visual-storyteller
Skill305 starsChanged 10 months agoMITView on GitHub
Narrative-driven animation skill for explanatory content and visual storytelling.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- iberi22/skillstheir own version, first seen Oct 15, 2026
- EiomSirius/creative-teamtheir own version, first seen May 5, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- EiomSirius/creative-team★ 0same name
- iberi22/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- animation-composerSkill
- math-visualizerSkill
- motion-graphicsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 54
Use relatable visual metaphors to explain abstract concepts.
- Distinctive: line 203
One idea at a time: - Don't introduce multiple concepts simultaneously
≈ “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.
Files
Visual Storyteller Skill
The Visual Storyteller transforms explanations and processes into engaging visual narratives that build understanding progressively.
Storytelling Framework
The CLEAR Method
- Context: Establish what we're exploring
- Layers: Build complexity gradually
- Examples: Show concrete instances
- Analogies: Connect to familiar concepts
- Reinforce: Summarize key insights
Narrative Arc for Explanations
1. Hook (Why should I care?)
↓
2. Setup (What do I need to know?)
↓
3. Rising Action (Build understanding step by step)
↓
4. Climax (The "aha!" moment)
↓
5. Resolution (How does this connect to the bigger picture?)Rules
rules/progressive-revelation.md
Show information piece by piece, never overwhelming the viewer.
rules/visual-metaphors.md
Use relatable visual metaphors to explain abstract concepts.
rules/pacing-for-understanding.md
Allow time for concepts to sink in before moving forward.
rules/emphasis-techniques.md
Highlight key elements using color, size, and animation.
Templates
Concept Explanation
from manim import *
class ConceptExplanation(Scene):
def construct(self):
# Hook: Pose an intriguing question
question = Text("Why does this happen?", color=YELLOW)
self.play(Write(question))
self.wait(2)
self.play(FadeOut(question))
# Setup: Introduce the elements
elements = self.introduce_elements()
# Rising Action: Build step by step
for i, step in enumerate(self.get_steps()):
step_label = Text(f"Step {i+1}", font_size=24).to_corner(UL)
self.play(FadeIn(step_label))
self.demonstrate_step(step, elements)
self.play(FadeOut(step_label))
# Climax: The revelation
self.play(Indicate(elements, scale_factor=1.2, color=GREEN))
insight = Text("And that's why!", color=GREEN)
self.play(Write(insight))
# Resolution: Connect to bigger picture
self.play(FadeOut(insight), FadeOut(elements))
summary = self.create_summary()
self.play(FadeIn(summary))Process Walkthrough
from manim import *
class ProcessWalkthrough(Scene):
def construct(self):
# Title
title = Text("How X Works").scale(1.2)
self.play(Write(title))
self.play(title.animate.to_edge(UP).scale(0.6))
# Create process diagram
steps = VGroup(*[
self.create_step_box(f"Step {i+1}", desc)
for i, desc in enumerate(self.step_descriptions)
]).arrange(RIGHT, buff=1)
# Progressive revelation
for i, step in enumerate(steps):
self.play(FadeIn(step, shift=UP))
self.wait(0.5)
# Highlight current step
self.play(step.animate.set_color(YELLOW))
self.demonstrate_step_detail(i)
self.play(step.animate.set_color(WHITE))
# Draw arrow to next step
if i < len(steps) - 1:
arrow = Arrow(step.get_right(), steps[i+1].get_left())
self.play(Create(arrow))Comparison/Contrast
from manim import *
class ComparisonScene(Scene):
def construct(self):
# Split screen
line = Line(UP * 3, DOWN * 3)
self.play(Create(line))
# Left side: Concept A
left_title = Text("Without X").to_edge(UP).shift(LEFT * 3)
left_demo = self.create_without_x().shift(LEFT * 3)
# Right side: Concept B
right_title = Text("With X").to_edge(UP).shift(RIGHT * 3)
right_demo = self.create_with_x().shift(RIGHT * 3)
# Show side by side
self.play(Write(left_title), Write(right_title))
self.play(Create(left_demo), Create(right_demo))
# Animate differences
self.highlight_differences(left_demo, right_demo)
# Conclusion
self.play(FadeOut(line), FadeOut(left_demo), FadeOut(left_title))
self.play(right_demo.animate.move_to(ORIGIN))
conclusion = Text("X makes the difference!", color=GREEN).next_to(right_demo, DOWN)
self.play(Write(conclusion))Emphasis Techniques
Color Highlighting
# Fade everything except the focus
self.play(
other_elements.animate.set_opacity(0.3),
focus_element.animate.set_color(YELLOW)
)Scale Emphasis
# Grow important element
self.play(important.animate.scale(1.5))Indicator Animation
# Pulse attention
self.play(Indicate(element, color=RED))Surrounding Highlight
# Circle the important part
circle = Circle(color=YELLOW).surround(element)
self.play(Create(circle))Pacing Guidelines
| Content Type | Wait Time | Animation Speed |
| New concept | 2-3 sec | Slow (run_time=2) |
| Step in process | 1-2 sec | Medium (run_time=1) |
| Transition | 0.5 sec | Fast (run_time=0.5) |
| Final reveal | 3-4 sec | Slow with emphasis |
Best Practices
- One idea at a time - Don't introduce multiple concepts simultaneously
- Build on prior knowledge - Connect new ideas to what's already shown
- Use consistent visual language - Same colors/shapes for same concepts
- Allow breathing room - Silence and stillness aid comprehension
- End with synthesis - Bring everything together at the conclusion
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
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.

