C&M
Reference Asset Pack Operator's Reference No. 01
YouTube Shorts automation · reference build + method

A pipeline that ran in production, documented so you can inspect it before you buy.

An automated YouTube Shorts system — n8n workflow, host scripts, and a 63-page manual — refined during a documented 35-day production run, with the method to rebuild it for your own channel using AI as a collaborator.

$499 Founding release

For operators who can run SSH, Docker, and n8n — and who want a documented system to adapt, not a one-click product. No channel-growth or revenue guarantees; the system is what you receive.

Inspect the package

See the output, the workflow, and the shipped files — before you buy.

The operating channel and its analytics stay private. The product mechanics do not. The manual pages, workflow canvas, script excerpts, and package tree below come directly from the shipped files.

Shown

The shipped manual pages, the actual n8n workflow canvas, exact script excerpts, and the full package contents.

Not claimed

Views, revenue, subscriber growth, or any outcome for your channel. This is a system, not a results promise.

Specimen 01 · The manual 63 pages · PDF + interactive HTML
Manual page — Chapter 1 overview showing the daily pipeline flow
Ch.1 — what the system does
Manual page — video composition spec table
Ch.4 — composition spec
Manual page — a subtle operational pitfall about card duration
Ch.7 — a real pitfall

Direct page previews from the shipped manual — structure, implementation, and the kind of operational detail you only write after living with the system. Click any page to read it.

Specimen 02 · The n8n workflow 1 workflow · 14 nodes · credentials removed
The actual n8n workflow canvas — 14 nodes from schedule trigger through GPT, image and TTS generation, to build job and sheet logging
Actual n8n canvas · click to enlarge
Credentials removedInactive on delivery14 nodes · 1 importable JSON

Annotated map — redrawn from the shipped 14-node graph to keep the full flow readable:

Schedule Delayrandom Get rowsheet Roll cardcount GPT-4oscript Code JSsplit Image+TTSHTTP ×2 Convertto file Buildjob Log sheet

Delivered inactive and with credentials removed, so you can inspect and configure it before enabling the schedule.

Specimen 03 · Host scripts excerpts from the shipped files

Validates the job and composes the final vertical MP4. Refuses to run while the default channel placeholder remains.

# breakage if a malformed id ever reaches this script. $WORK_DIR ends up in
# `rm -rf` later, so this guard matters.
if ! [[ "$JOB_ID" =~ ^[A-Za-z0-9_-]+$ ]]; then
  echo "ERROR: Invalid job_id: $JOB_ID"
  exit 1
fi

# Refuse to render with the default channel placeholder — otherwise every
# generated Short would carry the literal text "YOUR CHANNEL", then
# upload itself to YouTube. See Chapter 4 for setup.
if [ "$CHANNEL_NAME" = "YOUR CHANNEL" ]; then
  echo "ERROR: CHANNEL_NAME is still the placeholder."
  exit 1
fi

Watches for completed job folders and controls execution. Drains the whole queue on each event so a render never strands a job.

process_pending_jobs() {
  for f in "$JOBS_DIR"/*.json; do
    [ -f "$f" ] || continue
    JOB_ID=$(basename "$f" .json)

    # Skip malformed job ids early so they don't reach
    # process_job.sh as confusing FAILED entries.
    if ! [[ "$JOB_ID" =~ ^[A-Za-z0-9_-]+$ ]]; then
      echo "[$(date)] SKIPPED invalid job_id: $JOB_ID" >> "$DAEMON_LOG"
      continue
    fi
    "$SCRIPT" "$JOB_ID" >> "$DAEMON_LOG" 2>&1
  done
}

Handles authenticated YouTube uploads after composition. The comment is the operator's own note from the production run.

    # Reference build note:
    # chunksize=-1 uploads the MP4 in one request. This worked
    # for the 35-day production run, but very large files or
    # unstable networks may benefit from a fixed chunk size.
    # This script intentionally does not retry; the caller
    # decides policy.
    media = MediaFileUpload(
        file_path,
        chunksize=-1,
        resumable=True,
        mimetype="video/mp4",
    )
Specimen 04 · What lands in the ZIP 17 files
Reference-Asset-Pack/ ├── README_FIRST.pdf start here ├── QUICK_START.pdf one-page setup map ├── LICENSE.txt ├── manual/ │ ├── YouTube-Shorts-Automation-Manual.pdf 63 pages │ └── index.html interactive ├── scripts/ │ ├── process_job.sh │ ├── watcher.sh │ └── youtube_upload.py ├── workflow/ │ └── n8n-workflow.json 14 nodes └── reference-assets/ ├── asset-01 … asset-08.html 8 files
17
files total
3
scripts
1
workflow
8
reference assets
What you receive

What your purchase includes.

The manual explains the decisions; the scripts and workflow are the implementation; Chapter 8 is the part you reuse across channels. Everything below arrives as one download, with updates provided over the following six months.

01 Manual
63-page implementation manual

Infrastructure, AI pipeline, composition, upload, operational safety, pitfalls, and adaptation. Shipped as PDF and a searchable interactive HTML version.

02 Scripts
3 production host scripts

The FFmpeg composition script, the watcher daemon, and the Python YouTube uploader — the exact files, with configuration guards built in.

03 Workflow
1 sanitized n8n workflow

Importable JSON, 14 nodes, credentials removed and delivered inactive so you configure it deliberately before the first run.

04 Reference assets
8 standalone visual references

Standalone HTML you can open in any browser — the same explainers used to reason about the system.

What's InsideSystem Architecture — four stages, one daily runSetup Flow — five phases, end to endPackage Contents — what's in the ZIPIncluded / Not includedBefore / After — workflow comparisonQuick Start — one-page setup cardRisk & Control — three failure modes handled by design
05 The method
Chapter 8 — adapting it to your channel inside the manual

The reusable part: what to keep, what to replace, and how to use AI as a collaborator to rebuild the reference for your own concept. This is the product — it's Chapter 8 of the manual above, not a separate file.

06 Updates
6 months of compatibility updates provided over time

Not part of the initial download — fixes for breakage from dependency and platform changes, provided during your six-month update window. After that, you have the method to adapt yourself.

How the pipeline works

One scheduled run a day, four stages.

n8n orchestrates generation; the filesystem hands off to host scripts; FFmpeg composes; the Python uploader publishes. You check a log if you want to.

Stage 1
Orchestrate
A daily trigger picks a topic and generates the script, on-screen text, and metadata.
n8n · GPT-4o
Stage 2
Generate media
One image and one narration clip per card, five cards, written to the job folder.
image model · TTS
Stage 3
Compose
The watcher picks up the job; FFmpeg builds an 18–22s vertical MP4, card duration driven by narration length.
watcher.sh · FFmpeg
Stage 4
Publish
The Python uploader authenticates via a stored refresh token and posts to YouTube with title, description, and tags.
youtube_upload.py

Each run produces five cards — one generated image and one narration clip per card — composed into an 18–22 second, 1080×1920 Short. A 100-topic pool with 60-day anti-repetition keeps daily topics from repeating. Running cost is roughly $6.69/month (about $5 VPS + API), documented in the manual's cost breakdown.

The method

The reference build is a case study. The method is the product.

Most automation packages hand you a template to copy. This one hands you a working example — and a documented way to rebuild it for your own channel, with AI as a collaborator rather than an author. Chapter 8 is where that lives.

01 · The separation

What AI does, what you decide

AI handles structured transformations, known patterns, and cause hypotheses. Aesthetic identity, platform intuition, and the last debugging step stay yours. The chapter gives you a framework for telling them apart.

02 · Failure modes

Seven pitfalls mapped in advance

Layout safety, multi-line alignment, dynamic length, identity mismatch, audio sync, title wrap, visual breathing room. When you adapt, you'll hit several — pre-mapped so you don't rediscover them on day twelve.

03 · Incident anatomy

How one small miss becomes a disk-full event

A real multi-stage cascade documented end to end — deployment miss, field omission, preview-vs-runtime mismatch, retry storm — each with the guard that catches it.

04 · Reusable prompts

AI-as-collaborator, built in

Copy-paste meta-prompts for concept definition, image-prompt adaptation, script tone, and incident diagnosis — with the verified-not-guessed principle baked into each.

The files document one reference build. The method helps you reconstruct it for your own channel concept.

Fit check

Best for operators. Wrong for one-click buyers.

Reading both columns before buying saves everyone a refund conversation. The narrow fit is deliberate, not an accident.

You'll get value if you
  • Are comfortable with SSH, Docker, and reading shell scripts
  • Want to understand how the system is built and operated, not just run it blindly
  • Plan to adapt it to your own channel concept, not duplicate this one
  • Can complete the Google OAuth setup for uploads
  • Are fine with the ongoing VPS and API costs described above
Probably not for you if you
  • Want a one-click tool with a dashboard and a support team
  • Want a done-for-you channel with content and growth strategy bundled
  • Expect guaranteed views, monetization timelines, or platform tactics
  • Aren't willing to configure servers, credentials, and prompts yourself
  • Are unwilling to spend on API and hosting after purchase
Pricing

One-time purchase. Lifetime access to what you receive.

No subscription, no upsells. The Founding price applies during the initial release window and reflects the package as it exists today.

Founding release
Reference Asset Pack — Founding
$349 $499

One-time. Lifetime download access. 6 months of compatibility updates.

What you're paying for beyond the workflow JSON: the operating documentation, the host scripts, the recovery logic, and the adaptation method — shaped by a live daily production run, not a whiteboard.
  • 63-page manual (PDF + interactive HTML)
  • 3 production scripts, ready to configure
  • Sanitized n8n workflow (14 nodes), import-ready
  • 8 standalone visual reference assets
  • Chapter 8 — the adaptation method
  • 6 months of compatibility updates

Instant download of all files after purchase, via Lemon Squeezy. Support is best-effort by email, no SLA. A reference implementation, not a managed service. No performance guarantees — the system is what you receive; your channel's results are your work.

Sales availability: United States, Canada (excluding Québec), Australia, New Zealand, and Singapore only at launch. Other jurisdictions are not currently offered, even if the checkout interface technically displays them.

Included support
  • Download and access issues
  • Missing-file or install-blocking problems
  • Setup clarification within documented scope
  • Compatibility bug reports during the update window
Not included
  • Done-for-you installation
  • Channel strategy or niche selection
  • Debugging modified workflows or custom code
  • One-on-one coaching or performance guarantees
FAQ

Questions you'd reasonably ask.

A free template is a starting graph. This is a documented system that ran daily in production, plus the host scripts a workflow alone can't cover (FFmpeg composition, a watcher daemon, authenticated upload), plus the recovery logic and the method to adapt it. The value is the operating knowledge around the JSON, not the JSON.
No, but you should be comfortable with SSH, running shell commands, and reading what a script does. The manual is written for an operator, not a coder — but it assumes you can configure a server and complete an OAuth setup.
Roughly $6.69/month — about $5 for a small VPS and the rest in API usage for one daily Short. The pipeline section above and the manual's cost breakdown document it. You can lower it with cheaper image or TTS models.
No. The package is the manual, scripts, workflow, and reference assets. The setup is documented in writing, step by step, including a one-page Quick Start map.
Many structured, narration-led Shorts concepts. Your topic pool, image prompts, visual system, and content strategy still need to be designed for your channel — that's exactly what Chapter 8's method is for. The reference build documents one concept; the method is what you reuse.
The pipeline depends on tools you don't control — APIs, runtimes, platform policies. The manual maps the dependency categories and how to harden each. The package includes 6 months of compatibility updates; beyond that, you have the method to adapt yourself.
No. The operating channel and its analytics stay private — disclosing them would expose the niche to duplication. What's public is the mechanism: the manual, the workflow structure, the shipped code, and the exact package contents. Identity is redacted; the system is shown.
Because the package is digital and downloaded immediately, refunds are limited and governed by the Terms of Sale at checkout. Refunds don't cover API spend, VPS costs, or time invested. Read the Fit Check above — it's a better filter than the price.

A working reference build, the manual, and the method to make it yours.

Documented from a live daily production run. Inspect the manual, the workflow, and the shipped code above — then decide.

$499 Founding release