What is assemble-video?

A process for combining recorded video clips, generated narration, and branding sounds into a final MP4 video from a TOML project file.

It is for assembling Android or iOS feature videos, including an audio-first workflow that calculates clip durations before recording.

It removes manual timing and assembly work by matching clips to narration, joining scenes, and adding intro and outro sounds.

How baijum/ukulele-companion configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to baijum/ukulele-companion. 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/baijum/ukulele-companion/main/.cursor/skills/assemble-video/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/baijum/ukulele-companion

Made for: Cursor.

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/baijum/ukulele-companion/assemble-video/github.svg)](https://agentmods.dev/skills/baijum/ukulele-companion/assemble-video)

Your own site

<a href="https://agentmods.dev/skills/baijum/ukulele-companion/assemble-video"><img src="https://agentmods.dev/badge/skills/baijum/ukulele-companion/assemble-video/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/baijum/ukulele-companion/assemble-video"><img src="https://agentmods.dev/badge/skills/baijum/ukulele-companion/assemble-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 788 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Rogue Agent · line 16
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium Agent Snooping · line 97
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

How audits are shown

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	$0.00051	$0.00788
Opus 5	$0.00026	$0.00394
Sonnet 5	$0.00010	$0.00158
Haiku 4.5	$0.00005	$0.00079

Measured 12d ago against content hash cb5af2ad2458, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

assemble-video 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 12d 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.

.cursor/skills/assemble-video/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Assemble Video from TOML Project

Runs scripts/assemble_video.py to assemble per-scene video clips with AI-generated voiceover narration and branding jingles into a final MP4.

Prerequisites

ffmpeg on PATH
Python 3.11+ (for tomllib)
OPENAI_API_KEY in ~/.secrets
pip install openai
Pre-recorded video clips (use /record-clips to create them)

Workflow

Full assembly (clips already recorded)

source ~/.secrets
python3 scripts/assemble_video.py docs/videos/<feature>/android.toml

Replace android.toml with ios.toml for iOS videos.

The script:

Generates missing TTS audio from narration text
Pads each clip with tpad to match narration duration
Concatenates scenes using the ffmpeg concat filter
Adds branding jingles (intro/outro)
Reports output path, duration, and size

Audio-first workflow (recommended)

Generate audio first to know exact clip durations before recording:

# Step 1: Generate audio, print required clip durations
source ~/.secrets
python3 scripts/assemble_video.py docs/videos/<feature>/android.toml --audio-only

# Step 2: Record clips using the printed durations
# Use /record-clips skill

# Step 3: Assemble final video
python3 scripts/assemble_video.py docs/videos/<feature>/android.toml

TOML Project Format

Each feature has per-platform TOML files in docs/videos/<feature>/:

android.toml -- Android-specific scenes, recording notes, and resolution
ios.toml -- iOS-specific scenes, recording notes, and resolution

Audio (audio/ directory) is shared across platforms since narration is platform-agnostic.

[project]
title = "Feature Name - Ukulele Companion"
output = "../../feature-videos/android/feature-name.mp4"
resolution = "1080x2424"

[branding]
intro = "../../jingle-intro.wav"
outro = "../../jingle-outro.wav"

[voiceover]
model = "tts-1-hd"
voice = "nova"
volume_boost = 3.0

[[scene]]
name = "scene-name"
video = "clips/android/01-scene.mp4"
audio = "audio/01-scene.mp3"
narration = """Narration text."""
delay = 1.0
min_clip_duration = 25

Read the full file on GitHub · 98 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.

12d ago First seen · 98 lines · 51 tokens per session scan A cb5af2ad2458

Subscribe to this mod's changes

assemble-video is a skill published in the GitHub repository baijum/ukulele-companion (14 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 788 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 Educational android jetpack-compose kotlin material3 music

movie-tv

Search movies and TV shows, get ratings, recommendations using TMDB. Use when: user asks about movies, TV shows, ratings, 'what should I watch', trending shows. Don't use when: user asks about YouTube videos, music, or live TV schedules.

sepivip/SeekerClaw · 57 tokens

joke

Tell jokes and make the user laugh. Use when: user asks for a joke, wants humor, says 'make me laugh', or mood is light. Don't use when: user is asking a serious question, or wants comedy recommendations (use movie-tv skill).

sepivip/SeekerClaw · 55 tokens

sceneview-ios

Build 3D and AR apps on Apple platforms (iOS, macOS, visionOS) with SceneViewSwift — the SwiftUI wrapper around RealityKit. Use whenever the user asks for "3D in SwiftUI", "AR with ARKit in SwiftUI", a model viewer for iOS, or any Apple-platform 3D/AR app where the dependency is the SceneViewSwift Swift Package from…

sceneview/sceneview · 148 tokens

sceneview-web

Build 3D and WebXR (AR/VR) experiences in the browser with SceneView for Web — Filament.js (WebGL2/WASM) wrapped in a Kotlin/JS DSL and a plain-JavaScript API on window.sceneview. Use whenever the user asks for "3D in the browser", "a web model viewer", "WebXR AR/VR", or any browser 3D/AR app where the dependency is…

sceneview/sceneview · 147 tokens

sceneview

Build 3D and AR apps with the SceneView SDK in Jetpack Compose, SwiftUI (iOS/macOS/visionOS via SceneViewSwift), Web (Filament.js), Flutter and React Native. Use whenever the user asks for "3D in Compose", "AR with ARCore in Compose", a model viewer, or any cross-platform 3D/AR app where the dependency is…

sceneview/sceneview · 156 tokens

to-plan

Use when one ready GitHub issue or an in-chat task needs a repository-aware implementation plan for a later implementation workflow.

chrisbanes/skills · 27 tokens

ukulele-companion: Skill for Cursor