# AI use cases for ChatGPT YouTube Agent Skill (Jakeschincariol/chatgpt-youtube-agent-skill) Repo: [Jakeschincariol/chatgpt-youtube-agent-skill](https://github.com/Jakeschincariol/chatgpt-youtube-agent-skill) | Use cases: 5 | Page: https://dedupedai.com/use-cases/jakeschincariol-chatgpt-youtube-agent-skill/ A set of eleven ChatGPT skills and six dependency-free Python scripts that help run a YouTube channel, from scripting and packaging to retention analysis and Shorts. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Write a video script and score its hook before filming: https://dedupedai.com/use-cases/jakeschincariol-chatgpt-youtube-agent-skill/script-and-score-hook/ - Find the exact second viewers leave a video: https://dedupedai.com/use-cases/jakeschincariol-chatgpt-youtube-agent-skill/find-retention-drop-second/ - Check a title and thumbnail together before upload: https://dedupedai.com/use-cases/jakeschincariol-chatgpt-youtube-agent-skill/lint-title-thumbnail-pair/ - Pull Shorts candidates out of a long video: https://dedupedai.com/use-cases/jakeschincariol-chatgpt-youtube-agent-skill/find-shorts-in-long-video/ - Rank what works in your niche by channel lift: https://dedupedai.com/use-cases/jakeschincariol-chatgpt-youtube-agent-skill/rank-niche-videos-by-lift/ ## How to write a video script and score its hook before filming with ChatGPT YouTube Agent Skill Repo: [Jakeschincariol/chatgpt-youtube-agent-skill](https://github.com/Jakeschincariol/chatgpt-youtube-agent-skill) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Draft a script from 21 hook formulas and score the opening before you record. **Who it is for:** A solo YouTube creator who wastes takes on intros that do not hold attention. **The problem:** A weak opening loses viewers in the first seconds, and a bad hook is often only noticed after the video is filmed. **The outcome:** A script built from a chosen hook formula, with a hook score to check before you record. ### Steps 1. Install the skills by pasting https://github.com/Jakeschincariol/chatgpt-youtube-agent-skill into ChatGPT and saying install skill, or run `git clone https://github.com/Jakeschincariol/chatgpt-youtube-agent-skill` then `cp -r chatgpt-youtube-agent-skill/skills/yt-* ~/.codex/skills/`. 2. Restart the app so the skills load. 3. Copy `templates/voice.md` to `~/.codex/youtube/voice.md` and fill it in, or send ChatGPT three of your own videos and say write my voice profile from these. 4. Ask the yt-script skill for a script on your topic using the hook formulas. 5. Run `python hookscore.py` on the opening lines to get a hook score before you film. (inferred, check the README) ### Prompt to paste into your agent ```text Using the chatgpt-youtube-agent-skill repo, run the yt-script skill on the topic and use the voice file at ~/.codex/youtube/voice.md. Return a script with an opening written from one of the 21 hook formulas and a hook score for that opening. Verify that the output includes both the script and the score before recording. ``` ### Caveat The README says nothing gets published until you upload it yourself, so the script and hook score are drafts you still need to review and film. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-chatgpt-youtube-agent-skill/script-and-score-hook/ ## How to find the exact second viewers leave a video with ChatGPT YouTube Agent Skill Repo: [Jakeschincariol/chatgpt-youtube-agent-skill](https://github.com/Jakeschincariol/chatgpt-youtube-agent-skill) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Read a retention export and name the second people left and what was said. **Who it is for:** A YouTube editor reviewing a published video whose audience keeps dropping off early. **The problem:** A retention graph shows that viewers left, but not which moment in the script caused it. **The outcome:** A list of drop-off points with the exact second and the matching line of speech, so you know what to fix in the next edit. ### Steps 1. Install the skills using the link or the git clone and copy commands in the README. 2. Restart the app. 3. Export the audience-retention data for the video from your channel. 4. Ask the yt-retention skill to read the export and name the seconds people left. 5. Run `python retention.py` on the export file for a local check of the drop points. (inferred, check the README) ### Prompt to paste into your agent ```text Using the chatgpt-youtube-agent-skill repo, run the yt-retention skill on the retention export at for the video . Expected output: a list of exact seconds where viewers left, each with the spoken words at that point. Verify that every listed second matches a timestamp present in the export. ``` ### Caveat The README describes the retention skill as reading your export, so its accuracy depends on the export containing per-second data and the matching transcript. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-chatgpt-youtube-agent-skill/find-retention-drop-second/ ## How to check a title and thumbnail together before upload with ChatGPT YouTube Agent Skill Repo: [Jakeschincariol/chatgpt-youtube-agent-skill](https://github.com/Jakeschincariol/chatgpt-youtube-agent-skill) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Lint the title and thumbnail as one pairing so they do not repeat each other. **Who it is for:** A creator who has a finished video and wants a stronger click surface before publishing. **The problem:** Titles and thumbnails written separately often say the same thing twice, which wastes part of the click surface. **The outcome:** A review of the title and thumbnail as a pair, with notes on repeated wording and gaps. ### Steps 1. Install the skills from the README link or with the git clone and copy commands. 2. Restart the app. 3. Paste your draft title and describe or attach your thumbnail. 4. Ask the yt-package skill to lint the title and thumbnail as one pairing. 5. Run `python title.py` on your title text for a quick local check. (inferred, check the README) ### Prompt to paste into your agent ```text Using the chatgpt-youtube-agent-skill repo, run the yt-package skill on the title and the thumbnail description . Expected output: a pairing review that flags any wording the title and thumbnail share. Verify that the review addresses both the title and the thumbnail. ``` ### Caveat The README covers linting the pairing but does not say the skill checks the thumbnail image itself, so describe it in words when you ask. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-chatgpt-youtube-agent-skill/lint-title-thumbnail-pair/ ## How to pull Shorts candidates out of a long video with ChatGPT YouTube Agent Skill Repo: [Jakeschincariol/chatgpt-youtube-agent-skill](https://github.com/Jakeschincariol/chatgpt-youtube-agent-skill) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Find the Shorts already hiding in a long video and cut dead air from the edit list. **Who it is for:** A creator with a long finished video who wants short clips for the Shorts feed. **The problem:** Strong short moments sit inside long videos and are slow to find by scrubbing through the timeline. **The outcome:** A list of Shorts candidates from the long video, plus an edit decision list with dead air flagged. ### Steps 1. Install the skills from the README link or the git clone and copy commands. 2. Restart the app. 3. Paste the transcript of the long video into the chat. 4. Ask the yt-shorts skill to find the Shorts candidates in the transcript. 5. Ask the yt-edit skill for an edit decision list, then (inferred) run `python deadair.py` on the transcript to flag dead air. (inferred, check the README) ### Prompt to paste into your agent ```text Using the chatgpt-youtube-agent-skill repo, run the yt-shorts skill on the transcript of and then the yt-edit skill on the same transcript. Expected output: a list of Shorts candidates with start and end points and an edit decision list with dead air flagged. Verify that each candidate's timestamps fall within the transcript. ``` ### Caveat The README says the skills write and you upload, so each Shorts candidate and cut still needs your own review and export before publishing. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-chatgpt-youtube-agent-skill/find-shorts-in-long-video/ ## How to rank what works in your niche by channel lift with ChatGPT YouTube Agent Skill Repo: [Jakeschincariol/chatgpt-youtube-agent-skill](https://github.com/Jakeschincariol/chatgpt-youtube-agent-skill) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Find niche videos that beat their own channel's average, not just the biggest channels. **Who it is for:** A new or mid-size creator choosing topics by looking at what is working in their niche. **The problem:** Sorting niche videos by view count favors large channels, which hides ideas that worked well for smaller creators. **The outcome:** A ranked list of niche videos ordered by how far each one beat its own channel. ### Steps 1. Install the skills from the README link or the git clone and copy commands. 2. Restart the app. 3. Name your niche in the chat. 4. Ask the yt-viral skill to find what is working in that niche and rank it by channel-relative lift. 5. Run `python swipe.py` to check the ranked list locally. (inferred, check the README) ### Prompt to paste into your agent ```text Using the chatgpt-youtube-agent-skill repo, run the yt-viral skill for the niche . Expected output: a list of videos ranked by how far each beat its own channel, with the lift shown for each. Verify that the ranking is based on channel-relative lift and not on channel size. ``` ### Caveat The README describes ranking by channel-relative lift but does not list the data sources the skill uses, so check what it reads before relying on the ranking. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-chatgpt-youtube-agent-skill/rank-niche-videos-by-lift/