ads-performance-analytics

How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media dashboard, attribution analysis, ROAS vs LTV, multi-platform reconciliation, ad incrementality, geo holdout, conversion lift study, ghost bidding, paid media reporting, board-deck paid media metrics, blended CAC, MMM, MTA, last-click attribution. Also triggers when a marketer is about to scale, kill, or rebudget a campaign based on platform metrics, or when reconciling platform reports against warehouse revenue.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

A domain-rich interpretation playbook that pushes detail to seven real reference files and supplies concrete formulas, thresholds, worked examples, and a decision framework. It loses points on conciseness for re-explaining basic attribution/ROAS concepts and on workflow clarity for presenting considerations as a flat checklist rather than a checkpointed sequence.

Suggestions

Trim explanations of concepts Claude already knows (e.g., the definitional prose for last-click/first-click/linear/time-decay and 'ROAS is short-term / LTV is long-term'); keep only the platform-specific numbers and stage-based guidance.

Reformat the 12 considerations into a gated sequence with explicit validation checkpoints (e.g., 'After reconciling platform vs warehouse, if divergence >30%, flag double-counting before proceeding') so the workflow has clear pass/fail gates instead of a flat checklist.

Cut rhetorical framing such as 'The dashboard is the moment of truth...' and 'Both are wrong' to reduce token weight without losing the actionable guidance.

Dimension	Reasoning	Score
Conciseness	Dense with valuable platform-specific data (conversion windows, incremental-rate ranges, reconciliation math), but it re-explains concepts Claude already knows (definitional prose for last-click/first-click/linear/time-decay, 'ROAS is short-term / LTV is long-term') and carries rhetorical framing that could be trimmed.	2 / 3
Actionability	Concrete guidance throughout: a blended CAC formula, specific detection thresholds (>30% platform-vs-warehouse divergence), worked ROAS-vs-LTV and geo-holdout examples, and a 12-consideration framework ending in a Scale/Hold/Kill decision.	3 / 3
Workflow Clarity	The 12 considerations form a numbered sequence producing a clear decision output, but they read as a dimension checklist rather than a gated workflow with explicit validation checkpoints or error-recovery feedback loops.	2 / 3
Progressive Disclosure	The body serves as an overview with seven well-signaled one-level-deep references (all verified present in ./references/), each linked inline at the relevant section and listed with descriptions in a dedicated Reference files section.	3 / 3
	Total	10 / 12 Passed

Description

100%

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, specific description that names concrete capabilities, provides an explicit trigger clause covering both expert and plain-language scenarios, and occupies a clearly distinct niche. It cleanly answers both what the skill does and when to use it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing' — rather than vague marketing language.	3 / 3
Completeness	Explicitly answers what it does ('How to read paid media dashboards without fooling yourself' plus a capability list) and when to use it via an explicit 'Triggers on...' / 'Also triggers when...' clause.	3 / 3
Trigger Term Quality	An explicit 'Triggers on...' clause covers natural expert terms (ROAS vs LTV, geo holdout, ghost bidding, blended CAC, MMM, MTA, last-click attribution) plus plain scenarios ('scale, kill, or rebudget a campaign based on platform metrics').	3 / 3
Distinctiveness Conflict Risk	The niche is tightly scoped to paid-media dashboard interpretation with distinctive triggers, making it unlikely to fire for adjacent strategy or creative skills.	3 / 3
	Total	12 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: rampstackco/claude-skills
Commit: f1bc195

Reviewed: 12 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.