diff --git a/skills/creative/manim-video/README.md b/skills/creative/manim-video/README.md
new file mode 100644
index 000000000..4ed03d892
--- /dev/null
+++ b/skills/creative/manim-video/README.md
@@ -0,0 +1,23 @@
+# Manim Video Skill
+
+Production pipeline for mathematical and technical animations using [Manim Community Edition](https://www.manim.community/).
+
+## What it does
+
+Creates 3Blue1Brown-style animated videos from text prompts. The agent handles the full pipeline: creative planning, Python code generation, rendering, scene stitching, and iterative refinement.
+
+## Use cases
+
+- **Concept explainers** — "Explain how neural networks learn"
+- **Equation derivations** — "Animate the proof of the Pythagorean theorem"
+- **Algorithm visualizations** — "Show how quicksort works step by step"
+- **Data stories** — "Animate our before/after performance metrics"
+- **Architecture diagrams** — "Show our microservice architecture building up"
+
+## Prerequisites
+
+Python 3.10+, Manim CE (`pip install manim`), LaTeX, ffmpeg.
+
+```bash
+bash skills/creative/manim-video/scripts/setup.sh
+```
diff --git a/skills/creative/manim-video/SKILL.md b/skills/creative/manim-video/SKILL.md
new file mode 100644
index 000000000..34e6f7e67
--- /dev/null
+++ b/skills/creative/manim-video/SKILL.md
@@ -0,0 +1,231 @@
+---
+name: manim-video
+description: "Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric/mathematical content."
+version: 1.0.0
+---
+
+# Manim Video Production Pipeline
+
+## Creative Standard
+
+This is educational cinema. Every frame teaches. Every animation reveals structure.
+
+**Before writing a single line of code**, articulate the narrative arc. What misconception does this correct? What is the "aha moment"? What visual story takes the viewer from confusion to understanding? The user's prompt is a starting point — interpret it with pedagogical ambition.
+
+**Geometry before algebra.** Show the shape first, the equation second. Visual memory encodes faster than symbolic memory. When the viewer sees the geometric pattern before the formula, the equation feels earned.
+
+**First-render excellence is non-negotiable.** The output must be visually clear and aesthetically cohesive without revision rounds. If something looks cluttered, poorly timed, or like "AI-generated slides," it is wrong.
+
+**Opacity layering directs attention.** Never show everything at full brightness. Primary elements at 1.0, contextual elements at 0.4, structural elements (axes, grids) at 0.15. The brain processes visual salience in layers.
+
+**Breathing room.** Every animation needs `self.wait()` after it. The viewer needs time to absorb what just appeared. Never rush from one animation to the next. A 2-second pause after a key reveal is never wasted.
+
+**Cohesive visual language.** All scenes share a color palette, consistent typography sizing, matching animation speeds. A technically correct video where every scene uses random different colors is an aesthetic failure.
+
+## Prerequisites
+
+Run `scripts/setup.sh` to verify all dependencies. Requires: Python 3.10+, Manim Community Edition (`pip install manim`), LaTeX (`texlive-full` on Linux, `mactex` on macOS), and ffmpeg.
+
+## Modes
+
+| Mode | Input | Output | Reference |
+|------|-------|--------|-----------|
+| **Concept explainer** | Topic/concept | Animated explanation with geometric intuition | `references/scene-planning.md` |
+| **Equation derivation** | Math expressions | Step-by-step animated proof | `references/equations.md` |
+| **Algorithm visualization** | Algorithm description | Step-by-step execution with data structures | `references/graphs-and-data.md` |
+| **Data story** | Data/metrics | Animated charts, comparisons, counters | `references/graphs-and-data.md` |
+| **Architecture diagram** | System description | Components building up with connections | `references/mobjects.md` |
+| **Paper explainer** | Research paper | Key findings and methods animated | `references/scene-planning.md` |
+| **3D visualization** | 3D concept | Rotating surfaces, parametric curves, spatial geometry | `references/camera-and-3d.md` |
+
+## Stack
+
+Single Python script per project. No browser, no Node.js, no GPU required.
+
+| Layer | Tool | Purpose |
+|-------|------|---------|
+| Core | Manim Community Edition | Scene rendering, animation engine |
+| Math | LaTeX (texlive/MiKTeX) | Equation rendering via `MathTex` |
+| Video I/O | ffmpeg | Scene stitching, format conversion, audio muxing |
+| TTS | ElevenLabs / Qwen3-TTS (optional) | Narration voiceover |
+
+## Pipeline
+
+```
+PLAN --> CODE --> RENDER --> STITCH --> AUDIO (optional) --> REVIEW
+```
+
+1. **PLAN** — Write `plan.md` with narrative arc, scene list, visual elements, color palette, voiceover script
+2. **CODE** — Write `script.py` with one class per scene, each independently renderable
+3. **RENDER** — `manim -ql script.py Scene1 Scene2 ...` for draft, `-qh` for production
+4. **STITCH** — ffmpeg concat of scene clips into `final.mp4`
+5. **AUDIO** (optional) — Add voiceover and/or background music via ffmpeg. See `references/rendering.md`
+6. **REVIEW** — Render preview stills, verify against plan, adjust
+
+## Project Structure
+
+```
+project-name/
+  plan.md                # Narrative arc, scene breakdown
+  script.py              # All scenes in one file
+  concat.txt             # ffmpeg scene list
+  final.mp4              # Stitched output
+  media/                 # Auto-generated by Manim
+    videos/script/480p15/
+```
+
+## Creative Direction
+
+### Color Palettes
+
+| Palette | Background | Primary | Secondary | Accent | Use case |
+|---------|-----------|---------|-----------|--------|----------|
+| **Classic 3B1B** | `#1C1C1C` | `#58C4DD` (BLUE) | `#83C167` (GREEN) | `#FFFF00` (YELLOW) | General math/CS |
+| **Warm academic** | `#2D2B55` | `#FF6B6B` | `#FFD93D` | `#6BCB77` | Approachable |
+| **Neon tech** | `#0A0A0A` | `#00F5FF` | `#FF00FF` | `#39FF14` | Systems, architecture |
+| **Monochrome** | `#1A1A2E` | `#EAEAEA` | `#888888` | `#FFFFFF` | Minimalist |
+
+### Animation Speed
+
+| Context | run_time | self.wait() after |
+|---------|----------|-------------------|
+| Title/intro appear | 1.5s | 1.0s |
+| Key equation reveal | 2.0s | 2.0s |
+| Transform/morph | 1.5s | 1.5s |
+| Supporting label | 0.8s | 0.5s |
+| FadeOut cleanup | 0.5s | 0.3s |
+| "Aha moment" reveal | 2.5s | 3.0s |
+
+### Typography Scale
+
+| Role | Font size | Usage |
+|------|-----------|-------|
+| Title | 48 | Scene titles, opening text |
+| Heading | 36 | Section headers within a scene |
+| Body | 30 | Explanatory text |
+| Label | 24 | Annotations, axis labels |
+| Caption | 20 | Subtitles, fine print |
+
+### Fonts
+
+Always specify fonts explicitly — the default renders poorly. See `references/visual-design.md` for full recommendations.
+
+```python
+Text("Title", font_size=48, font="Inter", weight=BOLD)       # body text
+Text("code()", font_size=24, font="JetBrains Mono")           # monospaced
+MathTex(r"\nabla L")                                           # math (uses LaTeX)
+```
+
+### Per-Scene Variation
+
+Never use identical config for all scenes. For each scene:
+- **Different dominant color** from the palette
+- **Different layout** — don't always center everything
+- **Different animation entry** — vary between Write, FadeIn, GrowFromCenter, Create
+- **Different visual weight** — some scenes dense, others sparse
+
+## Workflow
+
+### Step 1: Plan (plan.md)
+
+Before any code, write `plan.md`. See `references/scene-planning.md` for the comprehensive template.
+
+### Step 2: Code (script.py)
+
+One class per scene. Every scene is independently renderable.
+
+```python
+from manim import *
+
+BG = "#1C1C1C"
+PRIMARY = "#58C4DD"
+SECONDARY = "#83C167"
+ACCENT = "#FFFF00"
+
+class Scene1_Introduction(Scene):
+    def construct(self):
+        self.camera.background_color = BG
+        title = Text("Why Does This Work?", font_size=48, color=PRIMARY)
+        self.add_subcaption("Why does this work?", duration=2)
+        self.play(Write(title), run_time=1.5)
+        self.wait(1.0)
+        self.play(FadeOut(title), run_time=0.5)
+```
+
+Key patterns:
+- **Subtitles** on every animation: `self.add_subcaption("text", duration=N)` or `subcaption="text"` on `self.play()`
+- **Shared color constants** at file top for cross-scene consistency
+- **`self.camera.background_color`** set in every scene
+- **Clean exits** — FadeOut all mobjects at scene end: `self.play(FadeOut(Group(*self.mobjects)))`
+
+### Step 3: Render
+
+```bash
+manim -ql script.py Scene1_Introduction Scene2_CoreConcept  # draft
+manim -qh script.py Scene1_Introduction Scene2_CoreConcept  # production
+```
+
+### Step 4: Stitch
+
+```bash
+cat > concat.txt << 'EOF'
+file 'media/videos/script/480p15/Scene1_Introduction.mp4'
+file 'media/videos/script/480p15/Scene2_CoreConcept.mp4'
+EOF
+ffmpeg -y -f concat -safe 0 -i concat.txt -c copy final.mp4
+```
+
+### Step 5: Review
+
+```bash
+manim -ql --format=png -s script.py Scene2_CoreConcept  # preview still
+```
+
+## Critical Implementation Notes
+
+### Raw Strings for LaTeX
+```python
+# WRONG: MathTex("\frac{1}{2}")
+# RIGHT:
+MathTex(r"\frac{1}{2}")
+```
+
+### buff >= 0.5 for Edge Text
+```python
+label.to_edge(DOWN, buff=0.5)  # never < 0.5
+```
+
+### FadeOut Before Replacing Text
+```python
+self.play(ReplacementTransform(note1, note2))  # not Write(note2) on top
+```
+
+### Never Animate Non-Added Mobjects
+```python
+self.play(Create(circle))  # must add first
+self.play(circle.animate.set_color(RED))  # then animate
+```
+
+## Performance Targets
+
+| Quality | Resolution | FPS | Speed |
+|---------|-----------|-----|-------|
+| `-ql` (draft) | 854x480 | 15 | 5-15s/scene |
+| `-qm` (medium) | 1280x720 | 30 | 15-60s/scene |
+| `-qh` (production) | 1920x1080 | 60 | 30-120s/scene |
+
+Always iterate at `-ql`. Only render `-qh` for final output.
+
+## References
+
+| File | Contents |
+|------|----------|
+| `references/animations.md` | Core animations, rate functions, composition, `.animate` syntax, timing patterns |
+| `references/mobjects.md` | Text, shapes, VGroup/Group, positioning, styling, custom mobjects |
+| `references/visual-design.md` | 12 design principles, opacity layering, layout templates, color palettes |
+| `references/equations.md` | LaTeX in Manim, TransformMatchingTex, derivation patterns |
+| `references/graphs-and-data.md` | Axes, plotting, BarChart, animated data, algorithm visualization |
+| `references/camera-and-3d.md` | MovingCameraScene, ThreeDScene, 3D surfaces, camera control |
+| `references/scene-planning.md` | Narrative arcs, layout templates, scene transitions, planning template |
+| `references/rendering.md` | CLI reference, quality presets, ffmpeg, voiceover workflow, GIF export |
+| `references/troubleshooting.md` | LaTeX errors, animation errors, common mistakes, debugging |
diff --git a/skills/creative/manim-video/references/animations.md b/skills/creative/manim-video/references/animations.md
new file mode 100644
index 000000000..b0ca0ab73
--- /dev/null
+++ b/skills/creative/manim-video/references/animations.md
@@ -0,0 +1,122 @@
+# Animations Reference
+
+## Core Concept
+
+An animation is a Python object that computes intermediate visual states of a mobject over time. Animations are objects passed to `self.play()`, not functions.
+
+`run_time` controls seconds (default: 1). Always specify it explicitly for important animations.
+
+## Creation Animations
+
+```python
+self.play(Create(circle))          # traces outline
+self.play(Write(equation))         # simulates handwriting (for Text/MathTex)
+self.play(FadeIn(group))           # opacity 0 -> 1
+self.play(GrowFromCenter(dot))     # scale 0 -> 1 from center
+self.play(DrawBorderThenFill(sq))  # outline first, then fill
+```
+
+## Removal Animations
+
+```python
+self.play(FadeOut(mobject))         # opacity 1 -> 0
+self.play(Uncreate(circle))        # reverse of Create
+self.play(ShrinkToCenter(group))   # scale 1 -> 0
+```
+
+## Transform Animations
+
+```python
+# Transform -- modifies the original in place
+self.play(Transform(circle, square))
+# After: circle IS the square (same object, new appearance)
+
+# ReplacementTransform -- replaces old with new
+self.play(ReplacementTransform(circle, square))
+# After: circle removed, square on screen
+
+# TransformMatchingTex -- smart equation morphing
+eq1 = MathTex(r"a^2 + b^2")
+eq2 = MathTex(r"a^2 + b^2 = c^2")
+self.play(TransformMatchingTex(eq1, eq2))
+```
+
+**Critical**: After `Transform(A, B)`, variable `A` references the on-screen mobject. Variable `B` is NOT on screen. Use `ReplacementTransform` when you want to work with `B` afterwards.
+
+## The .animate Syntax
+
+```python
+self.play(circle.animate.set_color(RED))
+self.play(circle.animate.shift(RIGHT * 2).scale(0.5))  # chain multiple
+```
+
+## Emphasis Animations
+
+```python
+self.play(Indicate(mobject))             # brief yellow flash + scale
+self.play(Circumscribe(mobject))         # draw rectangle around it
+self.play(Flash(point))                  # radial flash
+self.play(Wiggle(mobject))               # shake side to side
+```
+
+## Rate Functions
+
+```python
+self.play(FadeIn(mob), rate_func=smooth)          # default: ease in/out
+self.play(FadeIn(mob), rate_func=linear)           # constant speed
+self.play(FadeIn(mob), rate_func=rush_into)        # start slow, end fast
+self.play(FadeIn(mob), rate_func=rush_from)        # start fast, end slow
+self.play(FadeIn(mob), rate_func=there_and_back)   # animate then reverse
+```
+
+## Composition
+
+```python
+# Simultaneous
+self.play(FadeIn(title), Create(circle), run_time=2)
+
+# AnimationGroup with lag
+self.play(AnimationGroup(*[FadeIn(i) for i in items], lag_ratio=0.2))
+
+# LaggedStart
+self.play(LaggedStart(*[Write(l) for l in lines], lag_ratio=0.3, run_time=3))
+
+# Succession (sequential in one play call)
+self.play(Succession(FadeIn(title), Wait(0.5), Write(subtitle)))
+```
+
+## Updaters
+
+```python
+tracker = ValueTracker(0)
+dot = Dot().add_updater(lambda m: m.move_to(axes.c2p(tracker.get_value(), 0)))
+self.play(tracker.animate.set_value(5), run_time=3)
+```
+
+## Subtitles
+
+```python
+# Method 1: standalone
+self.add_subcaption("Key insight", duration=2)
+self.play(Write(equation), run_time=2.0)
+
+# Method 2: inline
+self.play(Write(equation), subcaption="Key insight", subcaption_duration=2)
+```
+
+Manim auto-generates `.srt` subtitle files. Always add subcaptions for accessibility.
+
+## Timing Patterns
+
+```python
+# Pause-after-reveal
+self.play(Write(key_equation), run_time=2.0)
+self.wait(2.0)
+
+# Dim-and-focus
+self.play(old_content.animate.set_opacity(0.3), FadeIn(new_content))
+
+# Clean exit
+self.play(FadeOut(Group(*self.mobjects)), run_time=0.5)
+self.wait(0.3)
+```
diff --git a/skills/creative/manim-video/references/camera-and-3d.md b/skills/creative/manim-video/references/camera-and-3d.md
new file mode 100644
index 000000000..71448ad60
--- /dev/null
+++ b/skills/creative/manim-video/references/camera-and-3d.md
@@ -0,0 +1,76 @@
+# Camera and 3D Reference
+
+## MovingCameraScene (2D Camera Control)
+
+```python
+class ZoomExample(MovingCameraScene):
+    def construct(self):
+        circle = Circle(radius=2, color=BLUE)
+        self.play(Create(circle))
+        # Zoom in
+        self.play(self.camera.frame.animate.set(width=4).move_to(circle.get_top()), run_time=2)
+        self.wait(2)
+        # Zoom back out
+        self.play(self.camera.frame.animate.set(width=14.222).move_to(ORIGIN), run_time=2)
+```
+
+### Camera Operations
+
+```python
+self.camera.frame.animate.set(width=6)     # zoom in
+self.camera.frame.animate.set(width=20)    # zoom out
+self.camera.frame.animate.move_to(target)  # pan
+self.camera.frame.save_state()             # save
+self.play(Restore(self.camera.frame))      # restore
+```
+
+## ThreeDScene
+
+```python
+class ThreeDExample(ThreeDScene):
+    def construct(self):
+        self.set_camera_orientation(phi=60*DEGREES, theta=-45*DEGREES)
+        axes = ThreeDAxes()
+        surface = Surface(
+            lambda u, v: axes.c2p(u, v, np.sin(u) * np.cos(v)),
+            u_range=[-PI, PI], v_range=[-PI, PI], resolution=(30, 30)
+        )
+        surface.set_color_by_gradient(BLUE, GREEN, YELLOW)
+        self.play(Create(axes), Create(surface))
+        self.begin_ambient_camera_rotation(rate=0.2)
+        self.wait(5)
+        self.stop_ambient_camera_rotation()
+```
+
+### Camera Control in 3D
+
+```python
+self.set_camera_orientation(phi=70*DEGREES, theta=-45*DEGREES)
+self.move_camera(phi=45*DEGREES, theta=30*DEGREES, run_time=2)
+self.begin_ambient_camera_rotation(rate=0.2)
+```
+
+### 3D Mobjects
+
+```python
+sphere = Sphere(radius=1).set_color(BLUE).set_opacity(0.7)
+cube = Cube(side_length=2, fill_color=GREEN, fill_opacity=0.5)
+arrow = Arrow3D(start=ORIGIN, end=[2, 1, 1], color=RED)
+# 2D text facing camera:
+label = Text("Label", font_size=30)
+self.add_fixed_in_frame_mobjects(label)
+```
+
+### Parametric Curves
+
+```python
+helix = ParametricFunction(
+    lambda t: [np.cos(t), np.sin(t), t / (2*PI)],
+    t_range=[0, 4*PI], color=YELLOW
+)
+```
+
+## When to Use 3D
+- Surfaces, vector fields, spatial geometry, 3D transforms
+## When NOT to Use 3D
+- 2D concepts, text-heavy scenes, flat data (bar charts, time series)
diff --git a/skills/creative/manim-video/references/equations.md b/skills/creative/manim-video/references/equations.md
new file mode 100644
index 000000000..183691fb5
--- /dev/null
+++ b/skills/creative/manim-video/references/equations.md
@@ -0,0 +1,80 @@
+# Equations and LaTeX Reference
+
+## Basic LaTeX
+
+```python
+eq = MathTex(r"E = mc^2")
+eq = MathTex(r"f(x) &= x^2 + 2x + 1 \\ &= (x + 1)^2")  # multi-line aligned
+```
+
+**Always use raw strings (`r""`).**
+
+## Step-by-Step Derivations
+
+```python
+step1 = MathTex(r"a^2 + b^2 = c^2")
+step2 = MathTex(r"a^2 = c^2 - b^2")
+self.play(Write(step1), run_time=1.5)
+self.wait(1.5)
+self.play(TransformMatchingTex(step1, step2), run_time=1.5)
+```
+
+## Selective Color
+
+```python
+eq = MathTex(r"a^2", r"+", r"b^2", r"=", r"c^2")
+eq[0].set_color(RED)
+eq[4].set_color(GREEN)
+```
+
+## Building Incrementally
+
+```python
+parts = MathTex(r"f(x)", r"=", r"\sum_{n=0}^{\infty}", r"\frac{f^{(n)}(a)}{n!}", r"(x-a)^n")
+self.play(Write(parts[0:2]))
+self.wait(0.5)
+self.play(Write(parts[2]))
+self.wait(0.5)
+self.play(Write(parts[3:]))
+```
+
+## Highlighting
+
+```python
+highlight = SurroundingRectangle(eq[2], color=YELLOW, buff=0.1)
+self.play(Create(highlight))
+self.play(Indicate(eq[4], color=YELLOW))
+```
+
+## Annotation
+
+```python
+brace = Brace(eq, DOWN, color=YELLOW)
+label = brace.get_text("Fundamental Theorem", font_size=24)
+self.play(GrowFromCenter(brace), Write(label))
+```
+
+## Common LaTeX
+
+```python
+MathTex(r"\frac{a}{b}")                  # fraction
+MathTex(r"\alpha, \beta, \gamma")         # Greek
+MathTex(r"\sum_{i=1}^{n} x_i")           # summation
+MathTex(r"\int_{0}^{\infty} e^{-x} dx")  # integral
+MathTex(r"\vec{v}")                       # vector
+MathTex(r"\lim_{x \to \infty} f(x)")    # limit
+```
+
+## Derivation Pattern
+
+```python
+class DerivationScene(Scene):
+    def construct(self):
+        self.camera.background_color = BG
+        s1 = MathTex(r"ax^2 + bx + c = 0")
+        self.play(Write(s1))
+        self.wait(1.5)
+        s2 = MathTex(r"x^2 + \frac{b}{a}x + \frac{c}{a} = 0")
+        s2.next_to(s1, DOWN, buff=0.8)
+        self.play(s1.animate.set_opacity(0.4), TransformMatchingTex(s1.copy(), s2))
+```
diff --git a/skills/creative/manim-video/references/graphs-and-data.md b/skills/creative/manim-video/references/graphs-and-data.md
new file mode 100644
index 000000000..c97396c43
--- /dev/null
+++ b/skills/creative/manim-video/references/graphs-and-data.md
@@ -0,0 +1,91 @@
+# Graphs, Plots, and Data Visualization
+
+## Axes
+
+```python
+axes = Axes(
+    x_range=[-3, 3, 1], y_range=[-2, 2, 1],
+    x_length=8, y_length=5,
+    axis_config={"include_numbers": True, "font_size": 24}
+)
+axes.set_opacity(0.15)  # structural element
+x_label = axes.get_x_axis_label(r"x")
+```
+
+## Plotting
+
+```python
+graph = axes.plot(lambda x: x**2, color=BLUE)
+graph_label = axes.get_graph_label(graph, label=r"x^2", x_val=2)
+area = axes.get_area(graph, x_range=[0, 2], color=BLUE, opacity=0.3)
+```
+
+## Animated Plotting
+
+```python
+self.play(Create(graph), run_time=3)  # trace the graph
+
+# Moving dot along curve
+dot = Dot(color=YELLOW).move_to(axes.c2p(0, 0))
+self.play(MoveAlongPath(dot, graph), run_time=3)
+
+# Dynamic parameter
+tracker = ValueTracker(1)
+dynamic = always_redraw(lambda: axes.plot(lambda x: tracker.get_value() * x**2, color=BLUE))
+self.add(dynamic)
+self.play(tracker.animate.set_value(3), run_time=2)
+```
+
+## Bar Charts
+
+```python
+chart = BarChart(
+    values=[4, 6, 2, 8, 5], bar_names=["A", "B", "C", "D", "E"],
+    y_range=[0, 10, 2], bar_colors=[RED, GREEN, BLUE, YELLOW, PURPLE]
+)
+self.play(Create(chart), run_time=2)
+self.play(chart.animate.change_bar_values([6, 3, 7, 4, 9]))
+```
+
+## Number Lines
+
+```python
+nl = NumberLine(x_range=[0, 10, 1], length=10, include_numbers=True)
+pointer = Arrow(nl.n2p(3) + UP * 0.5, nl.n2p(3), color=RED, buff=0)
+tracker = ValueTracker(3)
+pointer.add_updater(lambda m: m.put_start_and_end_on(
+    nl.n2p(tracker.get_value()) + UP * 0.5, nl.n2p(tracker.get_value())))
+self.play(tracker.animate.set_value(8), run_time=2)
+```
+
+## Animated Counters
+
+```python
+counter = DecimalNumber(0, font_size=72, num_decimal_places=0)
+self.play(counter.animate.set_value(1000), run_time=3, rate_func=rush_from)
+```
+
+## Algorithm Visualization Pattern
+
+```python
+values = [5, 2, 8, 1, 9, 3]
+bars = VGroup(*[
+    Rectangle(width=0.6, height=v * 0.4, color=BLUE, fill_opacity=0.7)
+    for v in values
+]).arrange(RIGHT, buff=0.2, aligned_edge=DOWN).move_to(ORIGIN)
+self.play(LaggedStart(*[GrowFromEdge(b, DOWN) for b in bars], lag_ratio=0.1))
+# Highlight, swap, etc.
+```
+
+## Data Story Pattern
+
+```python
+# Before/After comparison
+before = BarChart(values=[3, 5, 2], bar_colors=[RED]*3).shift(LEFT * 3)
+after = BarChart(values=[8, 9, 7], bar_colors=[GREEN]*3).shift(RIGHT * 3)
+self.play(Create(before)); self.wait(1)
+self.play(Create(after)); self.wait(1)
+arrow = Arrow(before.get_right(), after.get_left(), color=YELLOW)
+label = Text("+167%", font_size=36, color=YELLOW).next_to(arrow, UP)
+self.play(GrowArrow(arrow), Write(label))
+```
diff --git a/skills/creative/manim-video/references/mobjects.md b/skills/creative/manim-video/references/mobjects.md
new file mode 100644
index 000000000..069eee8fb
--- /dev/null
+++ b/skills/creative/manim-video/references/mobjects.md
@@ -0,0 +1,106 @@
+# Mobjects Reference
+
+Everything visible on screen is a Mobject. They have position, color, opacity, and can be animated.
+
+## Text
+
+```python
+title = Text("Hello World", font_size=48, color=BLUE)
+eq = MathTex(r"E = mc^2", font_size=40)
+
+# Multi-part (for selective coloring)
+eq = MathTex(r"a^2", r"+", r"b^2", r"=", r"c^2")
+eq[0].set_color(RED)
+eq[4].set_color(BLUE)
+
+# Mixed text and math
+t = Tex(r"The area is $\pi r^2$", font_size=36)
+
+# Styled markup
+t = MarkupText('<span foreground="#58C4DD">Blue</span> text', font_size=30)
+```
+
+**Always use raw strings (`r""`) for any string with backslashes.**
+
+## Shapes
+
+```python
+circle = Circle(radius=1, color=BLUE, fill_opacity=0.5)
+square = Square(side_length=2, color=RED)
+rect = Rectangle(width=4, height=2, color=GREEN)
+dot = Dot(point=ORIGIN, radius=0.08, color=YELLOW)
+line = Line(LEFT * 2, RIGHT * 2, color=WHITE)
+arrow = Arrow(LEFT, RIGHT, color=ORANGE)
+rrect = RoundedRectangle(corner_radius=0.3, width=4, height=2)
+brace = Brace(rect, DOWN, color=YELLOW)
+```
+
+## Positioning
+
+```python
+mob.move_to(ORIGIN)                        # center
+mob.move_to(UP * 2 + RIGHT)               # relative
+label.next_to(circle, DOWN, buff=0.3)     # next to another
+title.to_edge(UP, buff=0.5)               # screen edge (buff >= 0.5!)
+mob.to_corner(UL, buff=0.5)               # corner
+```
+
+## VGroup vs Group
+
+**VGroup** is for collections of shapes (VMobjects only — Circle, Square, Arrow, Line, MathTex):
+```python
+shapes = VGroup(circle, square, arrow)
+shapes.arrange(DOWN, buff=0.5)
+shapes.set_color(BLUE)
+```
+
+**Group** is for mixed collections (Text + shapes, or any Mobject types):
+```python
+# Text objects are Mobjects, not VMobjects — use Group when mixing
+labeled_shape = Group(circle, Text("Label").next_to(circle, DOWN))
+labeled_shape.move_to(ORIGIN)
+
+# FadeOut everything on screen (may contain mixed types)
+self.play(FadeOut(Group(*self.mobjects)))
+```
+
+**Rule: if your group contains any `Text()` objects, use `Group`, not `VGroup`.** VGroup will raise a TypeError on Manim CE v0.20+. MathTex and Tex are VMobjects and work with VGroup.
+
+Both support `arrange()`, `arrange_in_grid()`, `set_opacity()`, `shift()`, `scale()`, `move_to()`.
+
+## Styling
+
+```python
+mob.set_color(BLUE)
+mob.set_fill(RED, opacity=0.5)
+mob.set_stroke(WHITE, width=2)
+mob.set_opacity(0.4)
+mob.set_z_index(1)                         # layering
+```
+
+## Specialized Mobjects
+
+```python
+nl = NumberLine(x_range=[-3, 3, 1], length=8, include_numbers=True)
+table = Table([["A", "B"], ["C", "D"]], row_labels=[Text("R1"), Text("R2")])
+code = Code("example.py", tab_width=4, font_size=20, language="python")
+highlight = SurroundingRectangle(target, color=YELLOW, buff=0.2)
+bg = BackgroundRectangle(equation, fill_opacity=0.7, buff=0.2)
+```
+
+## Custom Mobjects
+
+```python
+class NetworkNode(Group):
+    def __init__(self, label_text, color=BLUE, **kwargs):
+        super().__init__(**kwargs)
+        self.circle = Circle(radius=0.4, color=color, fill_opacity=0.3)
+        self.label = Text(label_text, font_size=20).move_to(self.circle)
+        self.add(self.circle, self.label)
+```
+
+## Constants
+
+Directions: `UP, DOWN, LEFT, RIGHT, ORIGIN, UL, UR, DL, DR`
+Colors: `RED, BLUE, GREEN, YELLOW, WHITE, GRAY, ORANGE, PINK, PURPLE, TEAL, GOLD`
+Frame: `config.frame_width = 14.222, config.frame_height = 8.0`
diff --git a/skills/creative/manim-video/references/rendering.md b/skills/creative/manim-video/references/rendering.md
new file mode 100644
index 000000000..f4c863393
--- /dev/null
+++ b/skills/creative/manim-video/references/rendering.md
@@ -0,0 +1,93 @@
+# Rendering Reference
+
+## Prerequisites
+
+```bash
+manim --version       # Manim CE
+pdflatex --version    # LaTeX
+ffmpeg -version       # ffmpeg
+```
+
+## CLI Reference
+
+```bash
+manim -ql script.py Scene1 Scene2    # draft (480p 15fps)
+manim -qm script.py Scene1           # medium (720p 30fps)
+manim -qh script.py Scene1           # production (1080p 60fps)
+manim -ql --format=png -s script.py Scene1  # preview still (last frame)
+manim -ql --format=gif script.py Scene1     # GIF output
+```
+
+## Quality Presets
+
+| Flag | Resolution | FPS | Use case |
+|------|-----------|-----|----------|
+| `-ql` | 854x480 | 15 | Draft iteration (layout, timing) |
+| `-qm` | 1280x720 | 30 | Preview (use for text-heavy scenes) |
+| `-qh` | 1920x1080 | 60 | Production |
+
+**Text rendering quality:** `-ql` (480p15) produces noticeably poor text kerning and readability. For scenes with significant text, preview stills at `-qm` to catch issues invisible at 480p. Use `-ql` only for testing layout and animation timing.
+
+## Output Structure
+
+```
+media/videos/script/480p15/Scene1_Intro.mp4
+media/images/script/Scene1_Intro.png  (from -s flag)
+```
+
+## Stitching with ffmpeg
+
+```bash
+cat > concat.txt << 'EOF'
+file 'media/videos/script/480p15/Scene1_Intro.mp4'
+file 'media/videos/script/480p15/Scene2_Core.mp4'
+EOF
+ffmpeg -y -f concat -safe 0 -i concat.txt -c copy final.mp4
+```
+
+## Add Voiceover
+
+```bash
+# Mux narration
+ffmpeg -y -i final.mp4 -i narration.mp3 -c:v copy -c:a aac -b:a 192k -shortest final_narrated.mp4
+
+# Concat per-scene audio first
+cat > audio_concat.txt << 'EOF'
+file 'audio/scene1.mp3'
+file 'audio/scene2.mp3'
+EOF
+ffmpeg -y -f concat -safe 0 -i audio_concat.txt -c copy full_narration.mp3
+```
+
+## Add Background Music
+
+```bash
+ffmpeg -y -i final.mp4 -i music.mp3 \
+  -filter_complex "[1:a]volume=0.15[bg];[0:a][bg]amix=inputs=2:duration=shortest" \
+  -c:v copy final_with_music.mp4
+```
+
+## GIF Export
+
+```bash
+ffmpeg -y -i scene.mp4 \
+  -vf "fps=15,scale=640:-1:flags=lanczos,split[s0][s1];[s0]palettegen[p];[s1][p]paletteuse" \
+  output.gif
+```
+
+## Aspect Ratios
+
+```bash
+manim -ql --resolution 1080,1920 script.py Scene  # 9:16 vertical
+manim -ql --resolution 1080,1080 script.py Scene  # 1:1 square
+```
+
+## Render Workflow
+
+1. Draft render all scenes at `-ql`
+2. Preview stills at key moments (`-s`)
+3. Fix and re-render only broken scenes
+4. Stitch with ffmpeg
+5. Review stitched output
+6. Production render at `-qh`
+7. Re-stitch + add audio
diff --git a/skills/creative/manim-video/references/scene-planning.md b/skills/creative/manim-video/references/scene-planning.md
new file mode 100644
index 000000000..f42b78f38
--- /dev/null
+++ b/skills/creative/manim-video/references/scene-planning.md
@@ -0,0 +1,118 @@
+# Scene Planning Reference
+
+## Narrative Arc Structures
+
+### Discovery Arc (most common)
+1. Hook -- pose a question or surprising result
+2. Intuition -- build visual understanding
+3. Formalize -- introduce the equation/algorithm
+4. Reveal -- the "aha moment"
+5. Extend -- implications or generalizations
+
+### Problem-Solution Arc
+1. Problem -- what's broken
+2. Failed attempt -- obvious approach fails
+3. Key insight -- the idea that works
+4. Solution -- implement it
+5. Result -- show improvement
+
+### Comparison Arc
+1. Setup -- introduce two approaches
+2. Approach A -- how it works
+3. Approach B -- how it works
+4. Contrast -- differences
+5. Verdict -- which is better
+
+### Build-Up Arc (architecture/systems)
+1. Component A -- first piece
+2. Component B -- second piece
+3. Connection -- how they interact
+4. Scale -- add more pieces
+5. Full picture -- zoom out
+
+## Scene Transitions
+
+### Clean Break (default)
+```python
+self.play(FadeOut(Group(*self.mobjects)), run_time=0.5)
+self.wait(0.3)
+```
+
+### Carry-Forward
+Keep one element, fade the rest. Next scene starts with it still on screen.
+
+### Transform Bridge
+End scene with a shape, start next scene by transforming it.
+
+## Cross-Scene Consistency
+
+```python
+# Shared constants at file top
+BG = "#1C1C1C"
+PRIMARY = "#58C4DD"
+SECONDARY = "#83C167"
+ACCENT = "#FFFF00"
+TITLE_SIZE = 48
+BODY_SIZE = 30
+LABEL_SIZE = 24
+FAST = 0.8; NORMAL = 1.5; SLOW = 2.5
+```
+
+## Scene Checklist
+
+- [ ] Background color set
+- [ ] Subcaptions on every animation
+- [ ] `self.wait()` after every reveal
+- [ ] Text buff >= 0.5 for edge positioning
+- [ ] No text overlap
+- [ ] Color constants used (not hardcoded)
+- [ ] Opacity layering applied
+- [ ] Clean exit at scene end
+- [ ] No more than 5-6 elements visible at once
+
+## Duration Estimation
+
+| Content | Duration |
+|---------|----------|
+| Title card | 3-5s |
+| Concept introduction | 10-20s |
+| Equation reveal | 15-25s |
+| Algorithm step | 5-10s |
+| Data comparison | 10-15s |
+| "Aha moment" | 15-30s |
+| Conclusion | 5-10s |
+
+## Planning Template
+
+```markdown
+# [Video Title]
+
+## Overview
+- **Topic**: [Core concept]
+- **Hook**: [Opening question]
+- **Aha moment**: [Key insight]
+- **Target audience**: [Prerequisites]
+- **Length**: [seconds/minutes]
+- **Resolution**: 480p (draft) / 1080p (final)
+
+## Color Palette
+- Background: #1C1C1C
+- Primary: #58C4DD -- [purpose]
+- Secondary: #83C167 -- [purpose]
+- Accent: #FFFF00 -- [purpose]
+
+## Arc: [Discovery / Problem-Solution / Comparison / Build-Up]
+
+## Scene 1: [Name] (~Ns)
+**Purpose**: [one sentence]
+**Layout**: [FULL_CENTER / LEFT_RIGHT / GRID / PROGRESSIVE]
+
+### Visual elements
+- [Mobject: type, position, color]
+
+### Animation sequence
+1. [Animation] -- [what it reveals] (~Ns)
+
+### Subtitle
+"[text]"
+```
diff --git a/skills/creative/manim-video/references/troubleshooting.md b/skills/creative/manim-video/references/troubleshooting.md
new file mode 100644
index 000000000..98c63fd2b
--- /dev/null
+++ b/skills/creative/manim-video/references/troubleshooting.md
@@ -0,0 +1,135 @@
+# Troubleshooting
+
+## LaTeX Errors
+
+**Missing raw string** (the #1 error):
+```python
+# WRONG: MathTex("\\frac{1}{2}")  -- \\f is form-feed
+# RIGHT: MathTex(r"\frac{1}{2}")
+```
+
+**Unbalanced braces**: `MathTex(r"\frac{1}{2")` -- missing closing brace.
+
+**LaTeX not installed**: `which pdflatex` -- install texlive-full or mactex.
+
+**Missing package**: Add to preamble:
+```python
+tex_template = TexTemplate()
+tex_template.add_to_preamble(r"\usepackage{mathrsfs}")
+MathTex(r"\mathscr{L}", tex_template=tex_template)
+```
+
+## VGroup TypeError
+
+**Error:** `TypeError: Only values of type VMobject can be added as submobjects of VGroup`
+
+**Cause:** `Text()` objects are `Mobject`, not `VMobject`. Mixing `Text` with shapes in a `VGroup` fails on Manim CE v0.20+.
+
+```python
+# WRONG: Text is not a VMobject
+group = VGroup(circle, Text("Label"))
+
+# RIGHT: use Group for mixed types
+group = Group(circle, Text("Label"))
+
+# RIGHT: VGroup is fine for shapes-only
+shapes = VGroup(circle, square, arrow)
+
+# RIGHT: MathTex IS a VMobject — VGroup works
+equations = VGroup(MathTex(r"a"), MathTex(r"b"))
+```
+
+**Rule:** If the group contains any `Text()`, use `Group`. If it's all shapes or all `MathTex`, `VGroup` is fine.
+
+**FadeOut everything:** Always use `Group(*self.mobjects)`, not `VGroup(*self.mobjects)`:
+```python
+self.play(FadeOut(Group(*self.mobjects)))  # safe for mixed types
+```
+
+## Group save_state() / restore() Not Supported
+
+**Error:** `NotImplementedError: Please override in a child class.`
+
+**Cause:** `Group.save_state()` and `Group.restore()` are not implemented in Manim CE v0.20+. Only `VGroup` and individual `Mobject` subclasses support save/restore.
+
+```python
+# WRONG: Group doesn't support save_state
+group = Group(circle, Text("label"))
+group.save_state()  # NotImplementedError!
+
+# RIGHT: use FadeIn with shift/scale instead of save_state/restore
+self.play(FadeIn(group, shift=UP * 0.3, scale=0.8))
+
+# RIGHT: or save/restore on individual VMobjects
+circle.save_state()
+self.play(circle.animate.shift(RIGHT))
+self.play(Restore(circle))
+```
+
+## letter_spacing Is Not a Valid Parameter
+
+**Error:** `TypeError: Mobject.__init__() got an unexpected keyword argument 'letter_spacing'`
+
+**Cause:** `Text()` does not accept `letter_spacing`. Manim uses Pango for text rendering and does not expose kerning controls on `Text()`.
+
+```python
+# WRONG
+Text("HERMES", letter_spacing=6)
+
+# RIGHT: use MarkupText with Pango attributes for spacing control
+MarkupText('<span letter_spacing="6000">HERMES</span>', font_size=18)
+# Note: Pango letter_spacing is in 1/1024 of a point
+```
+
+## Animation Errors
+
+**Invisible animation** -- mobject never added:
+```python
+# WRONG: circle = Circle(); self.play(circle.animate.set_color(RED))
+# RIGHT: self.play(Create(circle)); self.play(circle.animate.set_color(RED))
+```
+
+**Transform confusion** -- after Transform(A, B), A is on screen, B is not. Use ReplacementTransform if you want B.
+
+**Duplicate animation** -- same mobject twice in one play():
+```python
+# WRONG: self.play(c.animate.shift(RIGHT), c.animate.set_color(RED))
+# RIGHT: self.play(c.animate.shift(RIGHT).set_color(RED))
+```
+
+**Updater fights animation**:
+```python
+mob.suspend_updating()
+self.play(mob.animate.shift(RIGHT))
+mob.resume_updating()
+```
+
+## Rendering Issues
+
+**Blurry output**: Using -ql (480p). Switch to -qm/-qh for final.
+
+**Slow render**: Use -ql during development. Reduce Surface resolution. Shorter self.wait().
+
+**Stale output**: `manim -ql --disable_caching script.py Scene`
+
+**ffmpeg concat fails**: All clips must match resolution/FPS/codec.
+
+## Common Mistakes
+
+**Text clips at edge**: `buff >= 0.5` for `.to_edge()`
+
+**Overlapping text**: Use `ReplacementTransform(old, new)`, not `Write(new)` on top.
+
+**Too crowded**: Max 5-6 elements visible. Split into scenes or use opacity layering.
+
+**No breathing room**: `self.wait(1.5)` minimum after reveals, `self.wait(2.0)` for key moments.
+
+**Missing background color**: Set `self.camera.background_color = BG` in every scene.
+
+## Debugging Strategy
+
+1. Render a still: `manim -ql -s script.py Scene` -- instant layout check
+2. Isolate the broken scene -- render only that one
+3. Replace `self.play()` with `self.add()` to see final state instantly
+4. Print positions: `print(mob.get_center())`
+5. Clear cache: delete `media/` directory
diff --git a/skills/creative/manim-video/references/visual-design.md b/skills/creative/manim-video/references/visual-design.md
new file mode 100644
index 000000000..e8dc09fe3
--- /dev/null
+++ b/skills/creative/manim-video/references/visual-design.md
@@ -0,0 +1,119 @@
+# Visual Design Principles
+
+## 12 Core Principles
+
+1. **Geometry Before Algebra** — Show the shape first, the equation second.
+2. **Opacity Layering** — PRIMARY=1.0, CONTEXT=0.4, GRID=0.15. Direct attention through brightness.
+3. **One New Idea Per Scene** — Each scene introduces exactly one concept.
+4. **Spatial Consistency** — Same concept occupies the same screen region throughout.
+5. **Color = Meaning** — Assign colors to concepts, not mobjects. If velocity is blue, it stays blue.
+6. **Progressive Disclosure** — Show simplest version first, add complexity incrementally.
+7. **Transform, Don't Replace** — Use Transform/ReplacementTransform to show connections.
+8. **Breathing Room** — `self.wait(1.5)` minimum after showing something new.
+9. **Visual Weight Balance** — Don't cluster everything on one side.
+10. **Consistent Motion Vocabulary** — Pick a small set of animation types and reuse them.
+11. **Dark Background, Light Content** — #1C1C1C to #2D2B55 backgrounds maximize contrast.
+12. **Intentional Empty Space** — Leave at least 15% of the frame empty.
+
+## Layout Templates
+
+### FULL_CENTER
+One main element centered, title above, note below.
+Best for: single equations, single diagrams, title cards.
+
+### LEFT_RIGHT
+Two elements side by side at x=-3.5 and x=3.5.
+Best for: equation + visual, before/after, comparison.
+
+### TOP_BOTTOM
+Main element at y=1.5, supporting content at y=-1.5.
+Best for: concept + examples, theorem + cases.
+
+### GRID
+Multiple elements via `arrange_in_grid()`.
+Best for: comparison matrices, multi-step processes.
+
+### PROGRESSIVE
+Elements appear one at a time, arranged DOWN with aligned_edge=LEFT.
+Best for: algorithms, proofs, step-by-step processes.
+
+### ANNOTATED_DIAGRAM
+Central diagram with floating labels connected by arrows.
+Best for: architecture diagrams, annotated figures.
+
+## Color Palettes
+
+### Classic 3B1B
+```python
+BG="#1C1C1C"; PRIMARY=BLUE; SECONDARY=GREEN; ACCENT=YELLOW; HIGHLIGHT=RED
+```
+
+### Warm Academic
+```python
+BG="#2D2B55"; PRIMARY="#FF6B6B"; SECONDARY="#FFD93D"; ACCENT="#6BCB77"
+```
+
+### Neon Tech
+```python
+BG="#0A0A0A"; PRIMARY="#00F5FF"; SECONDARY="#FF00FF"; ACCENT="#39FF14"
+```
+
+## Font Selection
+
+Manim's default `Text()` uses the system's default sans-serif font, which often renders with poor kerning. Always specify a font explicitly.
+
+### Recommended Fonts
+
+| Use case | Font | Fallback |
+|----------|------|----------|
+| Body text, titles | `"Inter"`, `"SF Pro Display"` | `"Helvetica Neue"`, `"Arial"` |
+| Code, terminal | `"JetBrains Mono"`, `"SF Mono"` | `"Menlo"`, `"Courier New"` |
+| Math labels | Use `MathTex` (renders via LaTeX, not system fonts) | — |
+
+```python
+# Clean body text
+title = Text("Gradient Descent", font_size=48, font="Inter", weight=BOLD)
+
+# Monospaced code
+code_label = Text("loss.backward()", font_size=24, font="JetBrains Mono")
+
+# Math — always use MathTex, not Text
+equation = MathTex(r"\nabla L = \frac{\partial L}{\partial w}")
+```
+
+### Font Availability
+
+Not all fonts are installed on all systems. Manim falls back silently to a default if the font is missing. Use widely available fonts:
+- **macOS**: SF Pro Display, SF Mono, Menlo, Helvetica Neue
+- **Linux**: DejaVu Sans, Liberation Sans, Ubuntu, Noto Sans
+- **Cross-platform**: Inter (install via Google Fonts), JetBrains Mono (install from jetbrains.com)
+
+For maximum portability, use `"Helvetica Neue"` (body) and `"Menlo"` (code) — both available on macOS and have Linux equivalents.
+
+### Fine-Grained Text Control
+
+`Text()` does not support `letter_spacing` or kerning parameters. For fine control, use `MarkupText` with Pango attributes:
+
+```python
+# Letter spacing (Pango units: 1/1024 of a point)
+MarkupText('<span letter_spacing="6000">HERMES</span>', font_size=18, font="Menlo")
+
+# Bold specific words
+MarkupText('This is <b>important</b>', font_size=24)
+
+# Color specific words
+MarkupText('Red <span foreground="#FF6B6B">warning</span>', font_size=24)
+```
+
+### Text Rendering Quality
+
+Manim's text rendering quality depends heavily on output resolution. At `-ql` (480p), text kerning looks noticeably poor. Always preview text-heavy scenes at `-qm` (720p) or higher. See `references/rendering.md` for quality preset guidance.
+
+## Visual Hierarchy Checklist
+
+For every frame:
+1. What is the ONE thing to look at? (brightest/largest)
+2. What is context? (dimmed to 0.3-0.4)
+3. What is structural? (dimmed to 0.15)
+4. Enough empty space? (>15%)
+5. All text readable at phone size?
diff --git a/skills/creative/manim-video/scripts/setup.sh b/skills/creative/manim-video/scripts/setup.sh
new file mode 100755
index 000000000..0e4676f24
--- /dev/null
+++ b/skills/creative/manim-video/scripts/setup.sh
@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+set -euo pipefail
+G="\033[0;32m"; R="\033[0;31m"; N="\033[0m"
+ok() { echo -e "  ${G}+${N} $1"; }
+fail() { echo -e "  ${R}x${N} $1"; }
+echo ""; echo "Manim Video Skill — Setup Check"; echo ""
+errors=0
+command -v python3 &>/dev/null && ok "Python $(python3 --version 2>&1 | awk '{print $2}')" || { fail "Python 3 not found"; errors=$((errors+1)); }
+python3 -c "import manim" 2>/dev/null && ok "Manim $(manim --version 2>&1 | head -1)" || { fail "Manim not installed: pip install manim"; errors=$((errors+1)); }
+command -v pdflatex &>/dev/null && ok "LaTeX (pdflatex)" || { fail "LaTeX not found (macOS: brew install --cask mactex-no-gui)"; errors=$((errors+1)); }
+command -v ffmpeg &>/dev/null && ok "ffmpeg" || { fail "ffmpeg not found"; errors=$((errors+1)); }
+echo ""
+[ $errors -eq 0 ] && echo -e "${G}All prerequisites satisfied.${N}" || echo -e "${R}$errors prerequisite(s) missing.${N}"
+echo ""