Agent Vision Toolkit — HTML and CSS reconstruction of the model-training infographic
Project screenshotsAbout this Skill
Equip text-only agents with image questions, OCR, target localization, cropping, SVG tracing, and screenshot comparison tools.
Why we picked it
Curated from the upstream task instructions. Use the original repository and its linked runtime files for installation, dependencies, and licensing.
Before you use it
- Requires Python 3.11+ and a configured vision API for model-based tools; optional tools need Pillow, NumPy, or a browser as documented.
Supported agents
Claude CodeCodex CLICursorGitHub CopilotDeepSeek HarnessGemini CLIGrok BuildHermes AgentOpenCodePiKiroRovo DevQoderMistral VibeGoogle Antigravity
Sources & references
Original sources are linked below. Practical starting points are editorial suggestions from SkillHey.
