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

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.

The body is a well-structured, actionable audit runbook with strong workflow sequencing and explicit validation for a destructive gate. Conciseness and progressive disclosure are good but not perfect, owing to dense jargon-laden sentences and references that assume a larger repository layout rather than the standalone bundle.

Suggestions

Provide a literal, copy-paste-ready invocation example (the scorer command with the resolved `AARON_SKILL_ROOT` and required catalogs) so the runtime path is fully executable from the SKILL.md alone.

For standalone installs, clarify which `../../../references/*.md` paths are repository-only versus covered by the bundled `references/auditor-runtime.md`, so a one-folder install knows exactly what it can rely on.

Tighten the longest run-on sentences in "Runtime and Setup" and "Persistence" into shorter imperative steps to lift conciseness toward fully lean.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence — no concept padding, no "what a ROAS is" explanations — with every section earning its place; a few long run-on sentences and heavy acronym load keep it just below fully lean.	4 / 5
Actionability	Concrete and executable guidance throughout — the env-var resolution `AARON_SKILL_ROOT="${CLAUDE_PLUGIN_ROOT:-...}"`, named files, veto IDs (ROAS-R1/R2/O1/O2/A1), typed scorer, and `validate-audit-artifact.py` with `--relative-path` — with only minor gaps (no literal invocation code block for the scorer).	4 / 5
Workflow Clarity	Clear sequenced workflow with explicit validation checkpoints for a destructive/batch gate: fail-closed `NEEDS_INPUT/UNDECIDED`, a Validation Checkpoints section, and the persist-then-revalidate loop ("persist only through one full-content Write, then revalidate the target").	5 / 5
Progressive Disclosure	Good structure with clearly signaled one-level-deep references (auditor-runbook, scoring-semantics, roas-benchmark, runtime-invocation) plus the bundled `references/auditor-runtime.md` (verified present); however several referenced paths (`../../../references/*.md`, sibling `SKILL.md` files) point outside the local bundle rather than being self-contained, a minor organization gap.	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.

The description is strong: concrete capabilities, an explicit "Use when" trigger, and explicit exclusions that distinguish it from adjacent marketing skills. Trigger-term coverage is the only soft spot, leaning on jargon over the everyday phrases a user might say.

Suggestions

Add everyday synonyms a user might say (e.g. "ad spend", "PPC", "paid social", "paid media account") alongside the technical terms to broaden natural trigger coverage.

Consider including a concrete file-type or export trigger (e.g. "when the user shares campaign and order-ID exports") since the skill is gated on its own exported data.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "auditing a paid ad account for incremental contribution, wasted spend, or measurement integrity", "runs a typed 20-item ROAS profile with verified vetoes", and a "SHIP/FIX/BLOCK/UNDECIDED gate on own exported data" — giving comprehensive coverage rather than just naming the domain.	5 / 5
Completeness	Explicitly answers both what (auditing, ROAS profile, vetoes, gate) and when ("Use when auditing a paid ad account ... before scaling") with concrete trigger phrases, then reinforces scope with negative routing.	5 / 5
Trigger Term Quality	Natural terms like "auditing a paid ad account", "wasted spend", "before scaling", and "ROAS" are present, but the phrasing leans jargon-heavy ("incremental contribution", "measurement integrity") and omits common synonyms users might say such as "ad spend", "PPC", or "paid social".	4 / 5
Distinctiveness Conflict Risk	Clear niche (paid-ad account audit / ROAS scoring) with explicit negative routing — "Not for campaign structure design — use campaign-architect; not for creative production — use ad-creative-builder" — minimizing conflict with sibling skills.	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: 11 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/activate/ad-account-auditor/SKILL.md
Commit: 888dd38

Reviewed: 1 day 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.