vision-tool은(는) 무엇을 하나요?
Image & video analysis for AI coding assistants without native vision. Works with any model - CLI, MCP, or opencode skill. 12 vision backends (Gemini, GPT-4o, Claude, etc.). Zero hardcoded secrets.
Image & video analysis for AI coding assistants without native vision. Works with any model - CLI, MCP, or opencode skill. 12 vision backends (Gemini, GPT-4o, Claude, etc.). Zero hardcoded secrets.
vision-tool is a Claude Code agent skill that image & video analysis for AI coding assistants without native vision. Works with any model - CLI, MCP, or opencode skill. 12 vision backends (Gemini, GPT-4o, Claude, etc.). Zero hardcoded secrets.
npx skills add farhanic017/vision-toolImage & video analysis for AI coding assistants without native vision. Works with any model - CLI, MCP, or opencode skill. 12 vision backends (Gemini, GPT-4o, Claude, etc.). Zero hardcoded secrets.
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
Use when you have a spec or requirements for a multi-step task, before touching code