content-quality-auditor

Use when auditing content quality, E-E-A-T, or publish readiness; runs a typed 80-item CORE-EEAT profile with evidence coverage, veto checks, and a fix plan. Not for structural tags/headers alone — use on-page-seo-checker; not for domain/citation trust — use domain-authority-auditor. 内容质量/EEAT评分

Quality

88%

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

Quality

Content

77%Weight 40%Scale 1-5

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

The skill body delivers strong, executable workflow guidance with explicit validation checkpoints for a high-stakes audit task. Its main weakness is progressive disclosure: redundant reference listings and mixed/broken reference paths create navigation friction that a standalone reader would struggle to resolve.

Suggestions

Consolidate the duplicate Runtime Reads and Runtime Contract sections into a single reference list so the bundled-vs-repo path distinction is stated once, not enumerated twice.

Reconcile reference paths so the bundled references/ files and the ../../../references repo paths are clearly labeled (standalone vs plugin install); broken relative links like core-eeat-benchmark.md and humanizer-slop.md are not present in the bundle and should be flagged as repo-only.

Move the CORE-EEAT benchmark detail (80 stable IDs, veto semantics) into the referenced benchmark file and keep the SKILL.md overview to trigger guidance and the high-level procedure.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely token-efficient with little concept over-explanation, but sections like the Runtime Reads/Runtime Contract duplication and extensive worked-examples add length that could be trimmed without losing clarity.	4 / 5
Actionability	Concrete executable commands are present ("python3 \"$AARON_SKILLS_ROOT/scripts/rubric-score.py\" score <run.json>", validate-audit-artifact.py), with specific profile/ID enums and verdict rules; minor gaps are externalized to runtime references rather than fully inlined.	4 / 5
Workflow Clarity	Multi-step Evidence Procedure is explicitly sequenced with validation checkpoints (qualified vetoes, typed run conformance, "NEEDS_INPUT" gating, Validation Checkpoints section and "only when valid" persistence gating) plus feedback loops for error recovery.	5 / 5
Progressive Disclosure	Structure is present with a Reference Materials section and real bundle files (auditor-runtime.md, item-reference.md, recursive-refinement.md), but the body duplicates two reference lists (Runtime Reads vs Runtime Contract), mixes repo-root paths (../../../references) that won't resolve in a standalone install with bundled references, and inlines substantial framework detail that belongs in the referenced benchmark.	3 / 5
	Total	16 / 20 Passed

Description

100%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.

The description is exemplary: it states concrete capabilities, provides natural trigger phrases, answers both what and when, and draws clear boundaries against sibling skills to avoid conflicts.

Dimension	Reasoning	Score
Specificity	Names the concrete audit type ("typed 80-item CORE-EEAT profile"), explicit outputs ("evidence coverage, veto checks, and a fix plan"), plus distinct exclusion boundaries — comprehensive coverage of concrete actions.	5 / 5
Completeness	Explicitly answers both what ("runs a typed 80-item CORE-EEAT profile with evidence coverage, veto checks, and a fix plan") and when ("Use when auditing content quality, E-E-A-T, or publish readiness") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Covers natural user phrases ("auditing content quality", "E-E-A-T", "publish readiness") plus variants ("publish-readiness", "CORE-EEAT review"), giving thorough keyword coverage including synonyms.	5 / 5
Distinctiveness Conflict Risk	Clear niche (CORE-EEAT content quality) with explicit redirects to sibling skills (on-page-seo-checker, domain-authority-auditor), minimizing overlap and wrong-skill triggering.	5 / 5
	Total	20 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 9 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: seo-geo/tune/content-quality-auditor/SKILL.md
Commit: 64562bc

Reviewed: 4 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.