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 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, domain-appropriate instruction skill with a clear sequenced workflow and explicit validation/checkpoint logic, plus clean one-level reference disclosure. It is slightly held back by repeated scope/delegation statements and by being strategic rather than directly executable.

Suggestions

Consolidate the repeated scope/delegation message (Skill Contract, Instructions step 8, and 'Scope guard') into a single authoritative block to remove redundancy and save tokens.

Add one concrete worked example of a finished account-structure output (e.g., a sample campaign/ad-group/negative-keyword map) to move the guidance from strategic toward copy-paste actionable.

Tighten the Data Sources paragraph by splitting the optional Google Ads MCP detail into its referenced CONNECTORS.md rather than inlining the URL and qualifier inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes domain competence (no over-explaining of PMax/ROAS), but the scope/delegation message is restated across the Skill Contract, step 8, and the 'Scope guard' block, which could be consolidated. Not a 5 because of that redundancy; not a 3 because there is no concept padding.	4 / 5
Actionability	Concrete, specific instruction-only guidance — exact ROAS A weights (0.15/0.30/0.10), named data exports, and discrete per-step actions — but it is strategic planning rather than copy-paste-executable commands, leaving minor gaps versus the 'fully executable' anchor.	4 / 5
Workflow Clarity	Eight clearly sequenced steps with explicit validation gates — 'If the placements report is absent, mark qualified ROAS-A1 Unknown', 'Any applicable Unknown makes the run NEEDS_INPUT/UNDECIDED/NOT_SCORED; do not emit an A score from partial coverage' — plus a 'Done when' checklist, matching the clear-sequence-with-explicit-validation anchor.	5 / 5
Progressive Disclosure	A concise overview body with well-signaled, one-level-deep references (roas-benchmark.md, CONNECTORS.md, SECURITY.md, skill-contract.md, measurement-control.md, budget-optimizer) collected in a Reference Materials section; no nested reference chains and content appropriately split.	5 / 5
	Total	18 / 20 Passed

Description

100%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 names concrete actions, supplies natural trigger phrases, and answers both 'what' and 'when' with explicit conflict-avoidance boundaries. Voice is consistently third person ('designs', 'scores') and it is concise despite the dense domain content.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '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' — comprehensive coverage with no vague padding.	5 / 5
Completeness	Explicitly answers both what (the design/audit/scoring actions) and when (the 'Use when the user asks...' trigger clause), and adds explicit 'Not for...' boundary guidance.	5 / 5
Trigger Term Quality	Embeds four natural user-spoken trigger phrases ('plan my paid account structure', 'pick Search vs PMax', 'lay out ad groups / asset groups', 'audit paid-vs-organic cannibalization') plus synonyms, covering the phrases a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (paid account structure + ROAS A) with three explicit 'Not for... use X' carve-outs (ad-account-auditor, budget-optimizer, site-structure-optimizer) minimizing wrong-skill triggering.	5 / 5
	Total	20 / 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: 17 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: ad/research/campaign-architect/SKILL.md
Commit: 888dd38

Reviewed: 6 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.