Name: ads-performance-analytics
Rating: 75.2 (1 reviews)
Author: rampstackco

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

93%

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

The canonical home for this skill is ads-performance-analytics in rampstackco/claude-skills

Quality

Content

92%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 interpretive playbook with a clear checklist workflow and strong progressive disclosure via verified reference files. The main improvement opportunity is trimming general concept explanations that Claude already knows to tighten token efficiency.

Suggestions

Condense the generic attribution-model definitions (last-click, first-click, linear, time-decay, U-shaped) to one-line differentiators since Claude already knows these models; keep only the paid-media-specific application guidance.

Move the full per-model prose in 'Attribution models in practice' into the existing attribution-model-comparison.md reference, leaving a compact decision-oriented summary inline.

Trim the explanatory preamble in 'Platform-reported vs reality' that defines view-through and modeled conversions at length; lead with the platform-specific defaults and the reconciliation rule instead.

Dimension	Reasoning	Score
Conciseness	Mostly dense and actionable with concrete platform-specific facts and worked examples, but it over-explains general concepts Claude already knows (generic definitions of last-click, first-click, view-through, self-attribution bias), placing it just below the lean-and-efficient anchor.	4 / 5
Actionability	Highly actionable for an interpretive skill: concrete formulas ('blended CAC as (total ad spend across platforms) divided by (total new customers from warehouse)'), specific numeric ranges (branded search 5-20% incremental), worked examples with numbers, a 12-consideration framework, and a Scale/Hold/Kill decision rule covering common cases.	5 / 5
Workflow Clarity	Clear checklist-driven workflow (the 12 considerations) with explicit validation/detection thresholds ('exceed...by more than 30%, you have heavy double-counting'), a data-availability feedback rule ('A stated gap is a complete answer'), and incrementality tests as a correction loop.	5 / 5
Progressive Disclosure	Clear overview with seven well-signaled one-level-deep references (all verified to exist in ./references/), each linked inline and indexed in a dedicated 'Reference files' section, with detail appropriately offloaded and summaries kept inline.	5 / 5
	Total	19 / 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, explicit description that pairs a clear statement of purpose with extensive, natural trigger terms and a well-defined paid-media niche. The only weakness is a slight reliance on topic enumeration over concrete action verbs and one vague closing phrase.

Dimension	Reasoning	Score
Specificity	Lists several specific capabilities ('Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise...incrementality testing'), but these are domain topics more than crisp action verbs and one phrase ('failure modes that produce expensive lessons') is vague, so it sits just below the comprehensive-action anchor.	4 / 5
Completeness	Explicitly answers both what ('How to read paid media dashboards without fooling yourself...') and when with concrete trigger clauses ('Triggers on...', 'Also triggers when a marketer is about to scale, kill, or rebudget...'), matching the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including synonyms and natural phrases users say ('read paid media dashboard', 'ROAS vs LTV', 'geo holdout', 'ghost bidding', 'blended CAC', 'MMM', 'MTA', 'board-deck paid media metrics'), matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Clear paid-media-analytics niche with highly distinctive triggers (ghost bidding, conversion lift study, geo holdout, blended CAC) and minimal overlap risk with adjacent analytics skills.	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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: rampstackco/claude-skills
Path: dist/pi/.agents/skills/ads-performance-analytics/SKILL.md
Commit: a67dd34

Reviewed: 2 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.