# Long video or podcast into shorts with an AI agent — skills, options and steps

> **For AI agents:** find the right skill in one call — `curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"` returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the use-case page.

Find the best moments in a long video, cut them, reframe to 9:16 and burn captions.

**Output:** 3–10 vertical clips, 30–150 s each, with captions and a title per clip

## Recommended route

- **Skill:** Clipify (`clipify`) — Finds funny lines or impact beats, cuts, reframes 16:9→9:16 and burns word captions, locally

## Best skills for this

1. **Clipify** (`clipify`, Louise de Sadeleer, live) — Start here: Finds funny lines or impact beats, cuts, reframes 16:9→9:16 and burns word captions, locally
   - Claude Code: `git clone https://github.com/louisedesadeleer/clipify.git ~/.claude/skills/clipify`
   - Details: https://skills.varg.ai/skills/clipify.md · Example: https://skills.varg.ai/previews/clipify.mp4
2. **Herk Edit Kit** (`herk-edit-kit`, Nate Herk, live) — Alternative: Talking-head reels and Shorts: silence and flub cuts, captions
   - Claude Code: `git clone https://github.com/nateherkai/herk-edit-kit.git`
   - Codex: `git clone https://github.com/nateherkai/herk-edit-kit.git`
   - Details: https://skills.varg.ai/skills/herk-edit-kit.md · Example: https://skills.varg.ai/previews/herk-edit-kit.mp4
3. **Claude Code Video Toolkit** (`claude-code-video-toolkit`, Digital Samba, live) — Alternative: Open-source video workspace for Claude Code with Remotion renders · Needs: Modal or RunPod account for open-model generation
   - Claude Code: `git clone https://github.com/digitalsamba/claude-code-video-toolkit.git && cd claude-code-video-toolkit && claude`
   - Details: https://skills.varg.ai/skills/claude-code-video-toolkit.md · Example: https://skills.varg.ai/previews/claude-code-video-toolkit.mp4
4. **OpenMontage** (`openmontage`, Calesthio, live) — Alternative: Agentic video studio with 12 production pipelines · Needs: API keys for the providers you enable
   - Claude Code: `git clone https://github.com/calesthio/OpenMontage.git`
   - Details: https://skills.varg.ai/skills/openmontage.md · Example: https://skills.varg.ai/previews/openmontage.mp4
5. **Media Download** (`media-download`, varg, live) — Adds: Downloads the source episode from YouTube or X by link
   - Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg`
   - Codex: `npx skills add vargHQ/skills --skill media-download -a codex -y`
   - Cursor: `npx skills add vargHQ/skills --skill media-download -a cursor -y`
   - Details: https://skills.varg.ai/skills/media-download.md · Example: https://skills.varg.ai/previews/media-download.mp4
6. **ElevenLabs Speech to Text** (`elevenlabs-speech-to-text`, ElevenLabs, live) — Adds: Word timestamps and speaker labels, so the crop follows whoever is talking · Needs: ElevenLabs API key (ELEVENLABS_API_KEY)
   - Claude Code: `npx skills add elevenlabs/skills --skill speech-to-text -a claude-code`
   - Codex: `npx skills add elevenlabs/skills --skill speech-to-text -a codex`
   - Cursor: `npx skills add elevenlabs/skills --skill speech-to-text -a cursor`
   - Gemini CLI: `npx skills add elevenlabs/skills --skill speech-to-text -a gemini-cli`
   - OpenClaw: `npx skills add elevenlabs/skills --skill speech-to-text -a openclaw`
   - Details: https://skills.varg.ai/skills/elevenlabs-speech-to-text.md

## Ask the person first

Put these choices in front of the person before spending anything. Paste the example link next to each option: people pick a look by seeing it.

**Which moments?**

- One clear claim per clip (insight) · real example: https://x.com/StevenBartlett/status/2112567934602407955
- Funniest lines
- Hot takes / controversy

**Reframe?**

- Follow the speaker's face · real example: https://x.com/StevenBartlett/status/2113918927927418989
- Cut from the host's question to the guest's answer · real example: https://x.com/StevenBartlett/status/2111183328766517278
- Stacked split, only when both reactions matter

**Clip length?**

- One punchline, 30–60 s
- A full answer, 90–150 s · real example: https://x.com/StevenBartlett/status/2058859955785011251

**Caption style?**

- Calm phrase captions, sentence case · real example: https://x.com/StevenBartlett/status/2112567934602407955
- Word-by-word pop — [Caption Animation](https://skills.varg.ai/skills/iart-caption-animation.md)
- Karaoke highlight — [Remotion Captions](https://skills.varg.ai/skills/remotion-captions.md) · example: https://skills.varg.ai/previews/remotion-captions.mp4
- 3D captions around the speaker — [3D Camera Captions](https://skills.varg.ai/skills/hyperframes-camera-3d-captions.md) · example: https://skills.varg.ai/previews/hyperframes-camera-3d-captions.mp4

## Steps

1. Download the episode; transcribe with word timestamps and speaker labels
2. Pick moments that each make one claim, and confirm the list with the person
3. Title every clip: guest + one specific claim
4. Open on the strongest line, track the speaker, cut host question → guest answer
5. If the show isn't yours, add commentary, b-roll or graphics (a crop and captions don't count)
6. Captions in the middle band, export 9:16, link each clip to the full episode

## What works now (researched 2026-10-27)

What wins in Oct 2026 is a single-idea clip that opens on the payoff line, tracks the person talking, and is titled 'guest + one specific claim'. Clips now often run 1:40-2:10 because Shorts take up to 3 minutes. Raw re-uploads by clip farms, gameplay split-screens and center crops of two-shots stopped working: since 1 Oct 2026 YouTube cuts Shorts reach for re-uploads that add nothing.

1. **Start the clip on the most quotable line, inside the first 2 seconds. Put the context after it, never a greeting or 'so anyway'.** OpusClip's study of 495K podcast clips tells creators to lead with the most provocative quote within 2 seconds, and its own data says 50-60% of people who leave do so in the first 3 seconds (vendor-reported). ([OpusClip, podcast clips on YouTube (2026 data)](https://www.opus.pro/research/best-time-podcast-clips-youtube))
2. **Let the idea set the length: 30-60 s for one punchline, 90-150 s for a full answer. End when the answer ends.** 44.7% of 495K podcast clips are 30-60 s. TikTok's viral tier has a 41 s median but a 179 s 90th percentile. Diary of a CEO's Oct 2026 vertical clips run 1:43-2:08 and still pull 50k-1.2M views on X. ([OpusClip, Anatomy of a viral TikTok in 2026](https://www.opus.pro/blog/anatomy-of-a-viral-tiktok-2026))
3. **Reframe by speaker, not by the centre. Track the active face and cut from the host's question to the guest's answer. Use a stacked split only when both reactions matter.** A fixed center crop is called the worst pattern for two-person shows because it cuts off off-centre speakers. Speaker tracking is the dominant layout. Native 9:16 beats letterboxed uploads by a reported 30-50% (operator A/B tests). ([Conbersa, podcast clip vertical format (May 2026)](https://www.conbersa.ai/learn/podcast-clip-vertical-video-format))
4. **If the episode isn't yours, add something of your own to every clip: commentary, an opening question card, b-roll or motion graphics. Captions and a crop alone don't count.** YouTube said on 1 Oct 2026 it will 'reduce the reach of content re-uploaded from other creators without adding anything of your own'. 'Minor technical edits or template-based changes' do not count as adding value. ([YouTube Help, Prioritizing original content on Shorts (Oct 2026)](https://support.google.com/youtube/blog/470890423/prioritizing-original-content-on-shorts?hl=en))
5. **Link every clip to the full episode and post it within 3 days of the episode, with a title that matches the episode's theme.** Spotter saw a 20% lift in long-form views from Shorts linked through Related Video. Shorts posted within 3 days of the episode drove the most. Instagram's new 'Features' (26 Oct 2026, per Colin and Samir quoting Mosseri) links up to 8 clips to the full video. ([Spotter, views from Related Shorts links](https://spottercommunity.beehiiv.com/p/increase-views-from-related-shorts))

**Stopped working:**

- Re-uploading another show's moments with only a crop and captions. YouTube now down-ranks this in the Shorts feed and it can be demonetised as reused content.
- Subway Surfers or Minecraft parkour split-screens under the speaker. The format is now shorthand for 'brainrot' and reads as low-effort filler.
- A fixed center crop of a wide two-shot. Speakers get cut off at the edges and the clip looks auto-generated.

## Viral formats right now

Show the person these examples when they choose a direction.

1. **Guest-on-one-claim insight clip**: One speaker in a tracked 9:16 crop, 1:40-2:10 long, calm phrase captions, titled '[Guest] on [one specific claim]'. It cuts to the host only for the question. Why it spreads: Diary of a CEO's own clips in this form get 50k-1.2M views on X, and the practical ones get saved more than liked (Huberman clip: 2,273 bookmarks to 1,771 likes). The title promises one concrete thing, and the clip delivers it. Make it with [Clipify](https://skills.varg.ai/skills/clipify.md) (`clipify`).
   - [@StevenBartlett on X, 2026-10-20, 107K views, 2K saves](https://x.com/StevenBartlett/status/2112567934602407955): Diary of a CEO's own clip. 1:43 long, single speaker tracked in 9:16, calm two-line sentence-case captions in the lower middle, small logo top-left. Title is 'guest + one specific claim'. Save ratio 1.28. · clip: https://video.twimg.com/amplify_video/2112567719652724736/vid/avc1/720x1280/KcdkYz0m8lnSnUGN.mp4
   - [@StevenBartlett on X, 2026-05-25, 1.2M views, 1K saves](https://x.com/StevenBartlett/status/2058859955785011251): 1:51 clip. Opens with a white headline bar ('Bruno Fernandes reveals Man United's biggest mistakes') under one-word ALL-CAPS captions; the bar drops after the first seconds and the single word keeps going. · clip: https://video.twimg.com/amplify_video/2058859702428037120/vid/avc1/720x1280/5g1PWUNT3L8W2ti2.mp4
   - [@StevenBartlett on X, 2026-10-16, 49K views, 2K saves](https://x.com/StevenBartlett/status/2111183328766517278): 2:04 clip built as host question then guest answer: the crop cuts from the host to the guest instead of a split screen. Save ratio 1.12 on under 50k views (qualifies on bookmarks). · clip: https://video.twimg.com/amplify_video/2111182908807372800/vid/avc1/720x1280/_ix_1P06F4TEN9Q8.mp4
2. **Transformed talking-head clip (b-roll led)**: The speaker shrinks to the bottom third while full-screen b-roll, screenshots or motion graphics illustrate each sentence. Flubs and silences are cut and short ALL-CAPS captions highlight one key word. Why it spreads: This is the version YouTube's Oct 2026 originality update rewards: the edit adds something new. Both examples were made by one agent prompt and got 638 and 1,509 bookmarks. Make it with [Herk Edit Kit](https://skills.varg.ai/skills/herk-edit-kit.md) (`herk-edit-kit`).
   - [@rileybrown on X, 2026-10-18, 45K views, 638 saves](https://x.com/rileybrown/status/2111925755215040779): Talking head turned into a b-roll-led short by one Opus prompt: flub cuts, full-screen b-roll, speaker in the bottom third only while talking, 2-3 word ALL-CAPS captions with the key word in yellow. He lists all 15 pipeline steps. · clip: https://video.twimg.com/amplify_video/2111923156575256578/vid/avc1/720x1280/ckA7ArpvCjdDvlEU.mp4
   - [@Aykutuces on X, 2026-10-16, 70K views, 2K saves](https://x.com/Aykutuces/status/2111094816591245352): Turkish. A plain desk recording gets 20 named effects (headline wall, kinetic captions, freeze frame, zoom-through cut...), each one asked for by name in Claude. Shares the full effect list. Save ratio 2.6. · clip: https://video.twimg.com/amplify_video/2111029835845849088/vid/avc1/720x1280/cOVnCYO6yMnOQ5NL.mp4

## Set up varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt

## Related

- [Faceless YouTube / TikTok video](https://skills.varg.ai/use-cases/faceless-video.md): A narrated short or long video with no presenter: script, voiceover, visuals, captions, music.