ModLens Vision Skill — Text-only DeepSeek reading a tweet screenshot in full detail via ModLens
Captures du projetÀ propos de ce Skill
Give text-only agents image understanding through a configurable vision CLI, covering image questions, screenshots, and chart interpretation.
Pourquoi ce choix
Curated from the upstream task instructions. Use the original repository and its linked runtime files for installation, dependencies, and licensing.
Avant de l’utiliser
- Install the ModLens runtime and configure a supported vision engine or local CLI; provider access and usage terms vary by engine.
Agents compatibles
Claude CodeCodex CLICursorGitHub CopilotDeepSeek HarnessGemini CLIGrok BuildHermes AgentOpenCodePiKiroRovo DevQoderMistral VibeGoogle Antigravity
Sources et références
Les sources originales sont liées ci-dessous. Les pistes pratiques sont des suggestions de la rédaction de SkillHey.
