seo-authority-builder

Analyzes content for E-E-A-T signals and suggests improvements to build authority and trust. Identifies missing credibility elements. Use PROACTIVELY for YMYL topics.

Quality

67%

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/seo-authority-builder/SKILL.md

Quality

Content

50%Weight 40%Scale 1-3

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

A well-structured but largely generic E-E-A-T reference that catalogs signals and tactics Claude largely already knows, with an abstract analysis workflow and a placeholder output template. It lacks executable evaluation criteria, validation checkpoints, and any progressive disclosure into reference files.

Suggestions

Replace generic signal/tactic catalogs with a concrete, reproducible evaluation procedure — specific scoring criteria for each E-E-A-T dimension and exact checks to run against a page.

Add validation/verification to the workflow (e.g., re-check author bio presence, confirm schema validates, verify cited sources resolve) so the audit has a feedback loop.

Move the long signal catalogs and tactic lists into a separate reference file (e.g., REFERENCES.md) and keep SKILL.md as a concise overview that links one level deep.

Dimension	Reasoning	Score
Conciseness	The body is mostly sectioned rather than padded prose, but long enumerated lists restate domain knowledge Claude already has (e.g., trust signals 'Contact information', 'SSL certificates', 'Privacy policy/terms'), so it does not reach the lean anchor at 3; not level 1 because it avoids textbook concept explanations.	2 / 3
Actionability	Provides an output scorecard template and named deliverables, but the actual analysis procedure is abstract ('Analyze content for existing E-E-A-T signals') with placeholder values (X/10, [subject]) and no executable commands or concrete evaluation criteria — fitting the some-guidance-but-incomplete anchor; not level 1 because a concrete output structure exists.	2 / 3
Workflow Clarity	The 7-step Approach is sequenced, but there are no validation checkpoints or feedback loops for producing an audit scorecard, capping it at 2 per the validation guideline; not level 1 because a clear sequence is present.	2 / 3
Progressive Disclosure	Content is organized into clear sections with no nested references, but it is a single monolithic file with inline material (signal catalogs, tactic lists) that could be split into reference files; not level 3 because nothing is offloaded to one-level-deep references, not level 1 because organization is reasonable.	2 / 3
	Total	8 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 focused, third-person description that covers both capability and explicit trigger conditions, with concrete actions and a distinct E-E-A-T/YMYL niche. Its main weakness is trigger-term naturalness, relying on domain jargon and a Claude-facing 'PROACTIVELY' cue rather than phrases a user would naturally say.

Suggestions

Add natural user-facing trigger phrasing (e.g., 'Use when reviewing content for trust, author credibility, or YMYL pages like health, finance, or legal topics') instead of the instruction-style 'Use PROACTIVELY'.

Broaden trigger terms with common variations users actually say (e.g., 'author authority', 'content trust', 'credibility', 'Google quality signals').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Analyzes content for E-E-A-T signals', 'suggests improvements to build authority and trust', 'Identifies missing credibility elements' — matching the multi-action anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Explicitly answers what (analyze, suggest, identify) and when ('Use PROACTIVELY for YMYL topics'), matching the both-what-and-when anchor; not below because the when clause is explicit.	3 / 3
Trigger Term Quality	Includes relevant domain keywords ('E-E-A-T signals', 'authority and trust', 'YMYL topics') but these skew toward jargon and miss common user phrasings; 'PROACTIVELY' is Claude-facing instruction, not a natural user term. Not level 3 because coverage of natural variations is thin, not level 1 because YMYL/E-E-A-T are terms users in this domain do say.	2 / 3
Distinctiveness Conflict Risk	Scoped to a clear E-E-A-T/YMYL niche with distinct triggers unlikely to fire for unrelated skills; not level 2 because the trigger language is specific rather than generic.	3 / 3
	Total	11 / 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: rmyndharis/antigravity-skills
Path: skills/seo-authority-builder/SKILL.md
Commit: e63f7dd

Reviewed: 13 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.