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

88%

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

77%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.

The body is a well-structured, actionable auditor spec with strong workflow sequencing and validation feedback loops. Its main weaknesses are verbosity from overlapping worked-example/guardrail sections and a reference layer where one bundled file is orphaned and several paths resolve only at repo-root install.

Suggestions

Collapse §2 Worked Examples, §3 Guardrails, and §5 Translation into the Verdict Rules / Evidence Procedure they restate, or move them to a bundled reference, to reduce token overlap.

Reference the bundled example-report.md from the body (e.g. in Report or Reference Materials) so no bundle file is orphaned, and note which reference paths are repo-install-only versus standalone-bundled.

Trim policy restatements between Runtime Contract, Skill Contract, and Validation Checkpoints where the same constraints (locked cohort, 40 explicit states, no absolute-anchor laws) recur.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of concept-explanation padding Claude already knows, but §2 Worked Examples, §3 Guardrails, and §5 Translation overlap with Verdict Rules and Evidence Procedure and could be tightened; it is mostly efficient but verbose even though accurate, fitting the score-2 anchor rather than the lean score-3 anchor.	2 / 3
Actionability	Provides copy-paste-ready commands — `python3 "$AARON_SKILLS_ROOT/scripts/rubric-score.py" score <run.json>` and `python3 "$AARON_SKILLS_ROOT/scripts/validate-audit-artifact.py" <draft> --relative-path <target>` — plus an explicit env-resolution one-liner and concrete typed input, matching the executable score-3 anchor (instruction-only context, so absence of more code is not penalized).	3 / 3
Workflow Clarity	Clear sequence (Required Setup → numbered Evidence Procedure → Report → Verdict Rules → Persistence → Validation Checkpoints) with explicit validation feedback loops ("validate it... persist only through one full-content Write, and revalidate the target") and a Validation Checkpoints list, matching the score-3 anchor; the persistence write is a risky operation and is properly guarded.	3 / 3
Progressive Disclosure	A Reference Materials section and Next Best Skill section give clearly signaled one-level-deep navigation, and auditor-runtime.md is a real bundled file; however example-report.md sits orphaned in the bundle and several body references (../../../references/auditor-runbook.md, scoring-semantics.md, cite-domain-rating.md, framework-catalog.json) point outside the bundle to repo-root paths, so organization could be cleaner for a standalone install, fitting score-2 rather than the fully-resolved score-3.	2 / 3
	Total	10 / 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 strong: third-person voice, concrete actions, an explicit Use-when trigger, and explicit negative-routing against two sibling skills. Minor jargon ("CITE profile", "veto checks") is offset by natural trigger terms.

Dimension	Reasoning	Score
Specificity	Quotes "runs a peer-relative 40-item CITE profile with evidence coverage and verified manipulation/penalty veto checks" — multiple concrete actions (profile run, evidence coverage, veto verification), matching the score-3 anchor rather than the single-action score-2 anchor.	3 / 3
Completeness	Explicitly answers both: what ("runs a peer-relative 40-item CITE profile...") and when ("Use when auditing domain authority, trust, or citation credibility"), with an explicit Use-when trigger, satisfying the score-3 anchor and not the score-2 cap.	3 / 3
Trigger Term Quality	Natural user terms appear — "auditing domain authority, trust, or citation credibility", "page-level content quality", "backlink profiling" — covering the phrases a user would actually say, beyond jargon like "CITE profile".	3 / 3
Distinctiveness Conflict Risk	Negative routing — "Not for page-level content quality — use content-quality-auditor; not for backlink profiling alone — use offsite-signal-analyzer" — carves a clear niche and actively prevents mis-trigger, matching the score-3 distinct-trigger anchor.	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/evaluate/domain-authority-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.