Skip to content
archive

2026-06-14-ibuzovskyi-hermes-agent-video-skills

XFeed · · 1 min read

HERMES AGENT CAN CREATE VIDEOS — Three Bundled Video Skills Most People Skip

Author: @IBuzovskyi (YanXbt) Date: Jun 14, 2026 URL: https://x.com/IBuzovskyi/status/2066724948702626255 Engagement: 8.3K Views · 4 Replies · 4 Reposts · 92 Likes · 170 Bookmarks

Full Tweet Content

HERMES AGENT CAN CREATE VIDEOS. NOT WITH AN API CALL. IT WRITES THE CODE, RENDERS THE SCENES, AND STITCHES THEM INTO AN MP4.

the video attached to this post was generated by Hermes Agent using manim-video skill.

three bundled video skills most people skip:

1. MANIM VIDEO

Math-animated explainers. Algorithm visualizations, equation derivations, architecture diagrams, data stories.

The pipeline: PLAN → CODE → RENDER → STITCH → AUDIO → REVIEW

Hermes writes a plan.md with narrative arc and scene list. Then codes a Python script with one class per scene. Renders each scene through Manim CE. Stitches clips with ffmpeg. Adds voiceover if you want it.

Requirements:

  • Python 3.10+
  • Manim Community Edition v0.20+
  • LaTeX (texlive-full)
  • ffmpeg
  • No GPU needed

Draft quality: manim -ql "script.py"

Production quality: manim -qh "script.py"

2. HYPERFRAMES

Complement to manim-video. Use manim for math and algorithms. Use hyperframes for everything else:

  • Motion graphics
  • Talking-head with captions
  • Product tours
  • Social overlays
  • Shader transitions

Architecture:

  • HTML is the source of truth
  • GSAP timeline for animation
  • CSS for appearance
  • HyperFrames engine captures frame-by-frame and encodes to MP4 or WebM with ffmpeg

3. KANBAN VIDEO ORCHESTRATOR

The advanced play. A multi-agent video production pipeline backed by Hermes Kanban.

How it works:

  • Creates profiles for each video role
  • A director profile decomposes the project into kanban tasks
  • Renderer profiles pick up scenes and produce them
  • The orchestrator decides which skill fits each scene:
    • manim-video for math
    • hyperframes for motion graphics
    • p5js for generative art
    • blender-mcp for 3D
    • ascii-video for terminal aesthetics
  • One prompt. Multiple agents. One final video.

HOW TO USE

Enable any of these:

/skills search manim
/skills search hyperframes
/skills search video

Or ask directly:

"Create a 60-second explainer video about how the self-improvement loop works in Hermes Agent. Use manim style. Dark background, amber and teal accents."

Hermes writes the plan, codes every scene, renders, stitches, and delivers an MP4. You review and publish.

Comment "MANIM" and I'll send you the exact prompt I used to generate the video in this post.

FULL HERMES NIGHT MODE WORKFLOW

[Link to article: HERMES AGENT BUILDS ITSELF WHILE YOU SLEEP. THE COMPLETE GUIDE TO THE 9-HOUR OVERNIGHT WORKFLOW.]