Skip to content
Back to skills

Pod Frame

ASecurity

Pod Frame video-editing style for Claude: Podcast edit: auto camera switching by who is talking, name cards, quote pulls and a live audio bar. Use for video podcasts and interviews with 2-4 cameras (or one wide shot). Turns a raw clip into a finished 16:9 edit with the video-studio-core engine (transcribe, auto-cut, motion graphics, sound, grade).

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 18, 2026
content-marketingpythongobash

Works with

  • cli

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned November 18, 2026

npx -y skills add Viprasol-Tech/claude-video-editing-skills --skill pod-frame --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pod Frame?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Pod Frame
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/viprasol-tech-pod-frame/badge)](https://www.skillsdirectory.com/skills/viprasol-tech-pod-frame)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: pod-frame
description: "Pod Frame video-editing style for Claude: Podcast edit: auto camera switching by who is talking, name cards, quote pulls and a live audio bar. Use for video podcasts and interviews with 2-4 cameras (or one wide shot). Turns a raw clip into a finished 16:9 edit with the video-studio-core engine (transcribe, auto-cut, motion graphics, sound, grade)."
license: MIT
---

# Pod Frame

Podcast edit: auto camera switching by who is talking, name cards, quote pulls and a live audio bar.

- **Best for:** video podcasts and interviews with 2-4 cameras (or one wide shot)
- **Category:** Podcast / repurposing
- **Default format:** 16:9 (change with `--format 9:16 | 1:1 | 4:5 | 16:9`)
- **Needs camera footage:** yes, a raw talking clip
- **Text behind the speaker:** no

## Before you start

This style runs on the **video-studio-core** skill, which must be installed in the same skills folder.

- `CORE` = the `video-studio-core` folder next to this one (e.g. `~/.claude/skills/video-studio-core`).
- `STYLE` = this skill's folder (it holds `theme.json` and `theme.css`).
- First time on a machine: `python CORE/scripts/check_env.py`, and fix anything it reports.
- If `CORE` is missing, tell the user to install `video-studio-core` from the same pack.

## Make the edit

```bash
python CORE/scripts/run.py clip.mp4 --style STYLE --work edit-pod-frame --stop-after plan --title "SHOW NAME"
# refine edit-*/plan.json (see below), then check stills:
python CORE/scripts/render.py edit-pod-frame/plan.json --frames 1,3,6,9
python CORE/scripts/render.py edit-pod-frame/plan.json
python CORE/scripts/finish.py edit-pod-frame/plan.json
```

Open `contact_sheet.png` and look at it before the full render. The final video is `final.mp4` in the work folder.
Use `--formats 1:1,16:9` on `finish.py` for extra sizes. Add music with `"music": {"src": "track.mp3", "volume": 0.12}` in the plan.

## The look

- Switch to whoever is talking; minimum shot 2 s; wide shot when both talk.
- Name card the first time each person speaks. Big quote card for the single best line.
- Clean captions in a boxed style, show logo chip top-left.

## Refine the plan

The draft from `make_plan.py` is automatic. Make it good:

- Read `words.json` and rewrite the hook (first 2-3 s) into a short, specific promise.
- Replace weak auto-picked key words with the words that carry the meaning (numbers, results, names, contrasts).
- Fix any mis-heard words in the `words` array (keep their times).
- With separate camera files: `multicam.py camA.mp4 camB.mp4 --wide wide.mp4 --out pod/multicam.mp4`, then use `pod/multicam.mp4` as the input to run.py.
- Add a `lowerthird` (name, role) at each person's first line; ask the user for names and roles.
- Find the best quote and add a `text` element with class `pf-quote` for 4-5 s.
- For shorts from the podcast use clip-miner.
- Element types and fields: `CORE/references/plan-schema.md`.

## Check before delivering

- Contact sheet: text readable, nothing cut off, nothing covering the face unless intended, safe zones respected (9:16: keep text between 10% and 85% of the height).
- Watch for timing: overlays land with the spoken word, not after it.
- `ffprobe` the final file: right size, duration and audio.
- Tell the user what you cut (seconds removed), what the look adds, and where the file is.

## Change the look

Colours and fonts live in `theme.json` (`vars`, `fontsUrl`) and `theme.css`. For a one-off change, edit `plan.json` (`theme.vars`, element `style`) instead of the skill files.

## Example requests

- "Edit my podcast, switch cameras to whoever is talking."
- "Add name cards for me and my guest Rahul, CEO of X."
- "Make the podcast look like a studio show."

Files in this skill

  • SKILL.md3.6 KB
  • theme.css616 B
  • theme.json1.2 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in content-marketing →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.