farhanic017/vision-tool
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.
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.
End-to-end HyperFrames video production skill for Claude Code. Local TTS, scene calibration, captions, and MP4 render pipeline.
🎬 Extract YouTube transcripts (single video or playlist) via a Playwright-driven CLI and AI-agent skill that drives YouTube's "Show transcript" panel.
Turn YouTube/Bilibili lectures into smart-cropped LaTeX/PDF notes. Claude Code & Codex skill.
Generate Makoto Shinkai style manga sequences and video prompts for AI tools with this Claude Skill. Use professional character tracking and cinematic layouts.
Universal behavioral principles for AI agents: Karpathy's guidelines adapted for Hermes (SOUL.md) and OpenAI Codex (skill). Generalized four-principle framework — Think Before Acting, Simplicity First, Surgical Changes, Goal-Driven Execution.
🧩 通用 Claude Code Skills 集合 · 即插即用 · 包含 clawd-animation、self-improving-agent、wechat-article-publisher 等