geo-schema

Schema.org structured data audit and generation optimized for AI discoverability — detect, validate, and generate JSON-LD markup

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/geo-schema/SKILL.md

Quality

Content

65%

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

The content is highly actionable with concrete commands, complete JSON-LD templates, and a clear report format, but it is monolithic and verbose with scattered time-sensitive dates and no validation feedback loop. Splitting reference material into separate files and tightening framing would materially improve it.

Suggestions

Move the per-type schema property tables, the 0-100 scoring rubric, and the sameAs strategy into separate reference files (e.g. SCHEMA-TYPES.md, SCORING.md) linked one level deep from SKILL.md.

Add an explicit validation feedback loop to the workflow (e.g. "If validation fails → fix the schema → re-run validation → only proceed when it passes").

Provide or create the referenced fetch_page.py under scripts/ (it is currently cited but absent from the bundle), and isolate time-sensitive dates in a single "Deprecated/changed schemas" section.

Dimension	Reasoning	Score
Conciseness	Dense and substantive but ~360 lines with framing Claude largely knows (e.g. "structured data is the primary machine-readable signal that tells AI systems what an entity IS") and scattered time-sensitive dates ("Aug 2023", "December 2025", "2024") not isolated in a deprecated/old-patterns section, matching the mostly-efficient-but-could-be-tightened anchor.	2 / 3
Actionability	Provides an executable command ("python3 ~/.claude/skills/geo/scripts/fetch_page.py <url> page"), complete copy-paste JSON-LD templates, per-type required/recommended property lists, and a concrete report format, matching the anchor for fully executable, copy-paste-ready guidance.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Detection → Validation → Types → Generation → Output) with an 8-point validation checklist, but there is no explicit validate→fix→re-validate feedback loop for this batch audit operation, which per the guidelines caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Monolithic SKILL.md with no references/, scripts/, or assets/ directories; the referenced fetch_page.py does not exist in the bundle, and large blocks (per-type details, 0-100 scoring rubric, sameAs strategy) that could be split out are inline, matching the anchor for content that should be separate being inline.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 specific and distinctive, clearly stating concrete actions for a well-defined niche. Its main weakness is the absence of an explicit "Use when..." trigger clause and incomplete coverage of natural user terms like "rich results" or "schema markup".

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when auditing or generating structured data, JSON-LD, schema markup, or rich results for AI discoverability."

Include additional natural trigger terms users say, such as "rich results", "rich snippets", and "schema markup", to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "audit and generation" and "detect, validate, and generate JSON-LD markup" — matching the anchor for naming several specific actions rather than a vague domain or single action.	3 / 3
Completeness	Clearly answers "what" (audit/detect/validate/generate) but has no "Use when..." clause or equivalent explicit trigger, which per the guidelines caps completeness at 2; the "when" is only implied.	2 / 3
Trigger Term Quality	Includes relevant natural terms ("structured data", "JSON-LD", "Schema.org") but omits common variations users say such as "rich results", "rich snippets", or "schema markup", fitting the anchor for some keywords with missing variations.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Schema.org/JSON-LD structured data for AI discoverability) with distinct triggers unlikely to overlap with unrelated skills, matching the anchor for a clear niche with low conflict risk.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: zubair-trabzada/geo-seo-claude
Path: skills/geo-schema/SKILL.md
Commit: 9eec32f

Reviewed: 5 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.