meta-ads-analyzer

Diagnose Meta Ads campaign performance using Meta's actual system mechanics — Breakdown Effect, Learning Phase, Auction Overlap, Pacing, and Creative Fatigue — and produce structured, testable recommendations that avoid judging segments by average CPA instead of marginal efficiency.

Quality

72%

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

Fix and improve this skill with Tessl

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

Quality

Content

77%

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

The body is a strong, actionable diagnostic workflow with clear sequencing and concrete thresholds, but it is monolithic and carries redundancy between the phase explanations and the reference section. Splitting reference material into bundle files and de-duplicating the Breakdown Effect messaging would improve the weaker dimensions.

Suggestions

Move the 'Metric Naming Standard' table and 'Reference: Domain Concepts' into separate reference files (e.g., references/metric-naming.md, references/domain-concepts.md) linked one level deep, so the main body stays a lean overview.

De-duplicate the Breakdown Effect / marginal-vs-average messaging: state it once authoritatively (e.g., in 3A or the Output Standards) and reference it elsewhere rather than re-explaining it in the intro, Phase 4, and the Reference section.

Consolidate the lens explanations in Phase 3 with the Domain Concepts reference so each mechanic is defined once.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but the Breakdown Effect principle is restated in the intro, Phase 3A, Phase 4, Output Standards, and the Reference section, and the 'Reference: Domain Concepts' block largely re-explains material already covered in the phases, so it could be tightened.	2 / 3
Actionability	Highly concrete guidance for an instruction skill: exact thresholds (~50 events, 17+5 shops exception, ≥50% sustained 3+ days), copy-paste report template ('Use this exact structure. No deviation.'), and a raw→display metric naming table — all copy-paste ready.	3 / 3
Workflow Clarity	Clear Phase 0–5 sequence with explicit 'Output for this phase' checkpoints, checklists (learning state, fluctuation table), a verification filter in Phase 4 ('if a finding can't be restated in marginal terms, drop it'), and mandatory rollback plans for any pause/scale action.	3 / 3
Progressive Disclosure	Well-organized internally with clear sections, but it is a monolithic ~250-line SKILL.md with no bundle files; the Metric Naming Standard and Domain Concepts reference are inline content that could be split into one-level-deep reference files.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 clearly niche-scoped to Meta Ads, but it omits an explicit 'Use when...' trigger clause and leans on technical jargon over natural user phrasing. Adding explicit trigger guidance would lift the weaker completeness and trigger-term dimensions.

Suggestions

Append an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when analyzing Meta Ads campaign performance, diagnosing high CPA, or auditing a campaign before scaling').

Soften or contextualize the jargon list (Breakdown Effect, Auction Overlap, etc.) so the opening phrase relies on terms a user would naturally say rather than internal mechanic names.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Diagnose Meta Ads campaign performance", "produce structured, testable recommendations", and names the specific mechanics (Breakdown Effect, Learning Phase, etc.) — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Clearly states what the skill does, but there is no "Use when..." clause or equivalent explicit trigger guidance; the when is only implied, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains natural terms users would say ("Meta Ads campaign performance", "CPA", "recommendations") but is heavy on technical jargon (Breakdown Effect, Auction Overlap, marginal efficiency) and lacks common phrasings a user would naturally voice, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The description carves a clear Meta-Ads-specific niche around named system mechanics, making it unlikely to trigger for sibling skills like the multi-platform analyzer or campaign builder.	3 / 3
	Total	10 / 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: gooseworks-ai/goose-skills
Path: skills/ads/composites/meta-ads-analyzer/SKILL.md
Commit: 8866b2a

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.