ads-meta
Meta Ads deep analysis covering Facebook and Instagram advertising. Evaluates 46 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".
91
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 100%
↑ 1.33xAgent success when using this skill
Validation for skill structure
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 an excellent skill description that follows best practices. It provides specific, measurable capabilities (46 checks across named domains), uses third person voice correctly, and includes an explicit 'Use when' clause with natural trigger terms covering platform name variations. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Evaluates 46 checks across Pixel/CAPI health, creative diversity and fatigue, account structure, and audience targeting' plus 'Includes Advantage+ assessment'. These are concrete, measurable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (deep analysis covering 46 checks across multiple domains) AND when (explicit 'Use when user says...' clause with specific trigger phrases). The structure follows the ideal pattern. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Meta Ads', 'Facebook Ads', 'Instagram Ads', 'Advantage+', 'Meta campaign'. These are exactly the phrases users would naturally use when requesting this type of analysis. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: Meta/Facebook/Instagram advertising specifically. The technical terms (Pixel/CAPI, Advantage+) and platform-specific triggers make it unlikely to conflict with generic marketing or other ad platform 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 well-structured Meta Ads audit skill with excellent organization and appropriate progressive disclosure. The content is concise and assumes Claude's competence with advertising concepts. Main weaknesses are the lack of executable code/commands and missing validation checkpoints in the workflow for this complex 46-check audit process.
Suggestions
Add example commands or scripts for data collection step (e.g., how to export from Ads Manager, how to capture EMQ scores)
Include a validation checkpoint after step 5 (evaluate checks) to verify all 46 checks have been assessed before calculating the score
Provide a sample partial output showing how to format individual check results (PASS/WARNING/FAIL with evidence)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, presenting checklists, thresholds, and structured data without explaining basic concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides concrete checklists and specific thresholds, but lacks executable code examples. The process steps reference external files without showing actual commands or scripts to run. Guidance is specific but not copy-paste executable. | 2 / 3 |
Workflow Clarity | The 7-step process is clearly sequenced, but lacks explicit validation checkpoints or feedback loops. No guidance on what to do if data collection fails or if scores don't calculate correctly. For an audit involving 46 checks, error recovery steps would strengthen this. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear overview sections and well-signaled one-level-deep references to external files (meta-audit.md, benchmarks.md, scoring-system.md, compliance.md). Content is appropriately split between quick reference tables inline and detailed materials in referenced files. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.