geo-content

Content quality and E-E-A-T assessment for AI citability — evaluate experience, expertise, authoritativeness, trustworthiness, and content structure

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-content/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 body is highly actionable with concrete scoring rubrics and a ready-to-use output template, supported by a clear step sequence. It is somewhat verbose in its framing prose and monolithic in structure, which would benefit from trimming context Claude knows and splitting large reference material into separate files.

Suggestions

Trim the Purpose/intro framing that re-states concepts Claude already knows, keeping only the operational scoring detail.

Add explicit validation checkpoints in the workflow (e.g., "verify date accuracy before freshness scoring"; "confirm claim accuracy before scoring Trustworthiness").

Move the large E-E-A-T signal tables and/or the full output template into separate reference files referenced one level deep from the main body.

Dimension	Reasoning	Score
Conciseness	The operational scoring tables and output template earn their tokens, but the Purpose/intro prose restates context Claude largely knows (e.g., "AI platforms do not just find content — they evaluate whether content deserves to be cited"), matching the score-2 anchor of mostly-efficient with some unnecessary explanation.	2 / 3
Actionability	Scoring tables give explicit point allocations and "how to score" criteria, word-count/readability benchmarks are specific, and the output section provides a copy-paste-ready markdown template, matching the score-3 anchor of concrete, executable guidance.	3 / 3
Workflow Clarity	"How to Use This Skill" lists a clear 6-step sequence with a defined deliverable, but there are no explicit validation/feedback checkpoints (e.g., verifying claim accuracy before scoring trustworthiness), fitting the score-2 anchor of sequenced steps with implicit checkpoints.	2 / 3
Progressive Disclosure	The ~340-line file is well-organized into clear headed sections but is monolithic: large reference tables and the full output template are inline with no one-level-deep references, matching the score-2 anchor of content that should be separate being inline despite decent structure.	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 occupies a clear niche, but it omits any explicit "Use when..." trigger guidance and leans on specialist jargon for its trigger terms. Adding a natural-language trigger clause and more user-common phrasings would raise completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause such as "Use when assessing web content quality, E-E-A-T signals, or AI citability for GEO/SEO."

Broaden trigger terms with natural-user phrasings (e.g., "content quality", "will AI cite this", "SEO content audit") alongside the specialist terms.

Lead with the concrete action verb and keep the dimension list concise so the "what" reads cleanly alongside the new "when" clause.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions ("evaluate experience, expertise, authoritativeness, trustworthiness, and content structure"), enumerating specific dimensions rather than vague language, matching the score-3 anchor.	3 / 3
Completeness	It answers "what" (E-E-A-T/content-structure assessment) but provides no "Use when..." clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	It includes relevant terms ("content quality", "content structure") but leans on specialist jargon ("E-E-A-T", "AI citability") and lacks common natural-user phrasings, fitting the score-2 anchor of partial keyword coverage.	2 / 3
Distinctiveness Conflict Risk	The E-E-A-T / AI-citability framing carves a clear niche unlikely to trigger unrelated skills, matching the score-3 anchor of a distinct niche with unlikely conflict.	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-content/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.