ad-campaign-analyzer

Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ads/composites/ad-campaign-analyzer/SKILL.md

Quality

Content

65%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.

The body is strongly actionable with concrete schemas, formulas, thresholds, and a complete output template, and its phased workflow is well-sequenced. Its weaknesses are the absence of validation/confirmation checkpoints for destructive reallocation moves and a monolithic structure with no progressive disclosure into reference files.

Suggestions

Add explicit validation/confirmation checkpoints before destructive or batch actions — e.g. confirm the proposed reallocation sums to the same total budget and verify the user's monthly budget before recommending dollar shifts, and require user confirmation before pausing campaigns.

Split the monolithic file: keep the workflow overview in SKILL.md and move the full output template and the per-phase diagnostic tables into reference files (e.g. references/output-template.md, references/diagnostics.md), signaling them with one-level-deep links.

Remove redundancy — merge the 'When to Use' and 'Trigger Phrases' sections and drop the near-empty 'Cost' and 'Tools Required' filler — to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — it relies on tables and templates rather than explaining concepts Claude already knows — but ~360 lines carry redundancy (the 'When to Use' and 'Trigger Phrases' sections overlap, and 'Cost'/'Tools Required' add little), so it could be tightened.	3 / 5
Actionability	Highly concrete and executable: exact expected column schemas per platform, explicit formulas ('Channel CAC = CPA ÷ (MQL rate × SQL rate × Close rate)'), significance thresholds (100 clicks/30 conversions), and a full copy-ready output template covering the common cases.	5 / 5
Workflow Clarity	The Phase 0–5 sequence is clear, but the skill directs destructive/batch operations (pausing campaigns, dollar-amount budget reallocation) with no validation or confirmation checkpoints, which per the rubric caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	No bundle files exist and the skill is a single monolithic ~360-line SKILL.md; section headers give some structure, but content that would naturally live in reference files (the full output template, all diagnostic tables) is inlined with no signaled references.	3 / 5
	Total	14 / 20 Passed

Description

75%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.

The description is specific and distinct, naming many concrete analytical actions and a clear niche, but it omits an explicit 'when to use' trigger clause, leaving completeness only weakly implied. Adding a 'Use when...' sentence with natural user phrasings would lift the completeness and trigger-term scores.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to analyze ad campaign performance, decide which ads to pause or scale, or reallocate ad budget across Google/Meta/LinkedIn.'

Add the natural trigger terms users actually say — 'ROAS', 'which ads should I kill/pause', 'ad spend', 'where am I getting the best return' — to broaden trigger coverage.

Keep the concrete action list as-is; it is already comprehensive and is the description's strongest dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the domain — 'identify what's working, what's wasting budget', 'specific cut/scale/test recommendations', 'Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation', 'specific dollar-amount shift recommendations and scenario modeling' — matching the comprehensive-coverage anchor.	5 / 5
Completeness	The 'what' is clearly and concretely answered, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural phrasings users say ('ad campaign performance', 'what's working', 'what's wasting budget', 'cut/scale/test', 'budget reallocation') but omits common natural variations users actually voice ('ROAS', 'which ads should I kill', 'my Google Ads', 'ad spend').	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche — cross-platform ad campaign diagnosis and budget reallocation for Google/Meta/LinkedIn — with distinct triggers and minimal overlap risk with unrelated skills.	5 / 5
	Total	17 / 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: gooseworks-ai/goose-skills
Path: skills/ads/composites/ad-campaign-analyzer/SKILL.md
Commit: 2523432

Reviewed: 7 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.