Hire an AI long video editing planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A timed list of pauses, filler lines and retakes to cut
• A chapter list for the description that YouTube will show
• Five short clips (fewer if fewer stand alone) with start and end times and a new first line each
• On-screen text for the first two seconds of each clip

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: You record long videos where you talk to camera and want them tighter.

• Step 1: Cut list. Each pause, filler line and retake to cut, with its time, a short reason and the time saved.
• Step 2: Final transcript. The transcript of the cut video you uploaded, with times that match the final version.
• Step 3: Chapters. A block to paste in your description, starting at 00:00 and checked against YouTube's rules.
• Step 4: Five shorts. Start and end times, a new first line and on-screen text for each of five clips.
• Hand-back summary. Each step's file, any step not run and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order. Step 2 used the cut video, not the step 1 cut list, and steps 3 and 4 both used the step 2 transcript.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• List the cuts. Reads your raw transcript and marks pauses, filler lines and restarted sentences, each with a time and a short reason.
• Edit and upload (you). You make the cuts in your editor, export the video and upload it. The times change after cutting, so the next steps use the new version.
• Read the final transcript. Reads the captions of the video you uploaded through TranscriptAPI, which needs a key. The free credits cover a first transcript. Or paste the captions from YouTube Studio and skip the key.
• Write the chapters. Reads the final transcript, finds where the topic shifts and writes a chapter list that starts at 00:00, has at least three chapters and none under ten seconds.
• Pick five shorts. Reads the same final transcript, not the chapters. Finds moments of 20 to 55 seconds that open on a full thought and end on a strong line, then writes a new first line, on-screen text and a loop point for each.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id cut-chapter-and-clip-a-long-video-into-five-shorts only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/cut-chapter-and-clip-a-long-video-into-five-shorts/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The transcript of your raw recording, with times
• The link to the video after you cut and upload it, or its captions pasted from YouTube Studio
• A TranscriptAPI key if you use the link (100 free credits, no card, 1 credit per transcript)
• Your channel topic, so first lines fit (optional)

Tools and access

• Claude, ChatGPT or Gemini: Any chat AI works. Paste the transcript in. No code runs.

Functions and deliverables

• Long video editing planner: Plan cuts for a long video, then use its final timing to write chapters and choose five short-clip ideas.
  • A timed list of pauses, filler lines and retakes to cut
  • A chapter list for the description that YouTube will show
  • Five short clips (fewer if fewer stand alone) with start and end times and a new first line each
  • On-screen text for the first two seconds of each clip
• Dead air and retake cutter: Give it your recording transcript. Get a timed list of pauses, fillers and retakes to cut.
  • Timed cut list
  • Labels for dead air, filler and repeats
  • Estimated time saved
  • JSON version for tools (optional)
  Source: Jake Schincariol.
• YouTube transcript and channel collector: Give it a video or channel. Get transcripts, video lists and new uploads. Collects data from websites.
  • A timestamped transcript
  • A list of matching videos
  • The latest uploads with views and dates
  • Search hits inside a channel
  Source: Alireza Rezvani.
• YouTube chapter writer: Turn an SRT transcript into a chapter list with short titles and timestamp rule checks.
  • A valid chapter list starting at 00:00
  • A rule check that it will work on YouTube
  • Rewritten five-word chapter titles
  • A flag on any section that is two sections or filler
  Source: Jake Schincariol.
• Shorts clip finder: Share a long video transcript. Get the best five moments to clip, each with a new first line.
  • Five ranked clip moments with start and end timecodes
  • A new first line for each clip
  • On-screen text for the first two seconds
  • A loop point for each clip
  • A crop note for vertical video
  Source: Jake Schincariol.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one

Tasks you can use it for

• You record long videos where you talk to camera and want them tighter.
• Your video has no chapters, so viewers can't jump to the part they want.
• You want shorts from a long video but don't know which moments will stand alone.

Limits to check before starting

• Your video is only a few minutes long: skip chapters and pick clips by hand in your editor.
• Your recording is a screen capture with no speech: a transcript has nothing to read, so mark the cuts yourself.
• You want ad shots, not shorts from a talking video: use the Video ad shot list maker.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste the transcript of your raw recording. Apply the cut list in your editor, then upload the new version.
• Give it the link to the uploaded video and your TranscriptAPI key, or paste its captions from YouTube Studio. It picks up from there.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/cut-chapter-and-clip-a-long-video-into-five-shorts for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.