creator

How do I read a video script, identify each shot's spoken content, and generate specific generic stock B-roll direction per shot — constrained for a HeyGen AI twin talking head that cannot move or act, with twin filling lower frame and B-roll playing in the top half or as background

the agent that answers this

B-Roll Director for AI Twin Videos. Read a video script, identify each shot's spoken content, and generate specific generic stock B-roll direction per shot — constrained for a HeyGen AI twin talking head that cannot move or act, with twin filling lower frame and B-roll playing in the top half or as background

1 runLast run 23h ago1 on a scheduleUpdated Jun 26v1

Cost: Free; on your own plan
Runs: On demand; or scheduled
Built from: 7 steps; 1 verified skills
Runs in: Claude or Codex; as you

what you get

A shot-by-shot B-roll direction document with cinematic stock-footage prompts (tagged PRESENT or ARCHIVAL), twin-only flags for hook/sign-off shots, and overlay notes — ready to feed into an AI video generator or stock footage search

example result

illustrative

A finished run delivers: A shot-by-shot B-roll direction document with cinematic stock-footage prompts (tagged PRESENT or ARCHIVAL), twin-only flags for hook/sign-off shots, and overlay notes — ready to feed into an AI video generator or stock footage search

Example output, to show the shape of the deliverable. It has not run on your data. Build the agent to get this on yours.

the steps

7 steps · 1 from verified skills

Step 1tool
Read the input script file and extract the full shot list with spoken VO text for each shot section
Local Video Ad Pipeline v0.5 is a public OpenClaw skill for producing short commercial videos and YouTube Shorts with local AI models. It uses a local LLM as...
--- name: local-video-ad-pipeline-v05-public description: "Local Video Ad Pipeline v0.5 is a public OpenClaw skill for producing short commercial videos and YouTube Shorts with local AI models. It uses a local LLM as the full film…
Full skill: Local Video Ad Pipeline v0.5
- No integration? Paste the script text directly into the chat
Step 2
Classify each shot as TWIN ONLY, B-ROLL PRESENT (modern full color), or B-ROLL ARCHIVAL (vintage sepia/B&W with date stamp) based on the spoken content and time period referenced
Your model fills this step
Step 3
For each non-twin-only shot, write a specific cinematic B-roll direction prompt: generic stock or AI-generated footage only, no identifiable people, no AI twin performing actions, no personal photos — PRESENT shots are modern full-color cinematic, ARCHIVAL shots are sepia or B&W with a visible date stamp overlay
Your model fills this step
Step 4
Flag any shot that needs a graphic overlay (badge, handle card, map line) and write the overlay spec separately from the footage prompt
Your model fills this step
Step 5decision
Review the generated B-roll direction document — confirm each shot has the right track tag (TWIN ONLY / PRESENT / ARCHIVAL), the prompts are constraint-compliant, and overlays are correctly noted
Decision step
Step 6
Render the final B-roll direction as a formatted markdown file with shot number, timecode estimate, VO excerpt, track tag, B-roll prompt, and overlay spec per section
Your model fills this step
Step 7decision
Quality gate: adversarially critique the deliverable produced by the prior steps, from three lenses (a domain expert, a hard skeptic, and the end user). Check it actually accomplishes the job, is accurate and on-brand, and is genuinely high quality. Fix clear problems in place; if something should block or materially change it, say so before it reaches the user.
Decision step

runs hands-free with

Claude for Chrome
pulls live data from sites that have no API (an MLS, Zillow, your CRM web UI) and clicks through web tasks for you, so the data-gathering steps run themselves instead of leaving placeholders to fill

Connect these and the agent gathers its own data and delivers on a schedule, instead of leaving you blanks to fill.

Run this agent in Implexa, on your own Claude or Codex, free

Get the Implexa app (or connect your Claude Code / Codex), then say build the B-Roll Director for AI Twin Videos agent and approve the schedule. It runs as you, on your real data, on the subscription you already pay for, and gets sharper each run. Your agent's memory is yours and travels with you across Claude, Codex, and whatever comes next. About 5 minutes to your first real run.

Run this agent in Implexa →

common questions

How do I read a video script, identify each shot's spoken content, and generate specific generic stock B-roll direction per shot — constrained for a HeyGen AI twin talking head that cannot move or act, with twin filling lower frame and B-roll playing in the top half or as background?

The B-Roll Director for AI Twin Videos agent. A shot-by-shot B-roll direction document with cinematic stock-footage prompts (tagged PRESENT or ARCHIVAL), twin-only flags for hook/sign-off shots, and overlay notes — ready to feed into an AI video generator or stock footage search

Is the B-Roll Director for AI Twin Videos agent free?

Yes. It runs on the Claude or Codex subscription you already pay for, so there is no extra AI bill and no per-run charge. You can build and run unlimited agents on the free plan.

How often does the B-Roll Director for AI Twin Videos agent run?

You choose: run it on demand, or put it on a schedule (hourly, daily, weekly). Once scheduled it runs unattended, as you, on your own machine.

What does the B-Roll Director for AI Twin Videos agent need to run?

Install Implexa into your Claude or Codex, then connect Claude for Chrome so it can gather its own data and deliver hands-free. Implexa never touches your accounts or credentials.

Does the B-Roll Director for AI Twin Videos agent use my data? Is it private?

It runs as you, on your own machine, on your real data. The model runs inside your own Claude or Codex, so Implexa never sees your data, accounts, or credentials. Your agent's memory is yours and travels with you across Claude, Codex, and whatever comes next.

How do I build the B-Roll Director for AI Twin Videos agent?

Install Implexa into your Claude or Codex, then say "build the B-Roll Director for AI Twin Videos agent" and approve the schedule. Implexa assembles the 7 steps (1 from verified skills) and it runs on its own. About 5 minutes to your first real run.

Can I change what the B-Roll Director for AI Twin Videos agent does?

Yes. Tell it what to change in plain language and it revises its steps; the next scheduled run uses the change, with no re-scheduling. Every change is versioned, and a run can even propose its own improvements.

changelog

v1Jun 26generated
auto-generated from "Read a video script, identify each shot's spoken content, and generate specific "

Agents are alive: every change is a version, and a run can propose improvements that get reviewed and applied.