How do I generate a finished concept-animation MP4 for a raw video using the user's provided reference video and brand style. Use full-screen or half-screen explanatory animations when they clarify concepts, reserve simple text-only treatments for basic emphasis, and avoid persistent presenter/name overlays; mention only "Sanna" when the presenter explicitly introduces herself or the script requires it

the agent that answers this

Brand-Style Concept Animation Video Producer. Generate a finished concept-animation MP4 for a raw video using the user's provided reference video and brand style. Use full-screen or half-screen explanatory animations when they clarify concepts, reserve simple text-only treatments for basic emphasis, and avoid persistent presenter/name overlays; mention only "Sanna" when the presenter explicitly introduces herself or the script requires it.

• Step 1tool

  Ingest the raw video and any attached reference video, then extract duration, audio, transcript, visible scene changes, speaker beats, candidate emphasis moments, and reference-video animation patterns.

  Your model fills this step

  • No integration? If automated transcription fails, ask the user for a transcript or SRT file.
  • No integration? If scene detection fails, use transcript pacing and audio emphasis only.
  • No integration? If the reference video is missing, record needs-input naming the exact reference video required instead of guessing the style.
• Step 2

  Infer the author's brand and motion style from the reference video and optional style guide, including typography, colors, animation timing, layout density, caption conventions, and when to use concept animation instead of bare text.

  Your model fills this step
• Step 3decision

  Choose the exact animation moments from the transcript and pacing, classifying each as full-screen concept animation, half-screen concept animation, footage-integrated callout, or simple text-only emphasis; prefer explanatory animations whenever the concept needs visual teaching, and keep text-only treatment only for basic phrases.

  Decision step
• Step 4decision

  Apply presenter/name rules: do not keep a persistent "Sanna Jain" overlay anywhere; use no name label by default, and use only "Sanna" briefly if the presenter introduces herself or the script context genuinely requires it.

  Decision step
• Step 5tool

  Generate or prepare supplemental visual assets needed for the explanatory animation plan: abstract concept scenes, product/process diagrams, callouts, b-roll plates, masks, cropped footage regions, and brand-safe motion backgrounds for full-screen and half-screen sequences.

  Your model fills this step

  • No integration? If Runway API access is unavailable, skip generated b-roll and rely on Remotion-native shapes, masks, text, diagrams, footage crops, and image assets.
  • No integration? If Runway browser rendering is used and the artifact is still processing, record a partial Needs You handoff with the render URL and required download destination.
• Step 6tool

  Create or prepare any presenter treatment only when needed by the script: use the original presenter footage or approved avatar source without obscuring the concept animation, and do not add a persistent name/title overlay.

  Your model fills this step

  • No integration? If HeyGen is unavailable, use the original talking-head footage as presenter source and add Remotion-framed presenter treatment only where needed.
  • No integration? If a browser render is submitted but not downloadable yet, record a partial Needs You handoff with the HeyGen project URL, expected local destination, and next download instruction.
• Step 7tool

  Preflight immediately before dependency-using steps: confirm local video paths, reference video path, transcript availability, output destination, and rendering dependencies. For Remotion, run `npx remotion versions` or install `remotion` in the project only if needed and safe.

  Your model fills this step

  • No integration? If a required local file is missing, record needs-input naming the exact file instead of searching outside the workspace.
  • No integration? If Remotion is not available and cannot be installed safely, ask for an existing Remotion project path or approval path.
• Step 8tool

  Build the Remotion composition: import the raw video, reference-derived style rules, animation plan, presenter assets if any, captions, and supporting media; implement deterministic full-screen and half-screen concept-animation components plus simple text-only components for basic moments, then render the requested MP4.

  |

  Programmatic video creation with React components, animations, and audio synchronization. Compose videos using React components with frame-based animation via useCurrentFrame() and interpolate() for precise timing and motion control…

  Full skill: remotion-video

  • No integration? If a repository already contains a Remotion project, add the composition into the existing structure.
  • No integration? If no project exists, create a minimal local Remotion composition in the workspace and render with npx remotion render.
  • No integration? If Remotion is not installed, ask the user to approve dependency installation or provide an existing Remotion project path.
• Step 9tool

  Verify the rendered video against the raw video, transcript, and reference video: check that concept moments are explained with full/half-screen animation where appropriate, simple text-only treatments are used only for basic text, brand style matches the reference, captions and overlays are readable, timing is correct, and no persistent "Sanna Jain" overlay remains.

  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

  • No integration? If visual QA flags overlap, unreadable text, wrong style, missing concept animation, or prohibited name overlay, revise the Remotion composition and re-render before presenting the result.
• Step 10decision

  Quality gate: adversarially critique the deliverable from a video strategist, motion designer, and viewer perspective. Confirm the animation choices teach the underlying concepts rather than merely decorating the transcript; fix clear problems in place before delivery.

  Decision step
• Step 11decision

  Voice Pass: before showing user-facing notes, rewrite the delivery summary, animation plan, and QA notes in concise natural language. Preserve concrete timestamps, file paths, decisions, and issues; remove generic praise, inflated claims, chatbot artifacts, and unsupported assertions.

  Decision step
• Step 12decision

  Present the final MP4, animation plan, and QA report for human approval before any posting, publishing, or reuse.

  Decision step

common questions

1. v2Jul 25manual

   added 1 step; rebound step 4 (gap -> decision), step 7 (skills.sh/remotion-video -> gap), step 8 (implexa/reel-editor-critique -> skills.sh/remotion-video), and more

2. v1Jul 25generated

   auto-generated from "Generate text animations for a raw video using Remotion and other internal tools"

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

related agents

• on-demandvideo-production

  How do I take detailed md file instructions and an input youtube video then generate detailed high quality remotion text/image animations using the prompt and instructions (if prompts don't exists create them) then place them exactly during in the right spots (when a presenter starts talking about it, to when the presenter finishes it)

  YouTube Remotion Overlay Animator

• 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

• dailybuilder

  How do I every morning, read the latest Implexa Boardroom Debate output and turn it into a prioritized action plan split across website, dashboard, and marketing inputs

  Boardroom Debate → Daily Action Plan

• weeklybuilder

  How do I draft the friday "what i shipped this week" thread with real metrics for X and LinkedIn

  build-in-public weekly thread