High-quality YouTube video summarization using the local summarize CLI with yt-dlp + whisper.cpp transcription and Claude CLI by default. Use when asked to summarize a YouTube video, extract a transcript from audio (not captions), or run a repeatable best-quality video summary workflow.
Produce best-quality summaries from YouTube videos by transcribing audio with yt-dlp + whisper.cpp and summarizing with Claude CLI. This avoids caption-track errors and keeps the workflow reproducible.
Do not use this skill for tweet-style markdownified YouTube transcripts from caption tracks. Use the summarize skill and run summarize --extract --format md --markdown-mode llm ... for that path.
scripts/summarize_youtube.sh "<youtube-url>"scripts/summarize_youtube.sh "<url>" > /tmp/summary.md~/.cache/whisper.cpp/ggml-medium.en.binnix shell nixpkgs#whisper-cpp --command whisper-cpp-download-ggml-model medium.en --output-dir ~/.cache/whisper.cppscripts/summarize_youtube.sh to transcribe via yt-dlp + whisper.cpp and summarize with Claude.--cli <provider>: claude (default), codex, gemini--length <preset>: short|medium|long|xl|xxl (default: xxl)--model <id>: whisper.cpp model id (default: medium.en)--timeout <duration> and --retries <count>: pass through to summarize--extract: transcript only (no LLM summary)scripts/summarize_youtube.sh is the canonical entry point. Prefer it over hand-crafted commands so the workflow stays consistent.
Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Start voice calls via the OpenClaw voice-call plugin.
Notion API for creating and managing pages, databases, and blocks.
Gemini CLI for one-shot Q&A, summaries, and generation.
Category:developer