agentleFS
wangge-aiwangge-ai/wangge-skills/skills/manim-hyperframes-video/SKILL.md

manim-hyperframes-video

Skill4 starsChanged 36 days agoMITView on GitHub

Use when a video needs precise technical explanation visuals with Manim

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 7 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this as the specialized layer for technical explainer videos.

    line 14
  2. Very specific:

    If none exists, use video-producer-core to create one.

    line 28
  3. Distinctive:

    Use Manim for exact logic: formulas, block splitting, replicas, routing, queues, latency, graphs, architecture.

    line 32
  4. Distinctive:

    Keep each Manim scene to one concept and usually 5-15 seconds.

    line 33
  5. Distinctive:

    Use HyperFrames for pacing, subtitles, cards, scene transitions, title resets, sound effects, and final assembly.

    line 37
  6. Distinctive:

    Treat HyperFrames as the master timeline.

    line 38
  7. Distinctive:

    Use AI/B-roll for visual texture, not for precise labels or technical correctness.

    line 41
  8. Distinctive:

    Avoid copyrighted clips, platform logos, and copied frames unless the user owns them.

    line 43
  9. Very specific:

    Run lint, validate, inspect, ffprobe, and representative frame checks.

    line 48
  10. Very specific:

    Run Manim through the environment where it is installed.

    line 52
  11. Very specific:

    If HyperFrames bundled Chrome fails, set HYPERFRAMES_BROWSER_PATH to a local Chrome executable.

    line 55
  12. Very specific:

    If model-based TTS fails, use Windows SAPI as a temporary Chinese narration fallback through video-producer-core.

    line 56
  13. Very specific:

    Read references/workflow-template.md for a technical storyboard template, folder structure, and Manim/HyperFrames scene patterns.

    line 91

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Manim + HyperFrames Technical Explainer

Overview

Use this as the specialized layer for technical explainer videos. It is not a general video generator; use video-producer-core first for broad video planning, then use this skill when the video needs deterministic diagrams, formulas, system flows, or Manim + HyperFrames implementation.

Division of Labor

LayerResponsibility
video-producer-coreBrief, script, storyboard, asset plan, audio plan, render verification
ManimFormulas, data blocks, arrows, graphs, system mechanics, deterministic technical motion
HyperFramesMaster timeline, captions, title cards, callouts, AI/B-roll, transitions, audio tracks, final render
AI/B-rollAtmosphere and context: data centers, chips, devices, hard drives, product shots

Workflow

  1. Start from a storyboard
    • If none exists, use video-producer-core to create one.
    • Mark each beat as Manim, HyperFrames, AI/B-roll, screen recording, or mixed.
  2. Choose Manim beats
    • Use Manim for exact logic: formulas, block splitting, replicas, routing, queues, latency, graphs, architecture.
    • Keep each Manim scene to one concept and usually 5-15 seconds.
    • Render transparent WebM when it will sit over HyperFrames backgrounds.
  3. Choose HyperFrames beats
    • Use HyperFrames for pacing, subtitles, cards, scene transitions, title resets, sound effects, and final assembly.
    • Treat HyperFrames as the master timeline. Do not put the whole video in Manim unless it is purely mathematical.
  4. Generate or collect assets
    • Use AI/B-roll for visual texture, not for precise labels or technical correctness.
    • Record all generated prompts in the project.
    • Avoid copyrighted clips, platform logos, and copied frames unless the user owns them.
  5. Build and verify
    • Render Manim atoms first.
    • Compose in HyperFrames.
    • Run lint, validate, inspect, ffprobe, and representative frame checks.

Windows Pitfalls

  • Run Manim through the environment where it is installed. If Manim is in .venv, use .venv\Scripts\manim.exe.
  • MathTex requires LaTeX/MiKTeX on PATH.
  • PowerShell scripts containing Chinese should be saved as UTF-8 with BOM for Windows PowerShell 5.1.
  • If HyperFrames bundled Chrome fails, set HYPERFRAMES_BROWSER_PATH to a local Chrome executable.
  • If model-based TTS fails, use Windows SAPI as a temporary Chinese narration fallback through video-producer-core.

Commands

# Manim transparent atom
manim -ql -t --format=webm manim/scene.py SceneName -o scene_name

# HyperFrames checks
npx hyperframes lint
npx hyperframes validate
npx hyperframes inspect --samples 15

# HyperFrames draft render
$env:HYPERFRAMES_BROWSER_PATH='C:\Program Files\Google\Chrome\Application\chrome.exe'
npx hyperframes render --quality draft --output renders/draft.mp4

# Final file probe
ffprobe -v error -show_entries stream=index,codec_type,codec_name,width,height,avg_frame_rate,duration -show_entries format=duration,size -of json renders/draft.mp4

Output Expectations

For a complete technical explainer job, produce:

  • Script and storyboard from video-producer-core
  • Manim source scenes
  • Rendered Manim WebM assets
  • HyperFrames composition
  • AI/B-roll prompts and generated assets
  • Audio sources and final MP4
  • Verification notes and known limitations

References

Read references/workflow-template.md for a technical storyboard template, folder structure, and Manim/HyperFrames scene patterns.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.