Social Video Folder Autocutter

Plan repeatable hard-drive folder-to-video pipelines for speaker-led multicam content, including 9:16 Reels/Shorts up to 3 minutes at 1.1x talking speed and 16:9 long-form 3-7 minute cuts, with Resolve handoff, Editframe asset generation, audio/caption gates, and narrative beat planning.

35 stars 4 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ChaiWithJai/davinci-resolve-claude-skills --skill social-video-folder-autocutter
Manual install
git clone --depth 1 https://github.com/ChaiWithJai/davinci-resolve-claude-skills.git /tmp/davinci-resolve-claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/davinci-resolve-claude-skills/skills/social-video-folder-autocutter ~/.claude/skills/social-video-folder-autocutter

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

From the SKILL.md

# Social Video Folder Autocutter

Use this before editing when the user wants a repeatable pipeline from a folder of camera/audio files into social or long-form cuts.

## Output Profiles

- **Vertical social:** `1080x1920`, 9:16, up to 3 minutes, default 1.1x speed for speaker-led sections, Netflix-style captions, source layers preserved in Resolve.
- **Horizontal long-form:** `1920x1080`, 16:9, 3-7 minutes, default normal speed, lower thirds/captions optional, source layers preserved in Resolve.

## Required Pipeline

1. Scan the folder:
   - run the DaVinci skill `probe_media.py`;
   - run `audio_quality_audit.py`;
   - identify camera ISOs, HQ audio, intro/bumper, brand files, old renders, and existing Resolve exports.
2. Make a story plan:
   - hook/agenda,
   - body beats,
   - recap/CTA,
   - rejected or risky segments.
3. Build edit decisions:
   - source file, in/out, angle, reason, transition, crop, audio source, caption text.
   - reject word-boundary-only cuts.
4. Build a B-roll coverage plan:
   - assign B-roll only where it proves a claim, establishes the event world, covers a jump cut, compresses time, or gives the audience an emotional/visual release.
   - tag every B-roll candidate as `wide`, `medium`, `close-up`, `insert/detail`, `environment`, `screen/product`, or `human moment`.
   - prefer wide/medium/close-up sequences over isolated filler shots.
   - require source page/licensing metadata for stock footage and store it with the manifest.
Read the full skill on GitHub

Details

Skill name
social-video-folder-autocutter
Path
skills/social-video-folder-autocutter/SKILL.md
License
MIT
Repo updated
17 May 2026

FAQ

What does the Social Video Folder Autocutter skill do?

Plan repeatable hard-drive folder-to-video pipelines for speaker-led multicam content, including 9:16 Reels/Shorts up to 3 minutes at 1.1x talking speed and 16:9 long-form 3-7 minute cuts, with Resolve handoff, Editframe asset generation, audio/caption gates, and narrative beat planning.

How do I install the Social Video Folder Autocutter skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ChaiWithJai/davinci-resolve-claude-skills --skill social-video-folder-autocutter. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Social Video Folder Autocutter popular?

It lives in ChaiWithJai/davinci-resolve-claude-skills, which has 35 GitHub stars and 4 forks.

Related skills

Davinci Resolve Audio Cleanup Podcast

35

ChaiWithJai/davinci-resolve-claude-skills

Use when a user has podcast, interview, or talking-head audio that needs cleanup — denoise, de-hum, level dialogue, and duck music under voice. Triggering symptoms include phrases like "podcast audio is noisy", "background hum in interview", "music too loud under voice", "level out my voiceover", "fix my podcast", or any DaVinci Resolve Fairlight audio cleanup question.

Images, Video & Audio

Davinci Resolve Color Grade Webcam

35

ChaiWithJai/davinci-resolve-claude-skills

Use when a user wants webcam, interview, or talking-head footage to look broadcast-quality — corrects exposure, white balance, skin tones, and overall color. Triggering symptoms include phrases like "my webcam footage looks dull", "skin tones look orange/green", "wash out background", "make the face pop", "match shots from two cameras", or any DaVinci Resolve color page question for talking-head content.

Writing & Content

Davinci Resolve Computer Use Training

35

ChaiWithJai/davinci-resolve-claude-skills

Use when the user wants Codex to learn DaVinci Resolve through Blackmagic Design lesson homework, operate the Resolve UI with Computer Use, validate skills against real Resolve behavior, or build a capstone workflow that turns local/T7 media into Instagram and YouTube cuts.

Frontend & Design

Dating Profile

46

zocomputer/skills

Creates an ideal dating profile by writing your bio and choosing the best photos in the right order

Images, Video & Audio56

Image to Editable Psd

24

liuethanyes-spec/image-to-editable-psd

把图片按分析拆层、素材生成、坐标装配三阶段重建为可编辑 PSD,默认代码写入或自动脚本。支持 PSGO 生图与实时规格查询;用户选择的生图服务覆盖本次全部位图生成和修复。

Images, Video & Audio

Extract Text From Image

46

zocomputer/skills

Extract text from images, scanned documents, and PDFs using OCR

Images, Video & Audio56

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