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

92%

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

85%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 dense but well-structured auditor skill: highly actionable commands and clear validated workflows with one-level-deep references that resolve to real bundle files, docked only slightly for repetition between the runtime contract and the reference list.

Suggestions

Dedupe the file list: 'Runtime Contract' and 'Reference Materials' both enumerate the same references — keep one authoritative list and link from the other.

Consider collapsing the §2/§3/§5 subsections (Worked Examples, Guardrails, Translation) into a single 'Edge cases & guardrails' section; much of this restates rules already in Evidence Procedure and Verdict/Handoff.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no over-explaining of E-E-A-T) but is not fully lean — the runtime file list is repeated in 'Reference Materials', and the worked-examples/guardrails/translation subsections restate rules already implied elsewhere.	2 / 3
Actionability	Gives executable commands ('python3 "$AARON_SKILLS_ROOT/scripts/rubric-score.py" score <run.json>', the validate-audit-artifact invocation), typed profile names, explicit veto IDs, and a copy-paste report template — fully concrete guidance.	3 / 3
Workflow Clarity	The Evidence Procedure is a numbered sequence with validation feedback loops (revalidate after persist, 'Only proceed when validation passes'), a Validation Checkpoints checklist, and explicit status/verdict decision rules in the Handoff section.	3 / 3
Progressive Disclosure	Well-sectioned overview with one-level-deep, clearly signaled references; the linked bundle files references/item-reference.md and references/recursive-refinement.md (plus bundled auditor-runtime.md) all exist in the references/ directory.	3 / 3
	Total	11 / 12 Passed

Description

100%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.

The description is concise, third-person, and hits all four anchors at the top of the scale: concrete actions, natural trigger terms, both what and when, and explicit boundaries against sibling skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'runs a typed 80-item CORE-EEAT profile with evidence coverage, veto checks, and a fix plan' — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (the typed CORE-EEAT profile, evidence coverage, veto checks, fix plan) and when ('Use when auditing content quality, E-E-A-T, or publish readiness'), satisfying the explicit-trigger anchor.	3 / 3
Trigger Term Quality	'Use when auditing content quality, E-E-A-T, or publish readiness' uses natural terms a user would actually say, with good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	Explicit de-confliction — 'Not for structural tags/headers alone — use on-page-seo-checker; not for domain/citation trust — use domain-authority-auditor' — carves a clear niche unlikely to trigger the wrong skill.	3 / 3
	Total	12 / 12 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: 4a77c48

Reviewed: 9 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.