meta-ads-analyzer

Diagnose Meta Ads campaign performance and account gaps using Meta's actual system mechanics — including customer-journey coverage, Breakdown Effect, Learning Phase, Auction Overlap, Pacing, and Creative Fatigue. Use for performance diagnosis, account audits, full-funnel or TOF/MOF/BOF gap analysis, deciding what to test or create next, and producing novice-friendly recommendations without forcing every campaign or ad into a funnel stage.

Quality

79%

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

75%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, highly actionable diagnostic skill with a clear phased workflow and properly signaled one-level-deep reference. Its main weakness is redundancy between the Phase 2–3 lenses and the 'Reference: Domain Concepts' section, which inflates token cost.

Suggestions

Remove or sharply compress the 'Reference: Domain Concepts' section (Breakdown Effect, Learning Phase, Auction Overlap, Pacing, Fluctuations) since each concept is already operationally defined in Phases 2–3; keep only the Creative Fatigue detail that is not covered earlier.

Add a short explicit validation/gate step in Phase 3 (e.g., 'confirm sufficient impressions/sample size before interpreting any ranking or CPA') to make the existing guardrails into a visible checkpoint.

Consider moving the full Metric Naming Standard table into references/ and keeping only the most-used mappings inline, to tighten the SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and specialized, but the 'Reference: Domain Concepts' section re-explains Breakdown Effect, Learning Phase, Auction Overlap, Pacing, and Performance Fluctuations already covered in Phases 2–3, creating noticeable redundancy.	3 / 5
Actionability	Highly actionable for an instruction-only skill: a concrete evaluation-level table, learning thresholds (~50 events, 17+5 shops), six diagnostic lenses with spotting/action guidance, a metric-naming map, and a copy-paste report template cover the common cases.	5 / 5
Workflow Clarity	A clear 6-phase sequence (Intake → Evaluation Level → Learning → Diagnose → Synthesize → Report) with per-phase 'Output for this phase' checkpoints and explicit guardrails, though explicit validate→fix→retry feedback loops are not present (acceptable for non-destructive analysis).	4 / 5
Progressive Disclosure	One real reference file (references/customer-journey-coverage.md) is clearly signaled with markdown links and kept one level deep, but a fair amount of reference-style content (domain concepts, metric table) is inlined rather than split out.	4 / 5
	Total	16 / 20 Passed

Description

83%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 that clearly states what the skill does and when to use it with concrete trigger phrases and a distinctive Meta-ads niche. It could add a few more natural user keywords (CPA, ROAS, pause/scale) to tighten trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Diagnose Meta Ads campaign performance and account gaps', 'account audits', 'full-funnel or TOF/MOF/BOF gap analysis', 'deciding what to test or create next', 'producing novice-friendly recommendations') plus named system mechanics, with only minor coverage gaps versus fully enumerated concrete verbs.	4 / 5
Completeness	Explicitly answers 'what' ('Diagnose Meta Ads campaign performance and account gaps using Meta's actual system mechanics') and 'when' with a concrete 'Use for...' clause enumerating trigger scenarios.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('Meta Ads', 'campaign performance', 'account audits', 'full-funnel', 'TOF/MOF/BOF', 'what to test or create next'), though common user phrases like 'CPA', 'ROAS', or 'pause this ad' are absent.	4 / 5
Distinctiveness Conflict Risk	The Meta-specific mechanics (Breakdown Effect, Learning Phase, Auction Overlap, Pacing, Creative Fatigue) carve a clear niche, but there is minor overlap risk with sibling skills like ad-campaign-analyzer and meta-ads-campaign-builder.	4 / 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/meta-ads-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.