- Home
- Skills
- Image & Video
- movie recap
Works with the AI Agents you already use
movie recap
Automate movie recap production with synced narration, dual-platform exports, and full metadata packages.
Free
movie recap
Example session with this skill installed
/movie-recap "The Great Escape" 2024 episode 1 --full-only
- Read your context and instructions
- Compiled the movie recap
- Generated the image
I have analyzed the source footage for "The Great Escape" (2024) Episode 1. I generated a 12-minute narration script, synthesized the audio at 1.10x, and rendered the full recap package with noncontinuous clips and hard-zoom styling.
Full Recap Package: The Great Escape (2024) E01
| File Name | Type | Size | Notes |
|---|---|---|---|
Great-Escape-E01-Full-Recap/Great-Escape-E01-recap-with-narration.mp4 | Video | 482 MB | 1080p, 12:14 duration, 1.10x zoom |
Great-Escape-E01-Full-Recap/Great-Escape-E01-narration-TTS.srt | Subtitles | 18 KB | Precise alignment for voice |
Great-Escape-E01-Full-Recap/Great-Escape-E01-captions-display.srt | Subtitles | 12 KB | Compact display-friendly captions |
Great-Escape-E01-Full-Recap/youtube-upload.txt | Metadata | 4 KB | Includes chapters and SEO tags |
Great-Escape-E01-Full-Recap/thumbnails/thumbnail-01.png | Image | 1.8 MB | High-action frame at 04:22 |
Next steps
- Review the
Great-Escape-E01-recap-with-narration.mp4for sync accuracy. - Check the
youtube-upload.txtfor the optional "Undertow" music credit block. - Use the provided thumbnails in the YouTube Studio dashboard.
thumbnail-01.png
PNG · 1536×1024
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Movie recap production is a high-friction workflow involving heavy video processing, precise audio alignment, and strict editorial rules. Managing multiple assets for different platforms while maintaining narrative flow and copyright-avoidance styling usually requires hours of manual editing.
This skill automates the end-to-end creation of movie recaps and social media reels from local video files. It handles source analysis, narration scripting, text-to-speech synthesis, and multi-format video rendering. By enforcing strict duration limits, specific clip pacing, and platform-optimized export settings, it delivers ready-to-upload packages without the manual overhead.
What it does
- Automated Media Probing analyzes source footage, subtitles, and metadata to map out story arcs and key actions.
- Narrated Scripting generates English narration with accurate cause-and-effect, avoiding AI fluff and spoilers.
- Dual-Mode Rendering produces 10-minute+ YouTube recaps and 45-75 second Instagram Reels simultaneously.
- Precision Alignment synchronizes spoken phrases to visual actions with frame-accurate timing.
- Package Generation exports MP4s, TTS-aligned SRTs, display captions, thumbnails, and platform-specific upload copy.
How it works
- Source Discovery scans the project folder for video files and probes them for duration, dimensions, and language.
- Script & Speech generates narration, synthesizes audio using local Kokoro models, and aligns word-level timestamps via Whisper.
- Timeline Assembly builds an edit manifest mapping narration anchors to noncontinuous source clips.
- Final Export renders the full recap and Reel versions with appropriate crops, zooms, and audio mixes.
Frameworks & tools
The skill requires a local environment with Python, FFmpeg, and PyAV. It utilizes Kokoro for high-quality local TTS and faster-whisper for ASR and audio alignment.
Why this beats prompting it yourself
Prompting an agent to "make a video" usually results in a script or a plan, not a file. This skill executes the actual rendering code, manages complex subtitle alignment logic, and enforces specific duration floors and ceilings that generic prompts consistently ignore.
Use cases
- YouTube Content Creation for building structured, spoiler-heavy movie recaps over 10 minutes.
- Social Media Marketing to generate high-engagement Reels that hook viewers before the climax.
- Asset Management for creating searchable, captioned archives of local film libraries.
Known limitations
Requires a pre-configured local runtime with specific models and FFmpeg binaries. Does not support automatic film downloading or watermarking without external assets.
Requires local execution and a supplied movie file. Setup downloads dependencies and models; Python and the coding agent must already be installed. Tested on Windows x64/Python 3.13; macOS/Linux remain untested. CPU rendering can be slow. Narration is English, and recognition or scene-alignment errors may require correction. Reels retain the source aspect ratio and require manual vertical reframing if desired. Review outputs before publishing.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 7 days ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts
Reads the user-selected film and subtitles; writes recap outputs and temporary editing files beside the source. Setup writes a shared runtime under ~/.movie-recap and installs skill files under ~/.claude/skills and/or ~/.agents/skills. Network access downloads dependencies and models. The installer does not upload movie files.