How do I take existing b-roll clips and Remotion text-animation files plus a presenter video, combine all elements into one finished YouTube video, and have a judge verify the b-rolls, animated text content, and their timing all match what the presenter is saying before finalizing

the agent that answers this

Remotion b-roll + text-animation video assembler (judge-verified). Take existing b-roll clips and Remotion text-animation files plus a presenter video, combine all elements into one finished YouTube video, and have a judge verify the b-rolls, animated text content, and their timing all match what the presenter is saying before finalizing.

• 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. Command-line tools (free, auto-install only if missing; idempotent, later runs find them present): Remotion - npx remotion versions (auto-fetches), or `npm i remotion` in the project.

  Your model fills this step
• Step 2tool

  Collect and validate all inputs — the presenter video, the b-roll clips, and the Remotion text-animation project; confirm each exists and probe duration, resolution, fps and audio with ffprobe so the assembly targets are known

  Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include…

  FFmpeg for Video Production FFmpeg is the essential tool for video/audio processing. This skill covers common operations for Remotion video projects. Quick Reference GIF to MP4 (Remotion-compatible) ffmpeg -i input.gif -movflags faststart…

  Full skill: ffmpeg

  • No integration? Ask the user for the missing file path and hold as needs-input
  • No integration? Accept a manifest text file listing clip paths
• Step 3tool

  Transcribe the presenter's audio into a timestamped transcript (word/segment level) so every element can be aligned to what the presenter is actually saying

  Local speech-to-text with the Whisper CLI (no API key).

  --- name: openai-whisper-hardened description: Local speech-to-text with the Whisper CLI (no API key). homepage: https://openai.com/research/whisper metadata: { "openclaw": { "emoji": "🎙️", "requires": { "bins": ["whisper"] }, "install":…

  Full skill: Openai Whisper Hardened

  • No integration? Use an existing SRT/VTT the user supplies
  • No integration? Use HyperFrames transcribe CLI
• Step 4

  Build the edit timeline: map each b-roll clip and each Remotion text-animation composition to a start/end time window aligned to the transcript, so every element covers the line it illustrates

  Use this skill to produce a Remotion short video through an audio-driven pipeline: script → audio → SRT → timeline → scenes.json → render → CapCut handoff, w...

  --- name: remotion-video-pipeline description: > Use this skill to produce a Remotion short video through an audio-driven pipeline: script → audio → SRT → timeline → scenes.json → render → CapCut handoff, with human gates. Delegates…

  Full skill: Remotion Video Pipeline
• Step 5tool

  Render the Remotion text-animation compositions to video with an alpha channel at the timings from the timeline, so the animated text overlays are ready to composite

  Your model fills this step

  • No integration? Render each composition via the Remotion CLI (npx remotion render)
  • No integration? Pre-rendered overlay files supplied by the user
• Step 6tool

  Composite everything into a single video: lay the presenter as the base track, cut in the b-rolls at their windows, and overlay the rendered text animations, exporting at the chosen YouTube format and fps

  Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include…

  ↳ same skill as step 2 (ffmpeg)

  Full skill: ffmpeg

  • No integration? Assemble with a HyperFrames composition
  • No integration? Use an editing library / NLE render
• Step 7

  Judge verification: an LLM judge reviews the assembled video against the presenter transcript and checks that each b-roll matches the topic being spoken, each animated text overlay's wording is correct, and every element's timing lines up with the presenter; output a pass/fail with a specific list of mismatches to fix

  Critique a finished @ImplexaAI reel (and its script) the way a top-1% short-form video editor would — brutally and specifically. Catches AI-sounding delivery (letter-by-letter reads like "D.M."/"U.R.L.", robotic abbreviations, awkward spoken seams), clumsy phrasing, weak hooks, pacing/dead-air, caption-sync and overlay problems, AND content gaps (a key message the reel should make but doesn't — e.g. "you can build/deploy this with a prompt in Claude Code or Codex"). Use as the final QC gate before posting any reel, when someone says "critique this reel / video like a real editor", "what's weak about this", "does the script land", "why does this sound AI", or to review a reel script before the avatar is rendered.

  --- name: reel-editor-critique description: > Critique a finished @ImplexaAI reel (and its script) the way a top-1% short-form video editor would — brutally and specifically. Catches AI-sounding delivery (letter-by-letter reads like…

  Full skill: reel-editor-critique
• Step 8

  If the judge failed, apply its correction list (re-time or swap b-rolls, fix text wording/timing, re-render the affected overlays) and re-composite, then re-submit to the judge; loop until the judge passes

  Implement a task with automated LLM-as-Judge verification for critical steps

  Implement Task with Verification Your job is to implement solution in best quality using task specification and sub-agents. You MUST NOT stop until it critically neccesary or you are done! Avoid asking questions until it is critically…

  Full skill: implement-task
• Step 9decision

  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 10decision

  Final human approval gate: present the judge-passed video and verification report for the user to approve, then export the final YouTube MP4 or upload to YouTube per their choice

  Decision step

common questions

1. v1Jul 17generated

   auto-generated from "Take existing b-roll clips and Remotion text-animation files plus a presenter vi"

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

related agents

• 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

  B-Roll Director for AI Twin Videos

• on-demandcreator

  How do I take a raw source video plus an instruction markdown file and generate a set of cinematic b-roll clips with the Runway ML API, guided by the style and shot direction in the instructions

  cinematic b-roll generator

• dailycreator

  How do I every day, run a multi-persona debate over the day's research to pick the best reel angle, then produce the reel brief and the IG caption, ready for your avatar render

  Daily IG reel: debate and brief

• dailycreator

  How do I produce my daily on-brand vertical IG reel end to end — research the day's angle, write the avatar script, generate the avatar video, render it with captions, and prep the caption + guide link, held for my approval before posting

  Daily IG reel: produce and render