Jakeschincariol/youtube-agent-skill

# yt-audit

An audit that lists twenty problems is a way of avoiding the one that matters. This ends in ONE fix.

## Before you write

1. Read `~/.claude/youtube/voice.md` if it exists. That is the user's voice profile: how they talk
   on camera, the words they never use, who they are talking to, what they will not claim. If it
   does not exist, ask for **three of their own videos**, read or transcribe them, infer the voice,
   and write the file. A script in the wrong voice is worse than no script, because they have to
   read it out loud.
2. Never invent a number, a result or a source. If a figure would strengthen it and you do not have
   one, ask for it or write the line without it.

# yt-chapters

```bash
python3 chapters.py transcript.srt --target 8
```

## The rules, which are not optional

A chapter list that breaks any of these silently does not become chapters at all - the block just
sits in the description doing nothing:

- The first entry must be **00:00**.
- There must be **at least three**.
- Each must be **at least 10 seconds** long.

# yt-comment

The comment section is a retention surface, not a chore. Replies in the first few hours are what
decide whether a thread becomes a conversation other people read.

## Before you write

1. Read `~/.claude/youtube/voice.md` if it exists. That is the user's voice profile: how they talk
   on camera, the words they never use, who they are talking to, what they will not claim. If it
   does not exist, ask for **three of their own videos**, read or transcribe them, infer the voice,
   and write the file. A script in the wrong voice is worse than no script, because they have to
   read it out loud.
2. Never invent a number, a result or a source. If a figure would strengthen it and you do not have
   one, ask for it or write the line without it.

# yt-edit

An edit decision list from a timestamped transcript. It prints the cuts. You apply them.

```bash
python3 deadair.py transcript.srt              # srt, vtt or whisper json
python3 deadair.py transcript.srt --floor 0.35 --json
```

No transcript yet? Ask for one, or produce one first - `whisper`, `faster-whisper`, or the caption
track YouTube generates on an unlisted upload all work. Do not guess at timings.

## What it finds

# yt-package

The title and the thumbnail are ONE unit. Writing them separately is why most packaging fails: the
thumbnail repeats the title, and half the click surface says the same thing twice.

```bash
python3 title.py --title "..." --thumb "AI RAN IT"
python3 title.py titles.txt            # one per line, ranked
```

## Before you write

1. Read `~/.claude/youtube/voice.md` if it exists. That is the user's voice profile: how they talk
   on camera, the words they never use, who they are talking to, what they will not claim. If it

# yt-plan

A plan that does not fit the week is a list of regrets. Ask two questions before writing anything:
**how many hours do you actually have**, and **what is already half-made**.

## Before you write

1. Read `~/.claude/youtube/voice.md` if it exists. That is the user's voice profile: how they talk
   on camera, the words they never use, who they are talking to, what they will not claim. If it
   does not exist, ask for **three of their own videos**, read or transcribe them, infer the voice,
   and write the file. A script in the wrong voice is worse than no script, because they have to
   read it out loud.
2. Never invent a number, a result or a source. If a figure would strengthen it and you do not have
   one, ask for it or write the line without it.

# yt-retention

The retention graph is the only honest feedback YouTube gives you. Almost nobody exports it.

```bash
python3 retention.py retention.csv --duration 600
python3 retention.py retention.csv --transcript transcript.srt
```

Getting the file: Studio -> a video -> Analytics -> Engagement -> the audience-retention chart ->
the download icon -> "Audience retention".

## Three different problems

# yt-script

One idea into a script somebody finishes.

Two tools live in this folder and both actually run. Use them. Do not eyeball the hook.

```bash
python3 hookscore.py hooks.txt              # rank your hook options
python3 hookscore.py --hook "one line"      # score a single one
```

## Before you write

1. Read `~/.claude/youtube/voice.md` if it exists. That is the user's voice profile: how they talk

# yt-seo

Search is a smaller lever than packaging and a bigger one than people think for evergreen videos.
For a video aimed at the subscriber feed, say so and spend the effort on `/yt-package` instead.

## Before you write

1. Read `~/.claude/youtube/voice.md` if it exists. That is the user's voice profile: how they talk
   on camera, the words they never use, who they are talking to, what they will not claim. If it
   does not exist, ask for **three of their own videos**, read or transcribe them, infer the voice,
   and write the file. A script in the wrong voice is worse than no script, because they have to
   read it out loud.
2. Never invent a number, a result or a source. If a figure would strengthen it and you do not have
   one, ask for it or write the line without it.

# yt-shorts

A Short cut out of a long video is not a clip of the best moment. It is a moment that **survives
without the video around it**, which is a much smaller set.

## Picking

Read the transcript and find spans of 20-55 seconds where all three are true:

1. It opens on a complete thought. If the first sentence needs the previous minute, it is not a Short.
2. There is a turn in it - a claim, then something that complicates or proves it.
3. It ends on a line, not a trail-off.

Rank the candidates and show the user the top five with their timecodes and first line, so they can

# yt-viral

Raw view counts rank channel size, not ideas. This ranks by **multiple over each channel's own
median**, which is the only version of the question that is about the video.

```bash
python3 swipe.py collected.json --min 2.0
```

## Collecting the input

You need at least **four videos per channel** or a median means nothing, and the tool will skip the
channel and tell you it did. Collect them however the user prefers - `yt-dlp --flat-playlist -J`
against a channel URL is the fastest, the public page works, a manual list works.