multimodal
Interleaving image, audio, and text modalities in prompts.
SKILL.mdskills/ai-ml/multimodal/SKILL.md
GitHubMultimodal
Interleaving image, audio, and text modalities in prompts.
Core Guidelines
- Alignment: Anchor visual/audio inputs to textual markers in prompt templates.
- Formatting: Format multimodal requests according to API client limits.
- Token Budgets: Calculate image/audio tokens correctly.