Video Editing
Turn raw screen recordings and footage into polished tutorials, vlogs, and platform-ready short-form video without treating AI as a full video generator.
Overview
Video Editing is an agent skill most often used in Build (also Launch distribution and Grow content) that structures AI-assisted cutting, overlays, and export of real footage through FFmpeg, Remotion, and polish tools.
Install
npx skills add https://github.com/affaan-m/everything-claude-code --skill video-editingWhat is this skill?
- Five-layer pipeline: capture → agent structuring → FFmpeg → Remotion → ElevenLabs/fal.ai → Descript or CapCut
- Compresses long recordings into short-form cuts instead of prompt-only video generation
- Platform reframing for YouTube, TikTok, and Instagram from one master edit
- Overlays, subtitles, music, and voiceover augmentation on existing footage
- Explicit layer boundaries—each tool has one job; do not skip or merge layers
- Five-layer pipeline from raw capture through Descript or CapCut
Adoption & trust: 5.6k installs on skills.sh; 210k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have long raw screen recordings or vlogs but lack a repeatable agent-guided path to short-form, multi-platform video without treating AI as a full replacement editor.
Who is it for?
Indie builders turning Screen Studio or camera footage into tutorials, demos, and reframed short-form clips.
Skip if: Teams that want end-to-end AI video generation from a single text prompt with no source footage.
When should I use this skill?
User wants to edit video, cut footage, create vlogs, build video content, add overlays or subtitles, or reframe for YouTube, TikTok, or Instagram.
What do I get? / Deliverables
You get a layered edit workflow from capture through final export in Descript or CapCut, ready to publish on target social or tutorial channels.
- Structured edit plan
- Cut and composed intermediate renders
- Platform-specific exported video files
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build because the skill centers on producing tutorial and demo artifacts from capture through export. Docs subphase fits structured how-to and demo video output that ships alongside product documentation and onboarding.
Where it fits
Structure a Screen Studio capture into chaptered tutorial segments before shipping onboarding docs.
Export TikTok and Reels cuts from one long product demo for launch week.
Repurpose a weekly livestream into subtitled clips for content calendar filler.
Rough-cut a landing-page hero video from raw prototype walkthrough footage.
How it compares
Use as a procedural post-production stack, not as a one-shot generative video prompt skill.
Common Questions / FAQ
Who is video-editing for?
Solo and indie builders who record apps or talking-head content and want an agent to orchestrate FFmpeg, Remotion, and familiar polish apps instead of manual trial-and-error.
When should I use video-editing?
During Build when producing tutorial or demo docs, at Launch when packaging distribution clips, and during Grow when repurposing long captures into platform-specific short-form.
Is video-editing safe to install?
Review the Security Audits panel on this Prism page before installing; the workflow implies shell, network, and third-party media APIs you should trust.
SKILL.md
READMESKILL.md - Video Editing
# Video Editing AI-assisted editing for real footage. Not generation from prompts. Editing existing video fast. ## When to Activate - User wants to edit, cut, or structure video footage - Turning long recordings into short-form content - Building vlogs, tutorials, or demo videos from raw capture - Adding overlays, subtitles, music, or voiceover to existing video - Reframing video for different platforms (YouTube, TikTok, Instagram) - User says "edit video", "cut this footage", "make a vlog", or "video workflow" ## Core Thesis AI video editing is useful when you stop asking it to create the whole video and start using it to compress, structure, and augment real footage. The value is not generation. The value is compression. ## The Pipeline ``` Screen Studio / raw footage → Claude / Codex → FFmpeg → Remotion → ElevenLabs / fal.ai → Descript or CapCut ``` Each layer has a specific job. Do not skip layers. Do not try to make one tool do everything. ## Layer 1: Capture (Screen Studio / Raw Footage) Collect the source material: - **Screen Studio**: polished screen recordings for app demos, coding sessions, browser workflows - **Raw camera footage**: vlog footage, interviews, event recordings - **Desktop capture via VideoDB**: session recording with real-time context (see `videodb` skill) Output: raw files ready for organization. ## Layer 2: Organization (Claude / Codex) Use Claude Code or Codex to: - **Transcribe and label**: generate transcript, identify topics and themes - **Plan structure**: decide what stays, what gets cut, what order works - **Identify dead sections**: find pauses, tangents, repeated takes - **Generate edit decision list**: timestamps for cuts, segments to keep - **Scaffold FFmpeg and Remotion code**: generate the commands and compositions ``` Example prompt: "Here's the transcript of a 4-hour recording. Identify the 8 strongest segments for a 24-minute vlog. Give me FFmpeg cut commands for each segment." ``` This layer is about structure, not final creative taste. ## Layer 3: Deterministic Cuts (FFmpeg) FFmpeg handles the boring but critical work: splitting, trimming, concatenating, and preprocessing. ### Extract segment by timestamp ```bash ffmpeg -i raw.mp4 -ss 00:12:30 -to 00:15:45 -c copy segment_01.mp4 ``` ### Batch cut from edit decision list ```bash #!/bin/bash # cuts.txt: start,end,label while IFS=, read -r start end label; do ffmpeg -i raw.mp4 -ss "$start" -to "$end" -c copy "segments/${label}.mp4" done < cuts.txt ``` ### Concatenate segments ```bash # Create file list for f in segments/*.mp4; do echo "file '$f'"; done > concat.txt ffmpeg -f concat -safe 0 -i concat.txt -c copy assembled.mp4 ``` ### Create proxy for faster editing ```bash ffmpeg -i raw.mp4 -vf "scale=960:-2" -c:v libx264 -preset ultrafast -crf 28 proxy.mp4 ``` ### Extract audio for transcription ```bash ffmpeg -i raw.mp4 -vn -acodec pcm_s16le -ar 16000 audio.wav ``` ### Normalize audio levels ```bash ffmpeg -i segment.mp4 -af loudnorm=I=-16:TP=-1.5:LRA=11 -c:v copy normalized.mp4 ``` ## Layer 4: Programmable Composition (Remotion) Remotion turns editing problems into composable code. Use it for things that traditional editors make painful: ### When to use Remotion - Overlays: text, images, branding, lower thirds - Data visualizations: charts, stats, animated numbers - Motion graphics: transitions, explainer animations - Composable scenes: reusable templates across videos - Product demos: annotated screenshots, UI highlights ### Basic Remotion composition ```tsx import { AbsoluteFill, Sequence, Video, useCurrentFrame } from "remotion