domain-authority-auditor

Use when auditing domain authority, trust, or citation credibility; runs a peer-relative 40-item CITE profile with evidence coverage and verified manipulation/penalty veto checks. Not for page-level content quality — use content-quality-auditor; not for backlink profiling alone — use offsite-signal-analyzer. 域名权威/网站可信度

Quality

86%

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

Quality

Content

81%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.

A well-structured, terse body with explicit validation checkpoints and clear workflow sequencing for a batch/persistence-oriented auditor skill. The main gaps are mild redundancy in the contract/setup sections and reference listings, plus reliance on external repo files not bundled here.

Suggestions

De-duplicate the reference listing: the Runtime Reads list and the Reference Materials section enumerate overlapping paths — consolidate into one clearly signaled navigation block.

Add a minimal copy-paste audit-run.schema.json input example so the scorer invocation is fully self-contained.

Clarify which references ship in the bundle versus which require the external repo, so a standalone install knows what is resolvable.

Dimension	Reasoning	Score
Conciseness	Dense and assumes Claude's competence with terse tables and verdict rules, but the Runtime Reads list, Runtime Contract prose, Skill Contract, and Required Setup overlap somewhat, and references appear in two places.	4 / 5
Actionability	Provides concrete executable commands (rubric-score.py, validate-audit-artifact.py, env resolution) and a specific evidence procedure, but lacks a copy-paste audit-run input example and relies on external repo scripts not present in the bundle.	4 / 5
Workflow Clarity	Clear sequenced procedure with an explicit Validation Checkpoints section, fail-closed fallback (return NOT_SCORED), and a persist→validate→revalidate feedback loop for the batch/persistence operations.	5 / 5
Progressive Disclosure	Well-signaled one-level-deep references with clear section headers and a verified bundled reference (references/auditor-runtime.md), but most references point to external ../../../references paths not in the bundle and the reference listing is duplicated across Runtime Reads and Reference Materials.	4 / 5
	Total	17 / 20 Passed

Description

92%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.

A strong, third-person description that explicitly states what the skill does, when to trigger it, and how it differs from neighboring skills via negative routing. Keyword coverage is good but could add a few more natural synonyms users might say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'runs a peer-relative 40-item CITE profile with evidence coverage and verified manipulation/penalty veto checks' — with comprehensive coverage of what the auditor does.	5 / 5
Completeness	Explicitly answers both what (40-item CITE profile, evidence coverage, veto checks) and when ('Use when auditing domain authority, trust, or citation credibility') with concrete trigger phrases and negative routing.	5 / 5
Trigger Term Quality	Good natural keywords ('auditing domain authority, trust, or citation credibility') but missing common user phrasings such as 'is this site trustworthy', 'reliable source', or 'domain reputation'.	4 / 5
Distinctiveness Conflict Risk	Clear niche with explicit negative routing ('Not for page-level content quality — use content-quality-auditor; not for backlink profiling alone — use offsite-signal-analyzer') minimizing conflict risk.	5 / 5
	Total	19 / 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/evaluate/domain-authority-auditor/SKILL.md
Commit: 888dd38

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.