / 5
Trigger Term Quality	"structured data", "rich-result markup", "Schema.org", and "JSON-LD" are natural phrases users say, giving good keyword coverage, but common variations such as "rich snippets" and "schema markup" are missing, which keeps it below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (Schema.org structured-data markup) with distinct trigger terms, and the "Use only when..." constraint further minimizes the chance of firing for unrelated skills.	5 / 5
	Total	19 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: AgriciDaniel/claude-seo
Path: skills/seo-schema/SKILL.md
Commit: 4b99de2

Reviewed: 3 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.