ad-account-auditor

Use when auditing a paid ad account for incremental contribution, wasted spend, or measurement integrity before scaling; runs a typed 20-item ROAS profile with verified vetoes and a SHIP/FIX/BLOCK/UNDECIDED gate on own exported data. Not for campaign structure design — use campaign-architect; not for creative production — use ad-creative-builder. 付费广告账户审计/ROAS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

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.

A well-structured, concise audit skill with strong workflow sequencing and explicit validation feedback loops. Its main weakness is bundle completeness: the executable scorer, validator script, and most referenced materials are not included, leaving a standalone reader able to collect observations but not fully execute or follow the primary reference path.

Suggestions

Bundle the executable artifacts the body depends on — the deterministic scorer and `validate-audit-artifact.py` — or clearly separate host-repo-only references from bundled ones so the full audit is runnable from the skill alone.

The Reference Materials section lists roas-benchmark.md, measurement-protocol.md, auditor-runbook.md, and scoring-semantics.md, none of which exist in the bundle; include them or note that they require the full repo/plugin install.

Resolve the dangling sibling-skill and `../../../protocol/offer-claims-registry` links (or mark them as cross-skill repo references) so progressive-disclosure navigation actually resolves within the bundle.

Dimension	Reasoning	Score
Conciseness	Lean, expert-oriented body with no explanations of concepts Claude already knows; terse sections and shorthand references assume competence, with only minor restatement of veto controls — not the padded, explanatory anchor 1.	3 / 3
Actionability	Gives concrete typed states, exact paths, an env-var one-liner, and a named validation script, but the deterministic scorer and `validate-audit-artifact.py` are not bundled, so the full workflow is not copy-paste executable from the bundle alone — matching the 'concrete but incomplete' anchor 2.	2 / 3
Workflow Clarity	Clear numbered scoring sequence, an explicit Validation Checkpoints checklist, and a validate → Write → revalidate feedback loop with fail-closed `NOT_SCORED` handling for the destructive persistence step.	3 / 3
Progressive Disclosure	Structure and reference signaling are good (Reference Materials section, one-level links), but most referenced files (runbook, scoring-semantics, roas-benchmark, measurement-protocol, runtime-invocation, the validator script, sibling skills) are absent from the actual bundle, so navigation does not resolve standalone.	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.

A strong, third-person description that states concrete capabilities, an explicit 'Use when' trigger, and clear anti-triggers naming sibling skills. It cleanly satisfies the what/when/distinctiveness requirements with no padding or voice violations.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'auditing a paid ad account for incremental contribution, wasted spend, or measurement integrity' and 'runs a typed 20-item ROAS profile with verified vetoes and a SHIP/FIX/BLOCK/UNDECIDED gate on own exported data' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('runs a typed 20-item ROAS profile...gate') and when ('Use when auditing a paid ad account...before scaling') with a present 'Use when' trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	Covers natural domain terms a user would say ('paid ad account', 'wasted spend', 'ROAS', 'before scaling') plus explicit anti-triggers, matching the good-coverage anchor rather than the single-domain anchor 2.	3 / 3
Distinctiveness Conflict Risk	Names a clear niche (paid-ad ROAS auditing) and disambiguates with anti-triggers ('Not for campaign structure design — use campaign-architect; not for creative production — use ad-creative-builder'), making wrong-skill triggering unlikely.	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: 11 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/activate/ad-account-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.