All Skills
Discover and install security-vetted AI agent skills for Claude Code, Cursor, GitHub Copilot, OpenClaw and more. Hebrew-ready, trusted, and open source.
2 skills found
Complete post-production package for Hebrew podcasts: RTL show notes with Spotify and Apple chapter markers, identification of 3-5 shareable 30-90 second clips, FFmpeg commands for extraction and Hebrew subtitle burn-in, and platform-tuned captions for Instagram Reels, TikTok, X, and LinkedIn. Use when shipping a Hebrew podcast episode from a Whisper transcript or SRT file and you need show notes, chapters, clips, and social captions in one coherent output without stitching together 4-5 separate tools and without tripping over RTL, nikud, and Hebrew subtitle burn-in bugs that generic tools (Kapwing, Maestra, Descript, Podsqueeze) mishandle. Do NOT use for standalone audio transcription (use video-subtitles), podcast RSS feed generation, audio mixing and mastering, or English-only podcasts.
Hebrew override layer on top of browser-use/video-use. Two paths: (1) captions-only.sh, one command that takes a long video, transcribes via Scribe, and burns Hebrew captions on the original. Costs $1-3 regardless of video length, the cheap path for non-technical users with a webinar or lecture. (2) The full video-use cut workflow for editing raw footage into curated teasers, ~$25-300 depending on length. Also covers SUB_FORCE_STYLE override (Helvetica has no Hebrew glyphs), python-bidi pre-shape recipe (libass+SRT BiDi is silently broken on macOS), Scribe garbage-character sanitization (Devanagari and other non-Hebrew chars Scribe mixes into Hebrew transcripts), Hebrew filler-word lexicon, explicit fontsdir= for reliable font discovery, and frame-sampling self-eval protocol. Use for any Hebrew video that needs captions or editing with video-use. Do NOT use for non-Hebrew video-use sessions, Hebrew podcast audio-only post-production (use hebrew-podcast-postproduction), or generic FFmpeg work without video-use.