Communitygithub.com

ahmedsakri/youtube-agent-pro

>- Place end screens and cards where they keep the session going instead of ending it - the right next video, at the right second, read off the retention curve. Use for "end screen", "cards", "what plays next", "where do I put cards", "keep people on my channel", or routing viewers between videos.

Was ist youtube-agent-pro?

youtube-agent-pro is a Claude Code agent skill that >- Place end screens and cards where they keep the session going instead of ending it - the right next video, at the right second, read off the retention curve. Use for "end screen", "cards", "what plays next", "where do I put cards", "keep people on my channel", or routing viewers between videos.

Funktioniert mit✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/ahmedsakri/youtube-agent-pro/tree/HEAD/openai/skills/yt-endscreen

In Ihrer bevorzugten KI fragen

Öffnet einen neuen Chat, in dem dieser Agent-Skill bereits geladen ist.

Dokumentation

yt-endscreen

Read the shared operating guide for profile lookup, helper paths, capability limits, and cross-skill routing before using this workflow.

An end screen can guide viewers to a relevant next video. Choose by continuity and observed viewer behavior rather than assuming the newest upload is best. Verify current feature eligibility before giving implementation steps. Shorts need a Shorts-appropriate related-video or spoken CTA plan; do not assume long-form end screens/cards are available in the Shorts feed.

Pair it with $yt-retention - the retention curve says where the viewer still is at the end, and whether a card mid-video would catch a leak or cause one.

Before you place

  1. Use the available voice profile or creator context (see the operating guide) for the close - the end screen has a spoken hand-off, and "one ask, not three" is the rule from $yt-script applied here too.
  2. If there is a retention export, read it first ($yt-retention). The end-screen timing is only as good as knowing how many viewers are left to see it.

The rules

  • End screen: the last 5-20 seconds. Point it at the video that continues the thought, not the newest upload. The best next video is the one a viewer who just finished this one would choose - a part 2, the thing this one referenced, the obvious next question.
  • Lead with watch, not subscribe. One video element and one subscribe element is the ceiling. If the video did its job, the next-video click is worth more than the subscribe ask, and it earns the subscribe anyway.
  • Hold something back for it. The last 20 seconds need a reason to stay - do not fully resolve before the end screen or there is nothing left to hold the viewer through it. A flat outro is where the final cliff is.
  • Cards: at a leak, not at a peak. A card mid-video catches viewers who are about to leave anyway - place it just before a known drop-off from the retention curve, never over a peak where it only distracts a viewer who was staying.

The move

  • From the retention curve, find the end-screen window (how many viewers remain) and any mid-video leak a card could catch.
  • Pick the next video by continuity, not recency.
  • Write the spoken hand-off (one ask) and the end-screen layout.
  • Place 0-2 cards, each at a leak, each pointing somewhere relevant.

What to hand back

  • the end-screen pick (which video, why), with the spoken hand-off line
  • the end-screen layout (video + subscribe), and the seconds to place it
  • the card placements (timecode + target), or "none - no leak worth a card"
  • one line: the single routing change most likely to lift session time

Individual skills in this repo

This repo contains 9 individual skills — each has its own dedicated page.

ahmedsakri/youtube-agent-pro

>- Analyze YouTube Studio data for Shorts or long-form videos, distinguish traffic surfaces, and identify evidence-backed performance hypotheses. Use for "read my analytics", "which video worked", "my views dropped", "what's my CTR telling me", or a pasted Studio export.

ahmedsakri/youtube-agent-pro

>- Audit a YouTube channel end to end - packaging, consistency, the first fifteen seconds, and what to fix first. Use for "audit my channel", "why isn't my channel growing", "review my videos", or a pasted channel URL.

ahmedsakri/youtube-agent-pro

>- Turn a script or an idea into a production brief you can shoot from - the shot list, the b-roll, the on-screen moments, the gear, and a runtime budget that keeps the edit from sprawling. Use for "shot list", "production brief", "how do I film this", "what b-roll do I need", or planning a shoot before recording.

ahmedsakri/youtube-agent-pro

>- Draft YouTube chapters from a timestamped transcript and check basic timestamp constraints before the creator uses them. Use for "add chapters", "timestamps", "break this video into sections".

ahmedsakri/youtube-agent-pro

>- Find the right channels to collaborate with and write the pitch that gets a reply - matched by audience overlap and size band, not by fandom. Use for "find a collab", "who should I collaborate with", "collab pitch", "reach out to other creators", or growing through other channels.

ahmedsakri/youtube-agent-pro

>- Draft replies to YouTube comments in the creator's voice, triaged by which ones are worth answering. Use for "reply to my comments", "handle the comment section", "someone asked X", or a pasted comment thread.

ahmedsakri/youtube-agent-pro

>- Turn a raw recording's transcript into an edit decision list - dead air, filler cues and retakes, with timecodes. Use for "edit this", "cut the dead space", "tighten this video", "I rambled", or any request to shorten footage from a transcript.

ahmedsakri/youtube-agent-pro

>- Fix the channel page and the subscriber conversion - the trailer, the above-the-fold, the sections, and the one video that converts browsers into subscribers. Use for "my channel page", "people watch but don't subscribe", "channel trailer", "subscriber conversion", or "optimise my homepage".

ahmedsakri/youtube-agent-pro

>- Turn a niche or a blank page into video ideas that are searchable, specific and bigger than the channel - each one scored before it costs a week of filming. Use for "what should I make", "I have no idea what to post", "give me video ideas", "ideas for my channel", or when a creator is staring at an empty upload schedule.

Verwandte Skills