creator

How do I analyze a raw video, find the best moments to insert cinematic b-rolls (~1.5 per minute of runtime), pick the strongest generation model per shot (Runway Gen-4.5 / Seedance 2.0 / HeyGen), and write highly detailed, artifact-safe generation prompts for each b-roll

the agent that answers this

cinematic b-roll placer & prompt writer. Analyze a raw video, find the best moments to insert cinematic b-rolls (~1.5 per minute of runtime), pick the strongest generation model per shot (Runway Gen-4.5 / Seedance 2.0 / HeyGen), and write highly detailed, artifact-safe generation prompts for each b-roll.

2 runsLast run 10h ago1 on a scheduleUpdated Jul 18v1

Cost: Free; on your own plan
Runs: On demand; or scheduled
Built from: 9 steps; 2 verified skills
Runs in: Claude or Codex; as you

what you get

A timestamped b-roll insertion plan: per slot — timecode, shot intent, chosen model with rationale, and a production-grade generation prompt engineered to avoid visual issues, delivered behind an approval gate before any render.

example result

illustrative

A finished run delivers: A timestamped b-roll insertion plan: per slot — timecode, shot intent, chosen model with rationale, and a production-grade generation prompt engineered to avoid visual issues, delivered behind an approval gate before any render.

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

9 steps · 2 from verified skills

Step 1tool
Preflight: before doing any work, make sure everything this agent needs is in place, so the run never fails halfway on a missing tool or an unconfigured account. Services and accounts (these need a key, login, or subscription, NOT auto-installed): Runway ML (usage-based (credits); get it at dev.runwayml.com; alternative: Seedance (via HeyGen) for image/video generation); HeyGen (free trial, then paid; get it at heygen.com); Seedance (via HeyGen credits; get it at heygen.com; alternative: Runway ML for image/video generation). Before the FIRST step that calls a paid service, verify its API key or login is configured. If one is missing, STOP and tell the user exactly what to sign up for, the link, and any cheaper alternative, instead of failing partway through a paid run.
Your model fills this step
Step 2
Ingest and transcribe the raw video into a timestamped transcript, and read total runtime, scene cuts, and aspect ratio
Your model fills this step
Step 3
Compute the b-roll budget from runtime (duration in minutes times the density, default 1.5 per minute) and map the narrative beats, dead-air pauses, and visually flat talking-head stretches where b-roll adds the most
Your model fills this step
Step 4
For each candidate slot, define the concrete shot intent — subject, setting, action, and how it should visually reinforce the spoken line at that timecode
Use when generating AI films, short dramas, cinematic sequences, or storyboard-driven video scenes that need strong cross-shot continuity and real film-langu...
--- name: chain-referenced-shortform-video description: Use when generating AI films, short dramas, cinematic sequences, or storyboard-driven video scenes that need strong cross-shot continuity and real film-language control. Covers…
Full skill: Chain-Referenced Shortform Video
Step 5decision
Select the best generation model per shot — Runway Gen-4.5 for hero/heavy-motion/VFX shots, Seedance 2.0 for bulk cinematic continuity b-roll, HeyGen for branded/avatar or in-editor shots — honoring the user's default_engine choice, with a one-line rationale each
Decision step
Step 6
Write a highly detailed, production-grade generation prompt for each b-roll — subject and action, camera movement and lens, lighting direction and color, mood/style to match the target look, aspect ratio, clip duration, and affirmative physics/anatomy guidance (detailed hands, anatomically correct, natural motion, no text warping) engineered so the model produces no visual artifacts
Seedance2 Video Generation Prompt Engineering — multimodal reference system, cinematic camera language, audio-video sync, and scene-by-scene prompt patterns...
--- name: seedance-2-prompt description: Seedance2 Video Generation Prompt Engineering — multimodal reference system, cinematic camera language, audio-video sync, and scene-by-scene prompt patterns for ByteDance's Seedance2 model. license:…
Full skill: Seedance2 Prompt Engineering
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
Step 8decision
Run a QA and consistency pass over every prompt: verify aspect ratio and duration match the source, flag artifact-prone elements (hands, faces, on-screen text, fast complex motion), confirm affirmative phrasing over negatives, and check continuity of look across all b-rolls
Decision step
Step 9decision
Assemble the final timestamped b-roll insertion plan (timecode, shot intent, chosen model, final prompt, QA notes) and present it for the user's approval before any b-roll is actually rendered
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 cinematic b-roll placer & prompt writer 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 analyze a raw video, find the best moments to insert cinematic b-rolls (~1.5 per minute of runtime), pick the strongest generation model per shot (Runway Gen-4.5 / Seedance 2.0 / HeyGen), and write highly detailed, artifact-safe generation prompts for each b-roll?

The cinematic b-roll placer & prompt writer agent. A timestamped b-roll insertion plan: per slot — timecode, shot intent, chosen model with rationale, and a production-grade generation prompt engineered to avoid visual issues, delivered behind an approval gate before any render.

Is the cinematic b-roll placer & prompt writer 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 cinematic b-roll placer & prompt writer 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 cinematic b-roll placer & prompt writer 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 cinematic b-roll placer & prompt writer 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 cinematic b-roll placer & prompt writer agent?

Install Implexa into your Claude or Codex, then say "build the cinematic b-roll placer & prompt writer agent" and approve the schedule. Implexa assembles the 9 steps (2 from verified skills) and it runs on its own. About 5 minutes to your first real run.

Can I change what the cinematic b-roll placer & prompt writer 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

v1Jul 18generated
auto-generated from "Analyze a raw video, find the best moments to insert cinematic b-rolls (~1.5 per"

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