ads-meta
Meta Ads deep analysis covering Facebook and Instagram advertising. Evaluates 50 checks across Pixel/CAPI health, creative diversity and fatigue, account structure, and audience targeting. Includes Advantage+ assessment. Use when user says Meta Ads, Facebook Ads, Instagram Ads, Advantage+, or Meta campaign.
88
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly defines its scope (Meta advertising platform analysis), lists specific capabilities (50 checks across multiple domains), and provides explicit trigger terms. It follows the recommended pattern of 'what it does' followed by 'Use when...' with natural user language, and uses third person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: evaluates 50 checks across Pixel/CAPI health, creative diversity and fatigue, account structure, audience targeting, and Advantage+ assessment. These are concrete, domain-specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (deep analysis covering 50 checks across Pixel/CAPI health, creative diversity, account structure, audience targeting) and 'when' (explicit 'Use when user says Meta Ads, Facebook Ads, Instagram Ads, Advantage+, or Meta campaign'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Meta Ads', 'Facebook Ads', 'Instagram Ads', 'Advantage+', 'Meta campaign'. These cover the major variations of how users refer to this advertising platform. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in Meta/Facebook/Instagram advertising analysis. The specific triggers (Meta Ads, Advantage+, Pixel/CAPI) are unlikely to conflict with other skills like general marketing or Google Ads skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, domain-specific skill with excellent actionability — concrete thresholds, specific metrics, and a clear output template make it highly executable. Progressive disclosure is well-handled with appropriate references to supporting files. The main weaknesses are minor verbosity (Andromeda context, Threads stats) and a workflow that lacks explicit validation checkpoints for what is a complex multi-step audit process.
Suggestions
Add a validation checkpoint after step 1 (data collection) specifying minimum required data to proceed — e.g., 'If no Events Manager data available, mark all Pixel/CAPI checks as UNABLE_TO_VERIFY and note in report.'
Trim the Andromeda section to just the actionable insight (Similarity Score >60% gets suppressed, prioritize distinct concepts) and remove the background explanation about the AI engine.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and domain-specific, but includes some unnecessary explanations (e.g., explaining what Andromeda is, the Threads placement section with MAU stats, and some context Claude would already know like 'iOS 14.5 data loss'). The EMQ parameter descriptions and some inline rationale could be trimmed. | 2 / 3 |
Actionability | Highly actionable with specific thresholds (EMQ ≥8.0, CTR ≥1.0%, dedup ≥90%), concrete pass/warning/fail criteria for each check, exact character limits for ad copy, specific budget formulas (≥5x CPA), and a clear output format with visual score template. The 50-check audit is well-defined with measurable criteria. | 3 / 3 |
Workflow Clarity | The 7-step process is listed clearly, but lacks validation checkpoints or feedback loops. There's no guidance on what to do if data is incomplete, no verification step after score calculation, and no error recovery path. For a complex 50-check audit with scoring, explicit validation between data collection and analysis would strengthen the workflow. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with clear references to external files (meta-audit.md for full 50 checks, benchmarks.md, scoring-system.md, compliance.md) — all one level deep and well-signaled. The SKILL.md serves as a comprehensive overview while delegating detailed reference material appropriately. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- AgriciDaniel/claude-ads
- Commit
402ba63
- Reviewed
Table of Contents
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.