video-edit · 0xsero — Claude Code skill: editing and installation
The video-edit Claude Code skill turns a screen, OBS, or talk recording into a publishable video. It trims pauses, masks on-screen leaks, improves audio, and prepares upload materials.
MIT ★ 92 updated 2026-11-04
npx skills add 0xSero/video-edit --skill video-edit -a claude-codeWhat video-edit does
video-edit cuts a screen capture, OBS session, or talk recording into a finished video. It uses the transcript and frames to remove dead air and static stretches, drop private webcam moments, and conceal sensitive text on screen. It then processes the audio, checks the rendered file, and prepares subtitles, chapters, and metadata.
The workflow also produces a thumbnail through youtube-pack and places the video and related files in ~/Downloads. Its toolchain requires ffmpeg 6+, python3, mlx_whisper, DeepFilterNet3, Pillow, numpy, soundfile, and Apple Vision via pyobjc-framework-Vision and pyobjc-framework-Quartz.
What it helps with
- trim pauses and visually static stretches from a recording
- remove private webcam moments
- mask sensitive text visible on screen
- prepare subtitles and chapters for the edited timeline
Example prompts for the agent
- Edit the latest screen recording in
~/Desktopinto a video for YouTube. - Cut pauses and private moments from my OBS recording.
- Scan this recording for leaks and prepare subtitles.
How to install video-edit
1Skills CLI (Vercel)
npx skills add 0xSero/video-edit --skill video-edit -a claude-code2Manually: put the files in place
~/.claude/skills/0xsero-video-edit/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/0xsero-video-edit/
1Skills CLI (Vercel)
npx skills add 0xSero/video-edit --skill video-edit -a codex2Manually: put the files in place
.agents/skills/0xsero-video-edit/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add 0xSero/video-edit --skill video-edit -a cursor2Manually: put the files in place
.cursor/skills/0xsero-video-edit/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install 0xSero/video-edit 0xsero-video-edit2Manually: put the files in place
.github/skills/0xsero-video-edit/SKILL.md1Skills CLI (Vercel)
npx skills add 0xSero/video-edit --skill video-edit -a gemini-cli2Platform CLI
gemini skills install https://github.com/0xSero/video-editManually: put the files in place
.devin/skills/0xsero-video-edit/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about video-edit
How do I install video-edit in Claude Code?
Run npx skills add 0xSero/video-edit --skill video-edit -a claude-code. The skill file is at ~/.claude/skills/0xsero-video-edit/SKILL.md.
What does video-edit do?
It edits screen, OBS, and talk recordings by trimming pauses and static sections, removing private moments, and masking visible leaks. It also processes audio and prepares subtitles, chapters, and upload metadata.
What does video-edit need to run?
It needs ffmpeg 6+, python3, mlx_whisper, DeepFilterNet3, Pillow, numpy, soundfile, and Apple Vision through pyobjc-framework-Vision and pyobjc-framework-Quartz.
Source text
SKILL.md · MIT
---
name: video-edit
description: Clean up a raw screen/OBS/talk recording into a tight professional upload - transcript-driven cuts, dead-air and visual-static removal, off-limits personal moments, on-screen leak redaction, audio enhancement, strong opening, verified render, then chapters/title/tags/description/subtitles/thumbnail, delivered to ~/Downloads and opened. Use when the user says "edit the video I recorded", "cut the silence out", "remove embarrassing parts", "make sure nothing leaks", "make it YouTube ready". Not for building promo/motion-graphics videos from slides; thumbnails alone go to youtube-pack.
---
# Video edit (screen / OBS / talk recording)
Script kit: `scripts/` in this skill (`prep.sh`, `transcript_txt.py`, `ocr_scan.py`,
`cam_flags.py`, `df_enhance.py`, `build_edl.py`, `render.py`, `verify_output.py`,
`chapters.py`, `overview.py`, `job.example.json`, `selftest.sh`). Run them from a copy in
`<workdir>/scripts/` so a job never depends on the skill dir. `scripts/selftest.sh` proves
an install end to end in a couple of minutes.
## Inputs
- `<src>`: the recording, usually newest `~/Desktop/*.mov` (OBS naming `YYYY-MM-DD HH-MM-SS.mov`). If several recent recordings exist, confirm which one BEFORE starting the long pipeline - editing the wrong video wastes an hour.
- `<target_minutes>`: ask if not given; typical 20-30 from a 45-90 min source.
- `<workdir>`: fresh scratch dir, e.g. `/tmp/<session>/edit`.
- Toolchain: `ffmpeg` 6+, `python3`, `mlx_whisper`, DeepFilterNet3, Pillow/numpy/soundfile, Apple Vision (`pyobjc-framework-Vision`/`-Quartz`).
## Steps
1. **Recon, never touch the source.** `ffprobe <src>` (resolution, fps, audio). Work only from copies/extracts in `<workdir>`.
2. **Prep.** `prep.sh "<src>" $W`: `orig48.wav`, `mono16.wav`, `frames/` (1 per 2 s), `camall/` (webcam crop at 1 fps, geometry auto-derived from the resolution), `sheet_overview.jpg`, `silences_raw.txt` (diagnostic only), and `transcript.json` (mlx_whisper large-v3-turbo, word timestamps, ~4 min). Whisper keeps running in the background after prep returns - start `df_enhance.py orig48.wav df_enhanced.wav` (DeepFilterNet3, ~6 min CPU) NOW, it is independent.
3. **Read the whole transcript** (3 chunks via `transcript_txt.py ... --from/--to`). Write keep ranges (source seconds) into `job.json -> keep`. Silence trimming is minor (~2 of 47 min); the real minutes come from content decisions. Whisper self-informs: a phrase repeated 10+ times or empty-segment runs = dead air, cut it.
4. **Visual-static pass.** "Nothing happening" is often visually static, NOT silent. Frame-difference the 0.5 fps frames: <1% pixels changed over a ~10 s window = inactive; merge runs split by <=1 s blips; require >=4 s to cut; 0.5 s handles. Blinking cursors/spinners fake activity - mask or raise the threshold; check intermediate frames for change-and-revert bursts. Typing is noise, not silence: gates use RMS on the *enhanced* track (`pause.loud_db`), never raw `silencedetect`.
5. **Opening.** Cut everything before the first real content. If the start is slow/boring, start on the most interesting demo; optionally cold-open with 1-2 exciting clips then a speed-up of the intro. Never open on wallpaper/black - a choppy first 30 s reads as trash.
6. **Leak scan (runs while you read).** `ocr_scan.py scan` after `run` on `frames/`: IPv4/v6, `*.ts.net`, emails, API keys, ssh material. Dense 2 fps pass on every terminal/config-heavy range (`ocr_scan.py dense src.mov dense 600:60 ...`). Static text -> `boxes` (solid fill); **scrolling terminal output -> blur the whole pane** (`blur` window + `blur_regions`, in source pixels) for the window - per-line boxes miss text between samples. `127.0.0.1`/`localhost` are fine. Log every window in `job.json`.
7. **Privacy cuts (webcam).** `cam_flags.py` (hand-near-mouth via Vision) + `cam_flags.py --sheet S:DUR` zoomed 2 fps sheets of each flagged cluster. Cut the moments the user would not publish: hand at the face during a pause, leaving the desk, another person in frame, full-screen face segments. Ordinary thinking poses and small gestures are fine. NEVER cut mid-sentence for a gesture - snap to the nearest sentence boundary and note what was lost.
8. **User timestamp cuts are literal.** "cut 0000 - 01:12" -> put it in `job.cuts` (or `keep`), apply exactly, then re-check pacing around the seam.
9. **Audio master.** Sanity: enhanced-vs-original correlation > 0.95 (`df_enhance.py` prints it). The default `audio_chain` is highpass 75, cuts/boosts around 220 Hz / 3.2 kHz / 9 kHz, de-esser, 3:1 compressor; notch any persistent fan tone by adding an `equalizer` term; `render.py` does the two-pass loudnorm to -16 LUFS / -1.5 dBTP. The untouched mic stays as audio track 2.
10. **EDL + render.** `build_edl.py` -> `segments.json` (pauses >0.7 s inside keeps shortened to 0.4 s; snapped to the probed frame rate; <0.3 s dropped). `render.py`: grouped parallel `h264_videotoolbox` encodes, concat `-c copy`, mux both tracks. It is restartable per group - if a group fails, fix and rerun, unchanged groups are skipped. Deliver 1080p unless asked otherwise (4K doubles render time for nothing).
11. **Verify before delivering.** `verify_output.py` exits non-zero unless frame count matches the EDL, both audio tracks match the video duration, and OCR of the *output* at 4 fps across every redaction window finds zero leaks. Also pull output frames at each privacy cut and at 0:00-1:00 and LOOK at them. Use `--full` for a whole-file leak sweep when the material is sensitive.
12. **Re-transcribe the new cut.** Transcript, subtitles and chapters must match the OUTPUT timeline, not the source - re-whisper the cut (or `chapters.py`, which remaps through the EDL) before writing SRT/chapters. Never ship SRT times taken from the source transcript.
13. **Metadata + deliver.** Without being asked twice: chapter timestamps (`chapters.py`, >=3, first at 0:00), 2-3 title options, ~30 tags under 500 chars (+2 tag/description variants if asked), description, SRT per language (~42 chars/line; multilingual on request), all as plain text. Thumbnail via youtube-pack: read the user's last 10 thumbnails for style; default white/creme background + black text, no face unless asked, logos/text big and uncluttered. Then move `<output>.mp4` (and SRTs/metadata) to `~/Downloads` and `open` the file / open the folder in default app.
## Outputs
- `<Topic> - YYYY-MM-DD - edit.mp4` (1080p, 2 audio tracks) in `~/Downloads`, opened in the default app.
- `<workdir>`: `job.json`, `segments.json`, `group_bounds.json`, `vf_<n>.txt`, redaction/privacy logs.
- `~/Downloads`: SRTs, `metadata.txt` (titles, description, tags, chapters).
- Optional on request: topical sub-videos split from the same source, each with its own chapters.
## Composes with
`whisper/DFN3 (in-kit) -> video-edit (verified mp4 in ~/Downloads) -> youtube-pack (thumbnail.png) -> browser upload to YouTube Studio configured like the user's other videos`.
## Rules
- Never modify the source recording.
- Target length is a target; if content won't shrink without gutting the talk, deliver slightly over and name the next two cuts.
- Cut whole tangents before trimming more pauses; keep hardware talk, live demos, honest caveats, the recap.
- Always end with: move to ~/Downloads + open.
- Report faithfully: you cannot hear the result - say so and point at track 2.
- Separately recorded audio (Discord/Craig) usually does not exist; check Desktop/Downloads/iCloud/Voice Memos, if absent use the OBS mic and say so.
- When asked to free space: delete old unaccepted drafts/variants, keep the source and the final.
- Multi-person podcasts: find the RIGHT audio tracks (usually 2 of many), map audio to the correct speaker, alternate video with the person talking, clean transitions.
- Never claim the edit is done because the render finished; only `verify_output.py` + eyeballed frames settle it.
## Verify
- `verify_output.py` prints PASS (frame count, two audio tracks, no leaks in windows) and exits 0.
- Eyeballed frames at 0:00-1:00 and every privacy cut (`verify_output.py --sheet 0:60`).
- SRT re-transcription spot-check against the cut.
- `ffprobe` the delivered file: duration, resolution, fps, 2 audio streams.
## Known failures
- Wrong video edited -> confirm newest/topic match before the pipeline.
- Subtitles/chapters on the source timeline -> re-transcribe after cutting (step 12).
- Hostname visible in output -> scrolling text between OCR samples; blur whole pane, widen the window, then output-side OCR.
- Silencedetect cuts typing/video playback -> gate on enhanced-audio RMS (`pause.loud_db`), not silence alone.
- Choppy black opening -> verify output 0:00-1:00 frames, cold-open on real content.
- `cp -i` overwrite prompt / sandbox TCC blocks `~/Downloads` -> use `/bin/cp` with sandbox disabled.
- ffmpeg filter dies ("Cannot allocate memory") past ~100 `between()` terms -> fewer `render_groups`.
- Blinking cursor counts as activity in frame differencing -> mask/tune threshold, check intermediate frames.
- `render.py` frame mismatch -> it refuses to concat; read `render_<n>.log` (`-ss` before a non-keyframe, broken decoder).
- Whisper still running when you read `transcript.json` -> `transcript_txt.py` reports empty segments; wait for `whisper.log` to finish.
## Examples
- 2026-09-02 talk, 47 min -> 26 min: 32 keep ranges, 2 privacy cuts (9:52-9:58, 26:08-26:14), 2 blur windows + 1 box for a `*.ts.net` hostname, render ~2 h wall clock, leak caught only by output-side OCR.
- 2026-09-24 teaching OBS session: user rejected first cut ("background noise, typing, beginning highly boring") -> removed typing noise, picked a better opening, re-did transcripts, then literal head cut `0:00-1:12`, leak scan, white/creme thumbnail with bigger logos, 2 metadata variants, moved to Downloads.
- Podcast (2026-09-18): 1h40m video + 5 candidate audio files -> identified the 2 right per-speaker tracks, mapped voice to video, 1080p, trim head, SRT + ES/AR/HI translations, chapter timestamps, thumbnail with both speakers, text on top, no black background.
© 0xSero · MIT · 0xSero/video-edit
Similar skills
All skills for Marketing and content →video-edit by other authors comes first.