When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,' 'audience targeting,' 'Google Ads,' 'Facebook ads,' 'LinkedIn ads,' 'ad budget,' 'cost per click,' 'ad spend,' 'should I run ads,' 'ABM,' 'account-based marketing,' 'B2B ads,' 'lead quality,' 'negative keywords,' 'Performance Max,' 'thought leader ads,' or 'when should I kill an ad.' Use this for campaign strategy, audience targeting, bidding, and optimization. For bulk ad creative generation and iteration, see ad-creative. For landing page optimization, see cro.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

67%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, actionable ads skill with strong reference routing and concrete operational guidance. Its main weakness is conciseness — several inline narrative sections could be tightened or moved to references.

Suggestions

Tighten the 'Modern Meta playbook' and audience sections: replace narrative analogies with bulleted, threshold-based guidance to cut tokens without losing signal.

Move the full 4-component retargeting framework and headline-mirror detail into a reference file, keeping only the routing pointer and the one-line principle inline.

Surface at least one explicit inline validation checkpoint for live-account operations (e.g., 'draft → propose change → expected effect → rollback → apply on approval') as a numbered sequence rather than only delegating it to audit-guardrails.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded in places — the Modern Meta playbook and audience sections carry extended narrative prose and analogies ('a hungry panda') that could be tightened; it is not a 4 because several sections over-explain beyond what Claude needs.	3 / 5
Actionability	Provides concrete, specific guidance — PAS/BAB frameworks, naming conventions with examples, 70/30 budget splits, 20% scaling increments, and a platform-by-platform audience-knowledge ratio table — with only minor gaps where hard numbers are deferred to references.	4 / 5
Workflow Clarity	Clear sequences with most checkpoints present (Before-Starting context gathering, decision-tree optimization levers, bid-strategy progression, pre-launch checklist, audit guardrails with draft-first/rollback); not a 5 because the hardest validation loops are delegated to reference files rather than stated inline.	4 / 5
Progressive Disclosure	Excellent Reference Routing table maps user intent to one-level-deep reference files (all 14 verified present) with coverage summaries; not a 5 because substantial playbook content (Meta Andromeda, retargeting framework, landing-page tricks) is inlined in the body rather than split out.	4 / 5
	Total	15 / 20 Passed

Description

95%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 with explicit 'Use when' triggers, comprehensive natural keyword coverage, and clear routing to adjacent skills. The only soft spot is that the enumerated actions are broad rather than granular.

Dimension	Reasoning	Score
Specificity	Names the paid-advertising domain and several concrete actions — 'campaign strategy, audience targeting, bidding, and optimization' — across named platforms, with only minor gaps in coverage; not a 5 because the named actions are somewhat broad rather than exhaustively specific.	4 / 5
Completeness	Explicitly answers both 'what' (campaign strategy, audience targeting, bidding, optimization on Google/Meta/LinkedIn/X) and 'when' via an explicit 'Use when the user wants help...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and user-phrasing such as 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'should I run ads,' 'when should I kill an ad,' 'Performance Max,' and 'negative keywords' — phrases a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	Clear paid-ads niche with distinct triggers, and it explicitly routes overlapping work away ('For bulk ad creative generation... see ad-creative. For landing page optimization, see cro.'), minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 7 suspicious	Warning

	Total	15 / 16 Passed

Repository: coreyhaines31/marketingskills
Path: skills/ads/SKILL.md
Commit: 5b2c000

Reviewed: ~4 hours 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.