campaign-architect

Use when the user asks to "plan my paid account structure", "pick Search vs PMax", "lay out ad groups / asset groups", or "audit paid-vs-organic cannibalization"; designs campaign-type selection, ad-group/asset-group layout, targeting + match types, negative/exclusion hygiene, and a paid↔organic overlap audit, and scores the ROAS A (Audience) dimension + structure. Not for computing the final RQS — use ad-account-auditor; not for budget split — use budget-optimizer; not for organic site architecture — use site-structure-optimizer. 付费广告账户结构/广告系列规划/否定关键词

Quality

92%

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

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.

The body is a well-organized, actionable overview with a clear sequenced workflow and explicit completion/validation checkpoints. Its only weakness is mild redundancy in restating the scope boundary and auditor handoff across several sections.

Suggestions

Consolidate the 'scores A + structure only / not for RQS / not budget split' scope boundary into a single scope-guard statement; remove its repetition from step 8 and the Next Best Skill section to tighten token use.

Since no references/scripts/assets bundle exists, ensure the external references the body cites (skill-contract.md, roas-benchmark.md, CONNECTORS.md, SECURITY.md) are real, reachable paths so the signaled navigation is not broken.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and well-structured, but the scope boundary ('scores A + structure only', 'not for RQS / not budget split') and the auditor handoff are restated across the intro, Done-when, scope guard, step 8, and Next Best Skill, so it could be tightened.	2 / 3
Actionability	Gives concrete, specific instructions — 'derive negatives from the search-terms report', 'choose match types per theme', 'compare paid query themes against organic landing pages in the GA4 traffic-acquisition export' — plus copy-paste Quick Start prompts; guidance is actionable rather than abstract.	3 / 3
Workflow Clarity	Provides a clear 8-step sequence with an explicit 'Done when' checklist and a validation checkpoint for missing data ('If the placements report is absent, mark qualified ROAS-A1 Unknown ... Any applicable Unknown makes the run NEEDS_INPUT/UNDECIDED/NOT_SCORED'), including a feedback path.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), and the body cleanly signals one-level-deep external references via a dedicated Reference Materials section with descriptive markdown links (roas-benchmark.md, CONNECTORS.md, SECURITY.md, skill-contract.md), avoiding inline reference walls.	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 yet specific, answering what and when with natural trigger phrases and explicit anti-triggers that sharply bound the skill. It is a strong, low-conflict trigger description.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'designs campaign-type selection, ad-group/asset-group layout, targeting + match types, negative/exclusion hygiene, and a paid↔organic overlap audit, and scores the ROAS A (Audience) dimension', matching the score-3 anchor rather than naming a domain with only some actions.	3 / 3
Completeness	Explicitly answers both what ('designs ... and scores the ROAS A dimension + structure') and when via an explicit 'Use when the user asks to ...' clause, so it is not the level-2 case of an implied when.	3 / 3
Trigger Term Quality	Embeds natural phrases a user would actually say — 'plan my paid account structure', 'pick Search vs PMax', 'lay out ad groups / asset groups', 'audit paid-vs-organic cannibalization' — giving good coverage of natural terms rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche with distinct triggers plus explicit anti-triggers ('Not for computing the final RQS — use ad-account-auditor; not for budget split — use budget-optimizer; not for organic site architecture'), making it unlikely to fire for 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: 16 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/research/campaign-architect/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.