A video-editing workflow for Cut-AI that uses a VTT subtitle transcript and an MP4 recording to find highlights and prepare short-form clips.

Use it to identify highlights, cut clips, add English and Chinese subtitles, extract clip transcripts, and draft content for seven platforms.

It turns a long recording into selected clips and related publishing material without requiring you to choose every segment manually.

How AI-Nate/Cut-AI configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to AI-Nate/Cut-AI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/AI-Nate/Cut-AI/main/.claude/skills/viral-clips/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/AI-Nate/Cut-AI

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ai-nate/cut-ai/viral-clips/github.svg)](https://agentmods.dev/skills/ai-nate/cut-ai/viral-clips)

Your own site

<a href="https://agentmods.dev/skills/ai-nate/cut-ai/viral-clips"><img src="https://agentmods.dev/badge/skills/ai-nate/cut-ai/viral-clips/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ai-nate/cut-ai/viral-clips"><img src="https://agentmods.dev/badge/skills/ai-nate/cut-ai/viral-clips.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,326 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.01326
Opus 5	$0.00026	$0.00663
Sonnet 5	$0.00010	$0.00265
Haiku 4.5	$0.00005	$0.00133

Measured 11d ago against content hash f36808cfc67b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

viral-clips scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/viral-clips/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running the Cut-AI viral clips pipeline. This is a 3-phase automation that takes a recording session directory and produces viral short-form clips with subtitles and platform-specific content drafts.

The user passed this data directory: $ARGUMENTS

Setup

Derive the session name from the directory basename (e.g., data/020725 -> session = 020725).
Auto-detect the .vtt transcript file and .mp4 video file inside the $ARGUMENTS directory using Glob. There should be exactly one of each. If there are multiple, ask the user which to use.
Set these variables for the rest of the pipeline:
- VTT = path to the .vtt file
- MP4 = path to the .mp4 file
- SESSION = session name
- HIGHLIGHTS = output/<SESSION>/highlights_<SESSION>.json
- OUTPUT_DIR = output/<SESSION>

Phase 1: Analyze Transcript

First create the output directory, then run the Gemini analysis to identify highlight clips:

mkdir -p output/<SESSION> && source venv/bin/activate && python script/cut_ai.py analyze --transcript <VTT> --output <HIGHLIGHTS>

After the command completes:

Display a summary table of all highlights found (number, title, time range, category, viral score).
STOP and ask the user to review <HIGHLIGHTS>. Tell them:
- "Review and edit <HIGHLIGHTS> if needed (adjust timestamps, remove/reorder clips, edit titles). Reply go when ready to proceed to Phase 2."
Do NOT proceed until the user confirms.

Phase 2: Cut Video with Dual-Language Subtitles

Once the user confirms, generate English and Chinese subtitle clips:

source venv/bin/activate && python script/cut_ai.py clip_dual --video <MP4> --highlights <HIGHLIGHTS> --subtitles <VTT> --output <OUTPUT_DIR>

This produces:

<OUTPUT_DIR>/English/ - clips with burned-in English subtitles
<OUTPUT_DIR>/Chinese/ - clips with burned-in bilingual English + Chinese subtitles

After completion, report how many clips were generated in each directory.

Read the full file on GitHub · 133 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 133 lines · 52 tokens per session scan A f36808cfc67b

Subscribe to this mod's changes

viral-clips is a skill published in the GitHub repository AI-Nate/Cut-AI (22 stars, last pushed 7mo ago), licensed MIT. It adds 52 tokens to every session and 1,326 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Creative and media

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

general-video

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…

heygen-com/hyperframes · 92 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

chengfeng-check-updates

An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.

Agentchengfeng/chengfeng-videocut-skills · 120 tokens

diagnostic-stem-delivery

Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.

HKUDS/OpenSpace · 23 tokens

Cut-AI: Skill for Claude Code