by smixs · Claude Skill · ★ 66
🎨 Visual Skills for Agents — Image & Video Prompting 🇷🇺 Читать на русском Two professional Claude Skills for AI visual content production. They write production-grade prompts for the leading image and video models — picking the right model for the task, applying its specific syntax, and returning a copy-paste-ready prompt. This is what a creative director, copywriter, or AI-content team uses instead of "be cinematic, 4k, masterpiece" filler. ✨ Supported Models 🖼️ Image generation models Brand assets, dense text, UI mockups, edits with hard preservation, up to
| Stars | 66 |
| Forks | 11 |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 63.1500066420096/100 |
| Last Updated | 2026-07-01 |
| Created | 2026-04-26 |
| Platforms | claude-code, cli, gemini |
| Est. Tokens | ~18k |
These tools work well together with visual-skills for enhanced workflows:
Explore other popular claude skill tools:
visual-skills is Professional Claude Skills for AI image and video prompting. Supports Nano Banana (Gemini 3 Pro/Flash), GPT Image 2, Seedance 2.0, Kling 3.0 (multi-shot + native dialogue), Veo. Works with Claude Code. It is categorized as a Claude Skill with 66 GitHub stars.
You can find installation instructions and usage details in the visual-skills GitHub repository at github.com/smixs/visual-skills. The project has 66 stars and 11 forks, indicating an active community.
visual-skills is released under the MIT license, making it free to use and modify according to the license terms.