ukulele-companion: Skill for Cursor

.cursor/skills/record-clips/SKILL.md

record-clips is a skill for Cursor from baijum/ukulele-companion. It costs 73 tokens per session (1,780 once invoked), scanned A, original, MIT.

A tool for recording short screen videos for each scene in an Android or iOS video project. It reads a TOML file, a simple text configuration format, to find the scenes and recording lengths.

In plain words
What is it for?
Use it to navigate an installed app in an Android emulator or iOS Simulator and save one clip per scene. It supports projects configured with android.toml or ios.toml.
Why use it?
Recording every app screen manually can lead to missing scenes or clips that are too short. This provides a defined recording process for the listed scenes.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is baijum/ukulele-companion's own configuration. It tells Cursor how to work on ukulele-companion itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ukulele-companion configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/assemble_video.py <android.toml or ios.toml> --audio-only.

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/record-clips/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.

agentmods badge for record-clips

README.md
[![agentmods](https://agentmods.dev/badge/skills/baijum/ukulele-companion/record-clips/github.svg)](https://agentmods.dev/skills/baijum/ukulele-companion/record-clips)
Your own site
<a href="https://agentmods.dev/skills/baijum/ukulele-companion/record-clips"><img src="https://agentmods.dev/badge/skills/baijum/ukulele-companion/record-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.

agentmods 80×15 button for record-clips

Your own site · 80×15
<a href="https://agentmods.dev/skills/baijum/ukulele-companion/record-clips"><img src="https://agentmods.dev/badge/skills/baijum/ukulele-companion/record-clips.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,780 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 high

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 →

  • high Tool Misuse · line 88
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Agent Snooping · line 155
    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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.01780
Opus 5 $0.00036 $0.00890
Sonnet 5 $0.00015 $0.00356
Haiku 4.5 $0.00007 $0.00178

Measured 11d ago against content hash fa94d4d2b32c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

record-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.

.cursor/skills/record-clips/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Record Clips for Video Project

Record per-scene video clips for a TOML video project. Each clip is a short screen recording of one scene's interactions on the Android emulator or iOS Simulator.

Prerequisites

Android

  • ADB at ~/Library/Android/sdk/platform-tools/adb
  • A running emulator (verify with adb devices)
  • App installed on emulator (run ./gradlew installDebug if needed)
  • Onboarding already dismissed

iOS

  • Xcode with xcrun simctl available
  • A booted iOS Simulator (verify with xcrun simctl list devices booted)
  • App installed on simulator
  • Onboarding already dismissed

Before recording clips, generate the voiceover audio first so you know exactly how long each clip needs to be:

source ~/.secrets
python3 scripts/assemble_video.py <android.toml or ios.toml> --audio-only

This prints a table showing the required min_clip_duration for each scene. Record clips at least that long.

Recording Process (Android)

Step 1: Read the project

Parse the android.toml to get the scene list. For each scene, note:

  • name -- what the scene shows
  • video -- where to save the clip (under clips/android/)
  • min_clip_duration -- minimum recording length (or use 30s default)
  • recording_notes -- step-by-step instructions for what to do on screen during recording. Follow these precisely to avoid navigating away from the target screen or triggering unwanted intents. If recording_notes is absent, infer interactions from the narration text.

Step 2: Prepare the app

ADB=~/Library/Android/sdk/platform-tools/adb
$ADB shell am force-stop com.baijum.ukufretboard
sleep 1
$ADB shell am start -n com.baijum.ukufretboard/.MainActivity
sleep 3

Step 3: Record each scene

For each scene:

  1. Read the scene's recording_notes field for explicit interaction instructions
  2. Navigate to the correct screen state (use drawer + uiautomator)
  3. Set up the initial state described in recording_notes
  4. Start recording with the scene's min_clip_duration as the time limit
  5. Perform the interactions listed in recording_notes (respect any "Do NOT" warnings)
  6. Stop recording and pull the file

Read the full file on GitHub · 182 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.

  1. 11d ago First seen · 182 lines · 73 tokens per session scan A fa94d4d2b32c

Subscribe to this mod's changes

record-clips is a skill published in the GitHub repository baijum/ukulele-companion (14 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 1,780 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

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

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

compose-animations

Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.

chrisbanes/skills · 64 tokens

compose-focus-navigation

Use when writing or reviewing Jetpack Compose UI for TV, keyboard, desktop, accessibility focus, D-pad navigation, FocusRequester, focusProperties, key events, or initial focus behavior.

chrisbanes/skills · 41 tokens

compose-state-and-effects

Use when writing or reviewing Jetpack Compose state ownership, remember state, state hoisting, screen state holders, LaunchedEffect, DisposableEffect, SideEffect, Flow collection, navigation, snackbar, analytics, or focus requests.

chrisbanes/skills · 50 tokens

compose-component-design

Use when designing or reviewing reusable Jetpack Compose component APIs with modifier parameters, root layout placement, caller-provided variable content, primitive content parameters, optional content, or boolean shape flags.

chrisbanes/skills · 41 tokens