How do I turn a raw talking-head video (e.g. a HeyGen avatar clip) into a polished, on-brand vertical reel with karaoke captions and rebuilt UI b-roll, then post it to Instagram
the agent that answers this
Raw talking-head video to on-brand reel. Turn a raw talking-head video (e.g. a HeyGen avatar clip) into a polished, on-brand vertical reel with karaoke captions and rebuilt UI b-roll, then post it to Instagram.
- Cost
- Free
- on your own plan
- Runs
- On demand
- or scheduled
- Built from
- 8 steps
- 7 verified skills
- Runs in
- Claude or Codex
- as you
the steps
8 steps · 7 from verified skills- Step 1
Transcribe the source talking-head video to word-level timings: extract its audio and run speech-to-text, producing per-word timestamps for karaoke-style captions.
Automate audio/video transcription, meeting notes, subtitle generation, and content processing
Transcription Automation Comprehensive skill for automating audio/video transcription and content processing. Core Workflows 1. Transcription Pipeline TRANSCRIPTION FLOW: ┌─────────────────┐ │ Audio/Video │ │ Input │ └────────┬────────┘ ▼…
Full skill: Transcription Automation - Step 2
Capture the real app or product screens referenced in the video using the browser, and rebuild them as clean on-brand motion-graphics components, logging provenance and redacting any private data.
Capture real product UIs (Vercel, Claude / Claude Code, Supabase, Stripe, GitHub, the Implexa dashboard, etc.) with Chrome MCP, then rebuild them as clean, on-brand, animated Remotion components for the @ImplexaAI reels — so a reel shows the ACTUAL stack instead of generic talking-head + text. Use when a reel beat references a product screen, when someone says "show the real app / dashboard / deploy screen", "capture the UI", "screenshot Vercel/Supabase/Stripe and put it in the reel", "our reels look generic — make them visual", or when producing the visual schedule for a Day-N reel. This is the visual layer that makes a reel informative AND visual.
--- name: app-ui-capture-to-remotion description: > Capture real product UIs (Vercel, Claude / Claude Code, Supabase, Stripe, GitHub, the Implexa dashboard, etc.) with Chrome MCP, then rebuild them as clean, on-brand, animated Remotion…
Full skill: app-ui-capture-to-remotion - Step 3
Build the vertical 1080x1920 reel composition in the brand video style: the talking-head video, word-synced karaoke captions, the rebuilt UI cards or b-roll dropped in at the right beats, and brand chrome like labels and an end badge.
Use this skill when creating Revenoid product/launch videos, social ads, or any motion content. Establishes the visual vocabulary (MCIP wordmark, concentric ring motif, Cowork chat surface, MCP tool-pill cascades, real-app browser tilts, type system, transition patterns) derived from the MCIP pitch deck and the Cowork product itself. Triggers — "make a Revenoid video", "build an ad", "build a launch trailer", "Remotion composition for", "30s vertical ad", "social cutout", "MCIP video", "MCP product video".
--- name: revenoid-video-style description: Use this skill when creating Revenoid product/launch videos, social ads, or any motion content. Establishes the visual vocabulary (MCIP wordmark, concentric ring motif, Cowork chat surface, MCP…
Full skill: revenoid-video-style - Step 4
Critique the cut like a top 1 percent editor: script, hook, pacing, delivery, caption sync, and on-brand-ness; fix clear problems and flag anything that should block before render.
This skill should be used when reviewing or editing copy to ensure adherence to Every's style guide. It provides a systematic line-by-line review process for…
Every Style Editor This skill provides a systematic approach to reviewing copy against Every's comprehensive style guide. It transforms Claude into a meticulous line editor and proofreader specializing in grammar, mechanics, and style…
Full skill: every-style-editor - Step 5tool
Render the composition to a final vertical MP4 file.
Combines GIFs and videos into composite tutorials with vertical or grid layouts via ffmpeg
--- name: media-composition description: | Combines GIFs and videos into composite tutorials with vertical or grid layouts via ffmpeg version: 1.9.8 triggers: - composition - ffmpeg - media - combine - stitch - tutorial - assembling…
Full skill: Nm Scry Media Composition- No integration? run the project remotion render script
- No integration? render the composition in HyperFrames
- Step 6
Produce the cover frame and the post copy: a humanized caption, a pinned first comment, and any cross-post variants.
Use when the user has one or more video clips and wants to add post-production on top — AI-generated cover as first frame, HTML/CSS captions synced to SRT, k...
--- name: wjs-overlaying-video description: Use when the user has one or more video clips and wants to add post-production on top — AI-generated cover as first frame, HTML/CSS captions synced to SRT, kinetic illustration overlays at hook…
Full skill: Wjs Overlaying Video - Step 7decision
Review the final reel and caption together before anything is posted.
Decision step - Step 8tool
Post the reel to Instagram as the configured handle as a Reel with the caption, then add the pinned first comment.
Full pipeline to turn a video podcast episode into Instagram content (carousel posts, quote cards, and Reels). Transcribes the episode, extracts key quotes w...
--- name: episode-to-instagram version: 1.0.1 description: Full pipeline to turn a video podcast episode into Instagram content (carousel posts, quote cards, and Reels). Transcribes the episode, extracts key quotes with timestamps, pulls…
Full skill: Openclaw Skills- No integration? open the Instagram composer and upload the reel plus caption manually
- No integration? schedule it via Meta Business Suite
common questions
How do I turn a raw talking-head video (e.g. a HeyGen avatar clip) into a polished, on-brand vertical reel with karaoke captions and rebuilt UI b-roll, then post it to Instagram?
The Raw talking-head video to on-brand reel agent. a rendered 1080x1920 reel with word-synced captions, on-brand visuals, a cover and caption, posted to Instagram after your approval
Is the Raw talking-head video to on-brand reel 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 Raw talking-head video to on-brand reel 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 Raw talking-head video to on-brand reel 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 Raw talking-head video to on-brand reel 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 Raw talking-head video to on-brand reel agent?
Install Implexa into your Claude or Codex, then say "build the Raw talking-head video to on-brand reel agent" and approve the schedule. Implexa assembles the 8 steps (7 from verified skills) and it runs on its own. About 5 minutes to your first real run.
Can I change what the Raw talking-head video to on-brand reel 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 5generated
auto-generated from "Turn a raw talking-head video (e.g. a HeyGen avatar clip) into a polished, on-br"
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
- 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
cinematic b-roll placer & prompt writer
- 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