Media — Development skill for Claude Code
Understand an audio / video / image file — Antigravity (agy/Gemini) transcribes and analyzes it, returning a timestamped digest while the full transcript goes to a file.
How to install Media
Installs to ~/.claude/skills/yuting0624-antigravity-for-claude-code-media/SKILL.md
mkdir -p ~/.claude/skills/yuting0624-antigravity-for-claude-code-media && curl -fsSL https://raw.githubusercontent.com/yuting0624/antigravity-for-claude-code/HEAD/commands/media.md -o ~/.claude/skills/yuting0624-antigravity-for-claude-code-media/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Media does
description: Understand an audio / video / image file — Antigravity (agy/Gemini) transcribes and analyzes it, returning a timestamped digest while the full transcript goes to a file. argument-hint: " [what to focus on] [--convert] [--tier pro|flash] [--timeout 20m]"
Claude Code can't hear audio or watch video, and doing it locally means an ffmpeg + speech-model stack. Gemini is natively multimodal — so **delegate the perception** to agy and keep the judgment here.
Input: $ARGUMEN
Alternatives in Development
- Tentacle Planner — You are the Tentacle Planner — a meta-agent that analyzes this codebase and creates department tentacles to or 1.4k ★
- Morning Debrief Analyzer — This prompt transcribes morning debrief audio recordings using OpenAI Whisper and analyzes the transcript to e 201 ★
- Claude Architect Exam Guide — The CCAR-F, CCAR-P prep guide built for non-technical learners and engineers alike 174 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Transcript Critic
Claude Code skill that transcribes audio/video with whisper.cpp to get structured critical analysis including
Videodb Skills
See, understand, and act on video & audio — ingest, search, edit, generate, and stream media via VideoDB.
Lecture Transcriber
Transcribe lecture videos/audio to timestamped transcripts, locally and free.
Gen Gallery
Build a self-contained HTML gallery of all generated media (image/audio/video)
Open It
Open the most recently created file in the best app for it (HTML/PDF → Chrome, video/audio → Media Player Clas
Mindmap From Transcript
You are reading a rich transcript of a video. The transcript was produced from the original audio and on-scree
Related Agents
Agy
Delegate complex execution, deep reasoning, architectural planning, adversarial code review, session documenta
Antigravity Agent
Runs Google Antigravity on the user's Antigravity subscription, reached through the agy CLI. One mode - consul
Agy Rescue
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper roo