Wall Street Explainer Video Builder
An end-to-end pipeline for producing 1–3 minute Wall Street-style finance/tech explainer videos from real footage, news screenshots and a 2.5D graphics stage.
Image & VideoAdvanced★ 417⑂ 86AI score 8/10Last updated: Oct 26, 2026
What it does
- Guides you through making a 1–3 minute, 16:9, host-free explainer where real people (keyed from actual footage), original news articles and official clips serve as evidence.
- Enforces a gated 8-stage workflow — topic → script → director's table → sourcing → temp VO & timeline → three opening hooks → 720p full cut → final 1080p — stopping for your approval at each stage.
- Ships a working toolchain:
footage.py(search/download/contact sheet/scene cuts/frame extract),snap_news.mjs(clean article screenshots),matte.py+ cleanup/despill scripts (GPU per-frame keying),temp_voice.py(edge-TTS timeline),render.mjs(deterministic frame rendering),motion_check.py(camera-motion audit),mix.py(-14 LUFS mix). - The real payload is the motion doctrine: the camera moves through layered depth to find the subject rather than letting elements animate themselves — the reason the output doesn't look like a slide deck or generic AI video. Deliberately no copy-paste shot templates.
Who it's for
- Finance/tech explainer creators on YouTube and short-form platforms
- Editors who want motion graphics built as code (HTML/JS rendered frame by frame)
- Research or content teams turning market reports into video
- Not for talking-head videos where a presenter appears on camera
Example uses
- "Make an explainer on how much Big Tech is burning on AI capex" — get three topic pitches, a script, a director's table, then 720p and finally 1080p.
- "Key out the CEO from this earnings clip and stand him in front of a giant number" — pull the segment with
footage.py get, matte withmatte.py, apply the horizontal push-swap move frommoves.js. - "My cut feels static like a slideshow" — run
motion_check.pyto compare frozen-frame time, hold counts and push/pull ratio against reference films, and usestrip.pyfilmstrips to spot broken motion.
· · · Install guide · · ·
Try it now, no install
Paste this into Claude to use the skill without installing anything.
Read the instructions in this file and follow them to help me: https://raw.githubusercontent.com/HeyChengC/wallstreet-explainer/HEAD/SKILL.md What I want: (describe your task here)
If Claude can't open the link, open it yourself and paste the contents instead.
↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on AI Skill Mart. Copy the SKILL.m folder from the GitHub repo HeyChengC/wallstreet-explainer into my ~/.claude/skills/wallstreet-explainer/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/HeyChengC/wallstreet-explainer.git ~/.claude/skills/wallstreet-explainer⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal and create the skills folder:
mkdir -p ~/.claude/skills - Clone the repo:
git clone https://github.com/HeyChengC/wallstreet-explainer.git ~/.claude/skills/wallstreet-explainer - Install base tools:
ffmpeg,yt-dlp, Node.js and Python 3. - Install Python deps:
pip install edge-tts numpy opencv-python Pillow rembg(optionalfaster-whisper;onnxruntime-gpufor fast matting). - Install Node deps inside the repo:
npm installthennpx playwright install chromium. - Download the fonts listed in the README into the
fonts/directory. - Restart Claude Code and say "use wallstreet-explainer to make a finance explainer" to trigger the skill.
- On your first run, stop at the 720p cut and review each stage's deliverable before rendering 1080p.
View source on GitHub ↗License: NOASSERTION