← YouTube Shorts Pack

5단계 온보딩 코스 / Interactive course →

YouTube Shorts Pack user guide

Before you buy

This is downloadable code, configuration examples and operating documentation to set up on your computer. You must install tools, connect accounts and review output. Uploading the ZIP to a web chat does not start the pipeline. Setup services, AI subscriptions, API credits and hosting are not included. Setup and first-output time depend on your environment.

The instructions target macOS and a terminal. Linux and Windows/WSL require changes to shells, paths, fonts, browser connections, notifications and scheduling; unchanged operation is not guaranteed. Start with one account and one output. Local jobs do not run while the computer is off or asleep.

Do I need both Claude and Codex subscriptions?

No. Start with one supported cloud CLI that your account can access, with enough remaining usage. Multiple engines provide alternatives when a provider is unavailable. An installation assistant and the CLI invoked by the scripts are separate: signing into a desktop app does not establish that CLI authentication is ready.

Set the engine order to the CLI you use. Image, voice and video APIs may charge separately from a text CLI subscription. Total running cost includes your chosen AI access, media generation and hosting/execution, in addition to the pack. Measure a single output before scheduling; no fixed monthly running cost is promised. Check provider billing and budget controls first.

Official documentation checked on 2026-09-28; check again before paying because plans, limits and models change.

• Claude Code setup and accounts · Claude API billing
• Codex plans · Codex authentication
• Gemini CLI authentication · Gemini API billing

What this pack needs

The first milestone is one reviewable local out/<slot-channel>/final.mp4. Views, revenue and monetization approval are not guaranteed. Local cards and the default TTS route can be a starting point; check the external service's terms and availability.

1. Configure a new folder

Extract and open the pack folder. Compare existing settings instead of overwriting them. Install Python 3.11+, ffmpeg, yt-dlp, zsh and your chosen cloud CLI first.

python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install pillow pyyaml edge-tts playwright
python3 -m playwright install chromium
cp config/channel.example.yaml config/channel.yaml
cp config/automation.example.json config/automation.json
cp config/design-policy.example.json config/design-policy.json
cp config/portfolio-policy.example.json config/portfolio-policy.json
cp config/theme.example.json config/theme.json
cp .env.example .env

Configure main-channel for your topic and slots, initially with a daily cap of 1. Set automation.json engine order to the engines you use. Replace example channel/profile settings, and check that any configured model is available to your account. Enter only your own settings in .env, leave unused API keys empty and export the environment:

set -a
source .env
set +a
export PACK_HOME="$PWD"
export OPS_HOME="$PWD"

Reactivate the environment in a new terminal. Configure the same environment for scheduled jobs later.

2. Generate without uploading

DRY=1 zsh bin/auto-short.sh
NO_UPLOAD=1 zsh bin/auto-short.sh

DRY prints the plan. NO_UPLOAD=1 generates the script, voice, images, render and QA output, then stops before the normal upload branch. This can consume model/API usage. Authentication, dependency or quota failures will stop progress. If your ZIP includes bin/selftest.sh, run it first; initial versions do not include that file.

3. Review

Find this run under out/. Review script.json, final.mp4 and generation/QA logs. Watch the entire video, checking cropping, captions, pronunciation, volume, factual sources and rights to source assets. Inspect supervisor logs under data/automation/ for failures; do not disable gates to force completion.

4. Enable uploads and scheduling

For the first reviewed video, upload manually as private in YouTube Studio to check the account and processing result. Then connect the Aside profile and follow docs/HUMAN-STEPS.md to check visibility and time zones. Version 1.1.0 requires explicit ALLOW_UPLOAD=1 and removing NO_UPLOAD before real uploads can occur. Do not assume that it will reuse the reviewed file: another slot can generate another output.

After verifying one complete flow, edit paths/time zones in jobs/ and register only the required jobs. Sleep, expired logins and quota limits delay local work. To stop, check both local schedules and Studio's scheduled videos.

Ask your installation assistant

Open the extracted folder in Claude Code or Codex and use this request. The assistant consumes your account's usage too. Enter secrets locally, not in chat.

Read docs/START-HERE.md and the README in this folder.
Check my OS, tools and the one cloud CLI I plan to use, including authentication.
Separate required tools, optional tools and additional charges.
Do not overwrite existing .env/config files or print secrets.
Keep schedulers, uploads, publishing and comment DMs disabled.
After checks, help me generate one local output only.
Identify unfinished adapters and failures explicitly.
Show output paths and the human review checklist. Stop before publishing.

Precautions

• Keep .env, tokens, browser profiles and private source material out of public repositories and support requests. Back up existing settings; compare new examples rather than overwriting your configuration.
• Review facts, numbers, sources and rights to images, video, music and voices. Check applicable platform and regional disclosure requirements for affiliate links. Automated review does not replace human review.
• Do not force local-only drafts out of hold by editing their status. Review and revise them through the intended approval flow.
• DRY=1 is a planning option only where the runner supports it. Generation with publishing disabled still consumes CLI/API usage and writes files. Adding an arbitrary --dry flag does not make a command safe.
• To stop automation, disable registered dagu/launchd/cron/Actions schedules, then check posts already scheduled on the platform separately. Stopping local jobs does not cancel existing platform schedules.

Troubleshooting

For support, provide the pack and ZIP version, OS, failing stage/command, expected result and last 20 error lines with secrets removed. Never send keys, cookies or your full .env. See docs/HUMAN-STEPS.md for the operating checklist and docs/PIPELINE.md for the stage reference.