Mega Shot

Makes finished narrated videos from an idea, driven by one video.yaml: researched, fact-checked script; narration in a cloned or built-in voice (local VoiceStudio TTS, voice cloning from any audio/video file); visuals in a style chosen with the user (stock footage and archival images, 2.5D parallax, whiteboard, flat 2D, kinetic type, 35 painterly styles, Three.js or Blender 3D, AI images, news graphics, satellite imagery, code-drawn story characters); music mix at -14 LUFS; high-quality export plus phone preview; automatic quality checks; English subtitles (SRT); YouTube thumbnails; publishing

9 starsImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add stevenguyenbt/mega-shot --skill mega-shot

Manual install

git clone --depth 1 https://github.com/stevenguyenbt/mega-shot.git /tmp/mega-shot
mkdir -p ~/.claude/skills
cp -r /tmp/mega-shot/. ~/.claude/skills/mega-shot

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# mega-shot · Video studio

One video = a folder `videos/<name>/` with `video.yaml` (script + settings) and `film.html` (how each scene is drawn).
The framework handles narration, timing, subtitles, transitions, post-processing, mixing, export and QA. Output: a
high-quality upload file, a < 29 MB phone preview, subtitles and a publishing package in `videos/<name>/out/`.

## Running the CLI

- The CLI is `xp` (bash/zsh) or `xp.cmd` (Windows) **inside this skill's folder**. Run it by path **from the user's
  project folder**, never from inside the skill folder: `<skill-folder>/xp setup` or `<skill-folder>\xp.cmd setup`.
  Below it is written as just `xp`.
- Project data lives in `<project>/.mega-shot/`, videos in `<project>/videos/`. Requires `uv` and `ffmpeg`.
- Commands and YAML keys have English names; the old Vietnamese names still work (the engine was built in Vietnamese,
  so some file names like `nghien_cuu.md` research notes and `giay_phep.json` licence book stay Vietnamese). Inside
  `film.html`, `c.data.<key>` uses the internal Vietnamese names. Details: [references/workflow-details.md](references/workflow-details.md),
  [references/glossary.md](references/glossary.md).
- Works in any agent that reads Agent Skills (Claude Code, Codex, Antigravity, Gemini CLI, Cursor). `xp agents install`
  links this folder into their skills directories; `xp agents init` writes a short block into the project's AGENTS.md /

Read the full skill on GitHub

Details

Skill name: mega-shot
Repository: stevenguyenbt/mega-shot
License: MIT
Repo updated: 29 October 2026

FAQ

What does the Mega Shot skill do?

How do I install the Mega Shot skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add stevenguyenbt/mega-shot --skill mega-shot. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Mega Shot popular?

It lives in stevenguyenbt/mega-shot, which has 9 GitHub stars and 0 forks.

Related skills

awrshift/skill-telegram

The only Telegram skill your AI agent needs. Read messages, parse channels, download and transcribe voice notes — all via Telethon user API. One session file, zero bots. Use when user says 'read telegram', 'check saved messages', 'fetch from telegram', 'parse channel', 'transcribe voice', 'telegram search', 'check my telegram', or when any agent needs Telegram data. Also trigger on 'what did I save in telegram', 'read my saved messages', 'get messages from channel X', 'download voice notes'. Covers: ad-hoc reading, channel parsing with sanitization, voice/audio download. Requires TG_API_ID, TG

Images, Video & Audio

Jmcomic

NanNank0/JMComic_downloader

Use jmcomic (JMComic-Crawler-Python) to query JMComic metadata (album/photo details, search, rankings, comments) and to download albums or chapters, optionally exporting them to PDF, ZIP, or a long image. All commands return a single JSON object from one stable CLI entry point.

Images, Video & Audio

Video Vision

Moh4696/claude-video-vision

Watch and understand local video files. Extracts sampled frames with ffmpeg and generates a timestamped transcript with local Whisper, then answers the user's question grounded in both visual and audio evidence. Use this skill whenever the user references a video file (.mp4, .mov, .mkv, .webm, .avi, .m4v) and wants it watched, summarized, analyzed, described, searched, captioned, transcribed, clipped, or asks questions like "what happens in this video", "what is said at 1:30", "find the part where X", "summarize this recording / lecture / meeting / clip", even if they don't explicitly say "wat

Images, Video & Audio

Fb Ad Video Studio

ai-agents-for-agencies-coaches/fb-ad-video-studio

Produce high-converting Facebook/Instagram/TikTok ad VIDEOS — motion-graphics spots and talking-head founder ads — by authoring HyperFrames HTML compositions and rendering to MP4. Opinionated layer on top of the HyperFrames framework that bakes in a battle-tested ad structure, the audio pipeline (VO + SFX + silence-cutting), caption sync, and a reverse-template workflow. Use whenever the user asks for a video ad, motion-graphics ad, founder/UGC ad, kinetic-typography spot, animated ad, Reel/Short ad, or "make a video like this ad". For raw HyperFrames framework questions use the `hyperframes`

Images, Video & Audio

Watch Video

Ootto-AI/ootto-watch

Give Claude eyes and ears on any online video, then analyze it. Downloads a video from a URL (YouTube, Instagram, X, Vimeo, and 1000+ yt-dlp sites), extracts key frames, and gets a transcript (native captions, else local Whisper), then hands the frames + timestamped transcript to Claude so it can produce a full breakdown — hook, format, storytelling structure, pacing and visual layout — grounded in what's actually on screen AND said. Pass several URLs to batch-analyze dozens at once and surface the patterns the best ones share. Use whenever the user shares a video link (or many) and wants it w

Images, Video & Audio

Clippos

dylan-buck/Clippos

Local video clipping automation for /clippos requests, attached video files, video links, social clip generation, captioned shorts, crop/framing, and rendered 9:16, 1:1, or 16:9 exports. Use this skill whenever the user wants an agent to turn a video into high-potential clips, score clips with the current harness model, approve selected clips, and render final MP4 outputs.

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.