ads-creative
Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative fatigue, evaluates platform-native compliance, and provides production priorities. Use when user says "creative audit", "ad creative", "creative fatigue", "ad copy", "ad design", or "creative review".
Install with Tessl CLI
npx tessl i github:AgriciDaniel/claude-ads --skill ads-creative87
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/skillValidation 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 a well-crafted skill description that excels across all dimensions. It provides specific capabilities (audit types, fatigue detection, compliance evaluation), includes natural trigger terms that marketing professionals would use, and has an explicit 'Use when' clause with clear activation phrases. The advertising/creative domain focus makes it highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'cross-platform creative quality audit', 'covering ad copy, video, image, and format diversity', 'detects creative fatigue', 'evaluates platform-native compliance', and 'provides production priorities'. | 3 / 3 |
Completeness | Clearly answers both what (audit covering ad copy, video, image, format diversity; detects fatigue; evaluates compliance; provides priorities) AND when with explicit 'Use when user says...' clause listing specific trigger phrases. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'creative audit', 'ad creative', 'creative fatigue', 'ad copy', 'ad design', 'creative review'. These are terms marketing professionals would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on advertising creative audits with distinct triggers like 'creative fatigue' and 'platform-native compliance'. Unlikely to conflict with general document or image processing skills due to specific advertising/marketing domain focus. | 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 creative audit skill with highly actionable, specific criteria and excellent progressive disclosure through external references. The main weaknesses are some verbosity in platform-specific details that could be externalized, and a workflow that lacks explicit validation checkpoints between assessment steps.
Suggestions
Add validation checkpoints to the workflow, e.g., 'Verify all platform data collected before proceeding to evaluation' and 'Confirm scoring calculations before generating report'
Move detailed platform specifications (format diversity matrix, per-platform assessment details) to the referenced platform-specs.md file to reduce token usage in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient with tables and structured lists, but includes some redundant information (e.g., explaining what formats exist on each platform when Claude likely knows this). The format diversity matrix and some platform specs could be more condensed or referenced externally. | 2 / 3 |
Actionability | Highly actionable with specific thresholds (CTR >20% decline, frequency >5.0), concrete requirements (≥8 headlines, ≥6 creatives), exact dimensions (1080x1920, safe zone coordinates), and clear pass/fail criteria. The checklists are copy-paste ready for evaluation. | 3 / 3 |
Workflow Clarity | The 7-step process is listed but lacks validation checkpoints between steps. There's no explicit feedback loop for when creative fails assessment criteria, and no verification step before generating the final report. For an audit workflow, validation gates would strengthen reliability. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear references to external files (platform-specs.md, benchmarks.md, scoring-system.md) at one level deep. Content is well-organized with logical sections, tables for quick reference, and clear output deliverables. The skill appropriately serves as an overview pointing to detailed materials. | 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.