diff --git a/skills/creative/manim-video/SKILL.md b/skills/creative/manim-video/SKILL.md
index 15bc3d3860..5c82526fc9 100644
--- a/skills/creative/manim-video/SKILL.md
+++ b/skills/creative/manim-video/SKILL.md
@@ -234,3 +234,8 @@ Always iterate at `-ql`. Only render `-qh` for final output.
 | `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 |
+| `references/animation-design-thinking.md` | When to animate vs show static, decomposition, pacing, narration sync |
+| `references/updaters-and-trackers.md` | ValueTracker, add_updater, always_redraw, time-based updaters, patterns |
+| `references/paper-explainer.md` | Turning research papers into animations — workflow, templates, domain patterns |
+| `references/decorations.md` | SurroundingRectangle, Brace, arrows, DashedLine, Angle, annotation lifecycle |
+| `references/production-quality.md` | Pre-code, pre-render, post-render checklists, spatial layout, color, tempo |
diff --git a/skills/creative/manim-video/references/animation-design-thinking.md b/skills/creative/manim-video/references/animation-design-thinking.md
new file mode 100644
index 0000000000..2ef3739aa0
--- /dev/null
+++ b/skills/creative/manim-video/references/animation-design-thinking.md
@@ -0,0 +1,161 @@
+# Animation Design Thinking
+
+How to decide WHAT to animate and HOW to structure it — before writing any code.
+
+## Should I animate this?
+
+Not everything benefits from animation. Motion adds cognitive load. Bad animation is worse than a good static diagram.
+
+**Animate when:**
+- A sequence unfolds over time (algorithm steps, derivation, pipeline stages)
+- Spatial relationships change (transformation, deformation, rotation)
+- Something is built from parts (construction, assembly, accumulation)
+- You're comparing states (before/after, method A vs method B)
+- Temporal evolution is the point (training curves, wave propagation, gradient descent)
+
+**Show static when:**
+- The concept is a single labeled diagram (circuit, anatomy, architecture overview)
+- Motion would distract from spatial layout
+- The viewer needs to study it carefully (dense table, reference chart)
+- The concept is already intuitive from a well-labeled figure
+
+**Rule of thumb:** If you'd explain it with "first X, then Y, then Z" — animate it. If you'd explain it by pointing at parts of one picture — show it static.
+
+## Decomposing a concept into animation
+
+### Step 1: Write the narration first
+
+Before any code, write what the narrator would say. This determines:
+- **Order** — what concept comes first
+- **Duration** — how long each idea gets
+- **Visuals** — what the viewer must SEE when they HEAR each sentence
+
+A scene where the narration says "the gradient points uphill" must show a gradient arrow at that moment. If the visual doesn't match the audio, the viewer's brain splits attention and both tracks are lost.
+
+### Step 2: Identify visual beats
+
+A "beat" is a moment where something changes on screen. Mark each beat in your narration:
+
+```
+"Consider a function f of x."         → [BEAT: axes + curve appear]
+"At this point..."                     → [BEAT: dot appears on curve]
+"...the slope is positive."            → [BEAT: tangent line drawn]
+"So the gradient tells us to go left." → [BEAT: arrow points left, dot moves]
+```
+
+Each beat is one `self.play()` call or a small group of simultaneous animations.
+
+### Step 3: Choose the right tool per beat
+
+| Visual need | Manim approach |
+|-------------|----------------|
+| Object appears for first time | `Create`, `Write`, `FadeIn`, `GrowFromCenter` |
+| Object transforms into another | `Transform`, `ReplacementTransform`, `FadeTransform` |
+| Attention drawn to existing object | `Indicate`, `Circumscribe`, `Flash`, `ShowPassingFlash` |
+| Continuous relationship maintained | `add_updater`, `always_redraw`, `ValueTracker` |
+| Object leaves the scene | `FadeOut`, `Uncreate`, `ShrinkToCenter` |
+| Static context that stays visible | `self.add()` (no animation) |
+
+## Pacing: the universal mistake is too fast
+
+### Timing rules
+
+| Content type | Minimum on-screen time |
+|-------------|----------------------|
+| New equation appearing | 2.0s animation + 2.0s pause |
+| New concept label | 1.0s animation + 1.0s pause |
+| Key insight ("aha moment") | 2.5s animation + 3.0s pause |
+| Supporting annotation | 0.8s animation + 0.5s pause |
+| Scene transition (FadeOut all) | 0.5s animation + 0.3s pause |
+
+### Breathing room
+
+After every reveal, add `self.wait()`. The viewer needs time to:
+1. Read the new text
+2. Connect it to what's already on screen
+3. Form an expectation about what comes next
+
+**No wait = the viewer is always behind you.** They're still reading the equation when you've already started transforming it.
+
+### Tempo variation
+
+Monotonous pacing feels like a lecture. Vary the tempo:
+- **Slow build** for core concepts (long run_time, long pauses)
+- **Quick succession** for supporting details (short run_time, minimal pauses)
+- **Dramatic pause** before the key reveal (extra `self.wait(2.0)` before the "aha")
+- **Rapid montage** for "and this applies to X, Y, Z..." sequences (`LaggedStart` with tight lag_ratio)
+
+## Narration synchronization
+
+### The "see then hear" principle
+
+The visual should appear slightly BEFORE the narration describes it. When the viewer sees a circle appear and THEN hears "consider a circle," the visual primes their brain for the concept. The reverse — hearing first, seeing second — creates confusion because they're searching the screen for something that isn't there yet.
+
+### Practical timing
+
+```python
+# Scene duration should match narration duration.
+# If narration for this scene is 8 seconds:
+# Total animation run_times + total self.wait() times = ~8 seconds.
+
+# Use manim-voiceover for automatic sync:
+with self.voiceover(text="The gradient points downhill") as tracker:
+    self.play(GrowArrow(gradient_arrow), run_time=tracker.duration)
+```
+
+## Equation decomposition strategy
+
+### The "dim and reveal" pattern
+
+When building a complex equation step by step:
+1. Show the full equation dimmed at `opacity=0.2` (sets expectation for where you're going)
+2. Highlight the first term at full opacity
+3. Explain it
+4. Highlight the next term, dim the first to `0.5` (it's now context)
+5. Repeat until the full equation is bright
+
+This is better than building left-to-right because the viewer always sees the destination.
+
+### Term ordering
+
+Animate terms in the order the viewer needs to understand them, not in the order they appear in the equation. For `E = mc²`:
+- Show `E` (the thing we want to know)
+- Then `m` (the input)
+- Then `c²` (the constant that makes it work)
+- Then the `=` (connecting them)
+
+## Architecture and pipeline diagrams
+
+### Box granularity
+
+The most common mistake: too many boxes. Each box is a concept the viewer must track. Five boxes with clear labels beats twelve boxes with abbreviations.
+
+**Rule:** If two consecutive boxes could be labeled "X" and "process X output," merge them into one box.
+
+### Animation strategy
+
+Build pipelines left-to-right (or top-to-bottom) with arrows connecting them:
+1. First box appears alone → explain it
+2. Arrow grows from first to second → "the output feeds into..."
+3. Second box appears → explain it
+4. Repeat
+
+Then show data flowing through: `ShowPassingFlash` along the arrows, or a colored dot traversing the path.
+
+### The zoom-and-return pattern
+
+For complex systems:
+1. Show the full overview (all boxes, small)
+2. Zoom into one box (`MovingCameraScene.camera.frame.animate`)
+3. Expand that box into its internal components
+4. Zoom back out to the overview
+5. Zoom into the next box
+
+## Common design mistakes
+
+1. **Animating everything at once.** The viewer can track 1-2 simultaneous animations. More than that and nothing registers.
+2. **No visual hierarchy.** Everything at the same opacity/size/color means nothing stands out. Use opacity layering.
+3. **Equations without context.** An equation appearing alone means nothing. Always show the geometric/visual interpretation first or simultaneously.
+4. **Skipping the "why."** Showing HOW a transformation works without WHY it matters. Add a sentence/label explaining the purpose.
+5. **Identical pacing throughout.** Every animation at run_time=1.5, every wait at 1.0. Vary it.
+6. **Forgetting the audience.** A video for high schoolers needs different pacing and complexity than one for PhD students. Decide the audience in the planning phase.
diff --git a/skills/creative/manim-video/references/decorations.md b/skills/creative/manim-video/references/decorations.md
new file mode 100644
index 0000000000..4c89fe7d83
--- /dev/null
+++ b/skills/creative/manim-video/references/decorations.md
@@ -0,0 +1,202 @@
+# Decorations and Visual Polish
+
+Decorations are mobjects that annotate, highlight, or frame other mobjects. They turn a technically correct animation into a visually polished one.
+
+## SurroundingRectangle
+
+Draws a rectangle around any mobject. The go-to for highlighting:
+
+```python
+highlight = SurroundingRectangle(
+    equation[2],            # the term to highlight
+    color=YELLOW,
+    buff=0.15,              # padding between content and border
+    corner_radius=0.1,      # rounded corners
+    stroke_width=2
+)
+self.play(Create(highlight))
+self.wait(1)
+self.play(FadeOut(highlight))
+```
+
+### Around part of an equation
+
+```python
+eq = MathTex(r"E", r"=", r"m", r"c^2")
+box = SurroundingRectangle(eq[2:], color=YELLOW, buff=0.1)  # highlight "mc²"
+label = Text("mass-energy", font_size=18, font="Menlo", color=YELLOW)
+label.next_to(box, DOWN, buff=0.2)
+self.play(Create(box), FadeIn(label))
+```
+
+## BackgroundRectangle
+
+Semi-transparent background behind text for readability over complex scenes:
+
+```python
+bg = BackgroundRectangle(equation, fill_opacity=0.7, buff=0.2, color=BLACK)
+self.play(FadeIn(bg), Write(equation))
+
+# Or using set_stroke for a "backdrop" effect on the text itself:
+label.set_stroke(BLACK, width=5, background=True)
+```
+
+The `set_stroke(background=True)` approach is cleaner for text labels over graphs/diagrams.
+
+## Brace and BraceLabel
+
+Curly braces that annotate sections of a diagram or equation:
+
+```python
+brace = Brace(equation[2:4], DOWN, color=YELLOW)
+brace_label = brace.get_text("these terms", font_size=20)
+self.play(GrowFromCenter(brace), FadeIn(brace_label))
+
+# Between two specific points
+brace = BraceBetweenPoints(point_a, point_b, direction=UP)
+```
+
+### Brace placement
+
+```python
+# Below a group
+Brace(group, DOWN)
+# Above a group
+Brace(group, UP)
+# Left of a group
+Brace(group, LEFT)
+# Right of a group
+Brace(group, RIGHT)
+```
+
+## Arrows for Annotation
+
+### Straight arrows pointing to mobjects
+
+```python
+arrow = Arrow(
+    start=label.get_bottom(),
+    end=target.get_top(),
+    color=YELLOW,
+    stroke_width=2,
+    buff=0.1,                    # gap between arrow tip and target
+    max_tip_length_to_length_ratio=0.15  # small arrowhead
+)
+self.play(GrowArrow(arrow), FadeIn(label))
+```
+
+### Curved arrows
+
+```python
+arrow = CurvedArrow(
+    start_point=source.get_right(),
+    end_point=target.get_left(),
+    angle=PI/4,                  # curve angle
+    color=PRIMARY
+)
+```
+
+### Labeling with arrows
+
+```python
+# LabeledArrow: arrow with built-in text label
+arr = LabeledArrow(
+    Text("gradient", font_size=16, font="Menlo"),
+    start=point_a, end=point_b, color=RED
+)
+```
+
+## DashedLine and DashedVMobject
+
+```python
+# Dashed line (for asymptotes, construction lines, implied connections)
+asymptote = DashedLine(
+    axes.c2p(2, -3), axes.c2p(2, 3),
+    color=YELLOW, dash_length=0.15
+)
+
+# Make any VMobject dashed
+dashed_circle = DashedVMobject(Circle(radius=2, color=BLUE), num_dashes=30)
+```
+
+## Angle and RightAngle Markers
+
+```python
+line1 = Line(ORIGIN, RIGHT * 2)
+line2 = Line(ORIGIN, UP * 2 + RIGHT)
+
+# Angle arc between two lines
+angle = Angle(line1, line2, radius=0.5, color=YELLOW)
+angle_value = angle.get_value()  # radians
+
+# Right angle marker (the small square)
+right_angle = RightAngle(line1, Line(ORIGIN, UP * 2), length=0.3, color=WHITE)
+```
+
+## Cross (strikethrough)
+
+Mark something as wrong or deprecated:
+
+```python
+cross = Cross(old_equation, color=RED, stroke_width=4)
+self.play(Create(cross))
+# Then show the correct version
+```
+
+## Underline
+
+```python
+underline = Underline(important_text, color=ACCENT, stroke_width=3)
+self.play(Create(underline))
+```
+
+## Color Highlighting Workflow
+
+### Method 1: At creation with t2c
+
+```python
+text = Text("The gradient is negative here", t2c={"gradient": BLUE, "negative": RED})
+```
+
+### Method 2: set_color_by_tex after creation
+
+```python
+eq = MathTex(r"\nabla L = -\frac{\partial L}{\partial w}")
+eq.set_color_by_tex(r"\nabla", BLUE)
+eq.set_color_by_tex(r"\partial", RED)
+```
+
+### Method 3: Index into submobjects
+
+```python
+eq = MathTex(r"a", r"+", r"b", r"=", r"c")
+eq[0].set_color(RED)    # "a"
+eq[2].set_color(BLUE)   # "b"
+eq[4].set_color(GREEN)  # "c"
+```
+
+## Combining Annotations
+
+Layer multiple annotations for emphasis:
+
+```python
+# Highlight a term, add a brace, and an arrow — in sequence
+box = SurroundingRectangle(eq[2], color=YELLOW, buff=0.1)
+brace = Brace(eq[2], DOWN, color=YELLOW)
+label = brace.get_text("learning rate", font_size=18)
+
+self.play(Create(box))
+self.wait(0.5)
+self.play(FadeOut(box), GrowFromCenter(brace), FadeIn(label))
+self.wait(1.5)
+self.play(FadeOut(brace), FadeOut(label))
+```
+
+### The annotation lifecycle
+
+Annotations should follow a rhythm:
+1. **Appear** — draw attention (Create, GrowFromCenter)
+2. **Hold** — viewer reads and understands (self.wait)
+3. **Disappear** — clear the stage for the next thing (FadeOut)
+
+Never leave annotations on screen indefinitely — they become visual noise once their purpose is served.
diff --git a/skills/creative/manim-video/references/paper-explainer.md b/skills/creative/manim-video/references/paper-explainer.md
new file mode 100644
index 0000000000..9088ffcae3
--- /dev/null
+++ b/skills/creative/manim-video/references/paper-explainer.md
@@ -0,0 +1,255 @@
+# Paper Explainer Workflow
+
+How to turn a research paper into an animated explainer video.
+
+## Why animate a paper?
+
+A research paper is optimized for precision and completeness. A video is optimized for understanding and retention. The translation is NOT "read the paper aloud with pictures" — it's "extract the core insight and make it feel obvious through visual storytelling."
+
+The paper has one job: prove the claim is true. The video has a different job: make the viewer understand WHY the claim is true, and WHY it matters.
+
+## Who is watching?
+
+Before anything, decide the audience:
+
+| Audience | Prerequisites | Pacing | Depth |
+|----------|--------------|--------|-------|
+| General public | None | Slow, many analogies | Intuition only, skip proofs |
+| Undergrad students | Basic math/CS | Medium, some formalism | Key equations, skip derivations |
+| Grad students / researchers | Domain knowledge | Faster, more notation | Full equations, sketch proofs |
+
+This determines everything: vocabulary, pacing, which sections to animate, how much math to show.
+
+## The 5-minute template
+
+Most paper explainers fit this structure (scale times proportionally for longer videos):
+
+| Section | Duration | Purpose |
+|---------|----------|---------|
+| **Hook** | 0:00-0:30 | Surprising result or provocative question |
+| **Problem** | 0:30-1:30 | What was broken/missing before this paper |
+| **Key insight** | 1:30-3:00 | The core idea, explained visually |
+| **How it works** | 3:00-4:00 | Method/algorithm, simplified |
+| **Evidence** | 4:00-4:30 | Key result that proves it works |
+| **Implications** | 4:30-5:00 | Why it matters, what it enables |
+
+### What to skip
+
+- Related work survey → one sentence: "Previous approaches did X, which had problem Y"
+- Implementation details → skip unless they're the contribution
+- Ablation studies → show one chart at most
+- Proofs → show the key step, not the full proof
+- Hyperparameter tuning → skip entirely
+
+### What to expand
+
+- The core insight → this gets the most screen time
+- Geometric/visual intuition → if the paper has math, show what it MEANS
+- Before/after comparison → the most compelling evidence
+
+## Pre-code workflow
+
+### Gate 1: Narration script
+
+Write the full narration before any code. Every sentence maps to a visual beat. If you can't write the narration, you don't understand the paper well enough to animate it.
+
+```markdown
+## Hook (30s)
+"What if I told you that a model with 7 billion parameters can outperform
+one with 70 billion — if you train it on the right data?"
+
+## Problem (60s)
+"The standard approach is to scale up. More parameters, more compute.
+[VISUAL: bar chart showing model sizes growing exponentially]
+But Chinchilla showed us that most models are undertrained..."
+```
+
+### Gate 2: Scene list
+
+After the narration, break it into scenes. Each scene is one Manim class.
+
+```markdown
+Scene 1: Hook — surprising stat with animated counter
+Scene 2: Problem — model size bar chart growing
+Scene 3: Key insight — training data vs parameters, animated 2D plot
+Scene 4: Method — pipeline diagram building left to right
+Scene 5: Results — before/after comparison with animated bars
+Scene 6: Closing — implications text
+```
+
+### Gate 3: Style constants
+
+Before coding scenes, define the visual language:
+
+```python
+# style.py — import in every scene file
+BG = "#0D1117"
+PRIMARY = "#58C4DD"
+SECONDARY = "#83C167"
+ACCENT = "#FFFF00"
+HIGHLIGHT = "#FF6B6B"
+MONO = "Menlo"
+
+# Color meanings for THIS paper
+MODEL_COLOR = PRIMARY      # "the model"
+DATA_COLOR = SECONDARY     # "training data"
+BASELINE_COLOR = HIGHLIGHT # "previous approach"
+RESULT_COLOR = ACCENT      # "our result"
+```
+
+## First-principles equation explanation
+
+When the paper has a key equation, don't just show it — build it from intuition:
+
+### The "what would you do?" pattern
+
+1. Pose the problem in plain language
+2. Ask what the simplest solution would be
+3. Show why it doesn't work (animate the failure)
+4. Introduce the paper's solution as the fix
+5. THEN show the equation — it now feels earned
+
+```python
+# Scene: Why we need attention (for a Transformer paper)
+# Step 1: "How do we let each word look at every other word?"
+# Step 2: Show naive approach (fully connected = O(n²) everything)
+# Step 3: Show it breaks (information overload, no selectivity)
+# Step 4: "What if each word could CHOOSE which words to attend to?"
+# Step 5: Show attention equation — Q, K, V now mean something
+```
+
+### Equation reveal strategy
+
+```python
+# Show equation dimmed first (full destination)
+eq = MathTex(r"Attention(Q,K,V) = softmax\left(\frac{QK^T}{\sqrt{d_k}}\right)V")
+eq.set_opacity(0.15)
+self.play(FadeIn(eq))
+
+# Highlight Q, K, V one at a time with color + label
+for part, color, label_text in [
+    (r"Q", PRIMARY, "Query: what am I looking for?"),
+    (r"K", SECONDARY, "Key: what do I contain?"),
+    (r"V", ACCENT, "Value: what do I output?"),
+]:
+    eq.set_color_by_tex(part, color)
+    label = Text(label_text, font_size=18, color=color, font=MONO)
+    # position label, animate it, wait, then dim it
+```
+
+## Building architecture diagrams
+
+### The progressive build pattern
+
+Don't show the full architecture at once. Build it:
+
+1. First component appears alone → explain
+2. Arrow grows → "this feeds into..."
+3. Second component appears → explain
+4. Repeat until complete
+
+```python
+# Component factory
+def make_box(label, color, width=2.0, height=0.8):
+    box = RoundedRectangle(corner_radius=0.1, width=width, height=height,
+                           color=color, fill_opacity=0.1, stroke_width=1.5)
+    text = Text(label, font_size=18, font=MONO, color=color).move_to(box)
+    return Group(box, text)
+
+encoder = make_box("Encoder", PRIMARY)
+decoder = make_box("Decoder", SECONDARY).next_to(encoder, RIGHT, buff=1.5)
+arrow = Arrow(encoder.get_right(), decoder.get_left(), color=DIM, stroke_width=1.5)
+
+self.play(FadeIn(encoder))
+self.wait(1)  # explain encoder
+self.play(GrowArrow(arrow))
+self.play(FadeIn(decoder))
+self.wait(1)  # explain decoder
+```
+
+### Data flow animation
+
+After building the diagram, show data moving through it:
+
+```python
+# Dot traveling along the pipeline
+data_dot = Dot(color=ACCENT, radius=0.1).move_to(encoder)
+self.play(FadeIn(data_dot))
+self.play(MoveAlongPath(data_dot, arrow), run_time=1)
+self.play(data_dot.animate.move_to(decoder), run_time=0.5)
+self.play(Flash(data_dot.get_center(), color=ACCENT), run_time=0.3)
+```
+
+## Animating results
+
+### Bar chart comparison (most common)
+
+```python
+# Before/after bars
+before_data = [45, 52, 38, 61]
+after_data = [78, 85, 72, 91]
+labels = ["Task A", "Task B", "Task C", "Task D"]
+
+before_chart = BarChart(before_data, bar_names=labels,
+    y_range=[0, 100, 20], bar_colors=[HIGHLIGHT]*4).scale(0.6).shift(LEFT*3)
+after_chart = BarChart(after_data, bar_names=labels,
+    y_range=[0, 100, 20], bar_colors=[SECONDARY]*4).scale(0.6).shift(RIGHT*3)
+
+before_label = Text("Baseline", font_size=20, color=HIGHLIGHT, font=MONO)
+after_label = Text("Ours", font_size=20, color=SECONDARY, font=MONO)
+
+# Reveal baseline first, then ours (dramatic comparison)
+self.play(Create(before_chart), FadeIn(before_label))
+self.wait(1.5)
+self.play(Create(after_chart), FadeIn(after_label))
+self.wait(0.5)
+
+# Highlight the improvement
+improvement = Text("+35% avg", font_size=24, color=ACCENT, font=MONO)
+self.play(FadeIn(improvement))
+```
+
+### Training curve (for ML papers)
+
+```python
+tracker = ValueTracker(0)
+curve = always_redraw(lambda: axes.plot(
+    lambda x: 1 - 0.8 * np.exp(-x / 3),
+    x_range=[0, tracker.get_value()], color=PRIMARY
+))
+epoch_label = always_redraw(lambda: Text(
+    f"Epoch {int(tracker.get_value())}", font_size=18, font=MONO
+).to_corner(UR))
+
+self.add(curve, epoch_label)
+self.play(tracker.animate.set_value(10), run_time=5, rate_func=linear)
+```
+
+## Domain-specific patterns
+
+### ML papers
+- Show data flow through the model (animated pipeline)
+- Training curves with `ValueTracker`
+- Attention heatmaps as colored grids
+- Embedding space as 2D scatter (PCA/t-SNE visualization)
+- Loss landscape as 3D surface with gradient descent dot
+
+### Physics/math papers
+- Use `LinearTransformationScene` for linear algebra
+- Vector fields with `ArrowVectorField` / `StreamLines`
+- Phase spaces with `NumberPlane` + trajectories
+- Wave equations with time-parameterized plots
+
+### Systems/architecture papers
+- Pipeline diagrams built progressively
+- `ShowPassingFlash` for data flow along arrows
+- `ZoomedScene` for zooming into components
+- Before/after latency/throughput comparisons
+
+## Common mistakes
+
+1. **Trying to cover the whole paper.** A 5-minute video can explain ONE core insight well. Covering everything means explaining nothing.
+2. **Reading the abstract as narration.** Academic writing is designed for readers, not listeners. Rewrite in conversational language.
+3. **Showing notation without meaning.** Never show a symbol without first showing what it represents visually.
+4. **Skipping the motivation.** Jumping straight to "here's our method" without showing why the problem matters. The Problem section is what makes the viewer care.
+5. **Identical pacing throughout.** The hook and key insight need the most visual energy. The method section can be faster. Evidence should land with impact (pause after showing the big number).
diff --git a/skills/creative/manim-video/references/production-quality.md b/skills/creative/manim-video/references/production-quality.md
new file mode 100644
index 0000000000..1b371f89b0
--- /dev/null
+++ b/skills/creative/manim-video/references/production-quality.md
@@ -0,0 +1,190 @@
+# Production Quality Checklist
+
+Standards and checks for ensuring animation output is publication-ready.
+
+## Pre-Code Checklist
+
+Before writing any Manim code:
+
+- [ ] Narration script written with visual beats marked
+- [ ] Scene list with purpose, duration, and layout for each
+- [ ] Color palette defined with meaning assignments (`PRIMARY` = main concept, etc.)
+- [ ] `MONO = "Menlo"` set as the font constant
+- [ ] Target resolution and aspect ratio decided
+
+## Text Quality
+
+### Overlap prevention
+
+```python
+# RULE: buff >= 0.5 for edge text
+label.to_edge(DOWN, buff=0.5)     # GOOD
+label.to_edge(DOWN, buff=0.3)     # BAD — may clip
+
+# RULE: FadeOut previous before adding new at same position
+self.play(ReplacementTransform(note1, note2))  # GOOD
+self.play(Write(note2))                          # BAD — overlaps note1
+
+# RULE: Reduce font size for dense scenes
+# When > 4 text elements visible, use font_size=20 not 28
+```
+
+### Width enforcement
+
+Long text strings overflow the frame:
+
+```python
+# RULE: Set max width for any text that might be long
+text = Text("This is a potentially long description", font_size=22, font=MONO)
+if text.width > config.frame_width - 1.0:
+    text.set_width(config.frame_width - 1.0)
+```
+
+### Font consistency
+
+```python
+# RULE: Define MONO once, use everywhere
+MONO = "Menlo"
+
+# WRONG: mixing fonts
+Text("Title", font="Helvetica")
+Text("Label", font="Arial")
+Text("Code", font="Courier")
+
+# RIGHT: one font
+Text("Title", font=MONO, weight=BOLD, font_size=48)
+Text("Label", font=MONO, font_size=20)
+Text("Code", font=MONO, font_size=18)
+```
+
+## Spatial Layout
+
+### The coordinate budget
+
+The visible frame is approximately 14.2 wide × 8.0 tall (default 16:9). With mandatory margins:
+
+```
+Usable area: x ∈ [-6.5, 6.5], y ∈ [-3.5, 3.5]
+Top title zone: y ∈ [2.5, 3.5]
+Bottom note zone: y ∈ [-3.5, -2.5]
+Main content: y ∈ [-2.5, 2.5], x ∈ [-6.0, 6.0]
+```
+
+### Fill the frame
+
+Empty scenes look unfinished. If the main content is small, add context:
+- A dimmed grid/axes behind the content
+- A title/subtitle at the top
+- A source citation at the bottom
+- Decorative geometry at low opacity
+
+### Maximum simultaneous elements
+
+**Hard limit: 6 actively visible elements.** Beyond that, the viewer can't track everything. If you need more:
+- Dim old elements to opacity 0.3
+- Remove elements that have served their purpose
+- Split into two scenes
+
+## Animation Quality
+
+### Variety audit
+
+Check that no two consecutive scenes use the exact same:
+- Animation type (if Scene 3 uses Write for everything, Scene 4 should use FadeIn or Create)
+- Color emphasis (rotate through palette colors)
+- Layout (center, left-right, grid — alternate)
+- Pacing (if Scene 2 was slow and deliberate, Scene 3 can be faster)
+
+### Tempo curve
+
+A good video follows a tempo curve:
+
+```
+Slow ──→ Medium ──→ FAST (climax) ──→ Slow (conclusion)
+
+Scene 1: Slow (introduction, setup)
+Scene 2: Medium (building understanding)
+Scene 3: Medium-Fast (core content, lots of animation)
+Scene 4: FAST (montage of applications/results)
+Scene 5: Slow (conclusion, key takeaway)
+```
+
+### Transition quality
+
+Between scenes:
+- **Clean exit**: `self.play(FadeOut(Group(*self.mobjects)), run_time=0.5)`
+- **Brief pause**: `self.wait(0.3)` after fadeout, before next scene's first animation
+- **Never hard-cut**: always animate the transition
+
+## Color Quality
+
+### Dimming on dark backgrounds
+
+Colors that look vibrant on white look muddy on dark backgrounds (#0D1117, #1C1C1C). Test your palette:
+
+```python
+# Colors that work well on dark backgrounds:
+# Bright and saturated: #58C4DD, #83C167, #FFFF00, #FF6B6B
+# Colors that DON'T work: #666666 (invisible), #2244AA (too dark)
+
+# RULE: Structural elements (axes, grids) at opacity 0.15
+# Context elements at 0.3-0.4
+# Primary elements at 1.0
+```
+
+### Color meaning consistency
+
+Once a color is assigned a meaning, it keeps that meaning for the entire video:
+
+```python
+# If PRIMARY (#58C4DD) means "the model" in Scene 1,
+# it means "the model" in every scene.
+# Never reuse PRIMARY for a different concept later.
+```
+
+## Data Visualization Quality
+
+### Minimum requirements for charts
+
+- Axis labels on every axis
+- Y-axis range starts at 0 (or has a clear break indicator)
+- Bar/line colors match the legend
+- Numbers on notable data points (at least the maximum and the comparison point)
+
+### Animated counters
+
+When showing a number changing:
+```python
+# GOOD: DecimalNumber with smooth animation
+counter = DecimalNumber(0, font_size=48, num_decimal_places=0, font="Menlo")
+self.play(counter.animate.set_value(1000), run_time=3, rate_func=rush_from)
+
+# BAD: Text that jumps between values
+```
+
+## Pre-Render Checklist
+
+Before running `manim -qh`:
+
+- [ ] All scenes render without errors at `-ql`
+- [ ] Preview stills at `-qm` for text-heavy scenes (check kerning)
+- [ ] Background color set in every scene (`self.camera.background_color = BG`)
+- [ ] `add_subcaption()` or `subcaption=` on every significant animation
+- [ ] No text smaller than font_size=18
+- [ ] No text using proportional fonts (use monospace)
+- [ ] buff >= 0.5 on all `.to_edge()` calls
+- [ ] Clean exit (FadeOut all) at end of every scene
+- [ ] `self.wait()` after every reveal
+- [ ] Color constants used (no hardcoded hex strings in scene code)
+- [ ] All scenes use the same quality flag (don't mix `-ql` and `-qh`)
+
+## Post-Render Checklist
+
+After stitching the final video:
+
+- [ ] Watch the complete video at 1x speed — does it feel rushed anywhere?
+- [ ] Is there a moment where two things animate simultaneously and it's confusing?
+- [ ] Does every text label have enough time to be read?
+- [ ] Are transitions between scenes smooth (no black frames, no jarring cuts)?
+- [ ] Is the audio in sync with the visuals (if using voiceover)?
+- [ ] Is the Gibbs-like "first impression" good? The first 5 seconds determine if someone keeps watching
diff --git a/skills/creative/manim-video/references/updaters-and-trackers.md b/skills/creative/manim-video/references/updaters-and-trackers.md
new file mode 100644
index 0000000000..ae39463966
--- /dev/null
+++ b/skills/creative/manim-video/references/updaters-and-trackers.md
@@ -0,0 +1,260 @@
+# Updaters and Value Trackers
+
+## The problem updaters solve
+
+Normal animations are discrete: `self.play()` goes from state A to state B. But what if you need continuous relationships — a label that always hovers above a moving dot, or a line that always connects two points?
+
+Without updaters, you'd manually reposition every dependent object before every `self.play()`. Five animations that move a dot means five manual repositioning calls for the label. Miss one and it freezes in the wrong spot.
+
+Updaters let you declare a relationship ONCE. Manim calls the updater function EVERY FRAME (15-60 fps depending on quality) to enforce that relationship, no matter what else is happening.
+
+## ValueTracker: an invisible steering wheel
+
+A ValueTracker is an invisible Mobject that holds a single float. It never appears on screen. It exists so you can ANIMATE it while other objects REACT to its value.
+
+Think of it as a slider: drag the slider from 0 to 5, and every object wired to it responds in real time.
+
+```python
+tracker = ValueTracker(0)        # invisible, stores 0.0
+tracker.get_value()              # read: 0.0
+tracker.set_value(5)             # write: jump to 5.0 instantly
+tracker.animate.set_value(5)     # animate: smoothly interpolate to 5.0
+```
+
+### The three-step pattern
+
+Every ValueTracker usage follows this:
+
+1. **Create the tracker** (the invisible slider)
+2. **Create visible objects that READ the tracker** via updaters
+3. **Animate the tracker** — all dependents update automatically
+
+```python
+# Step 1: Create tracker
+x_tracker = ValueTracker(1)
+
+# Step 2: Create dependent objects
+dot = always_redraw(lambda: Dot(axes.c2p(x_tracker.get_value(), 0), color=YELLOW))
+v_line = always_redraw(lambda: axes.get_vertical_line(
+    axes.c2p(x_tracker.get_value(), func(x_tracker.get_value())), color=BLUE
+))
+label = always_redraw(lambda: DecimalNumber(x_tracker.get_value(), font_size=24)
+    .next_to(dot, UP))
+
+self.add(dot, v_line, label)
+
+# Step 3: Animate the tracker — everything follows
+self.play(x_tracker.animate.set_value(5), run_time=3)
+```
+
+## Types of updaters
+
+### Lambda updater (most common)
+
+Runs a function every frame, passing the mobject itself:
+
+```python
+# Label always stays above the dot
+label.add_updater(lambda m: m.next_to(dot, UP, buff=0.2))
+
+# Line always connects two points
+line.add_updater(lambda m: m.put_start_and_end_on(
+    point_a.get_center(), point_b.get_center()
+))
+```
+
+### Time-based updater (with dt)
+
+The second argument `dt` is the time since the last frame (~0.017s at 60fps):
+
+```python
+# Continuous rotation
+square.add_updater(lambda m, dt: m.rotate(0.5 * dt))
+
+# Continuous rightward drift
+dot.add_updater(lambda m, dt: m.shift(RIGHT * 0.3 * dt))
+
+# Oscillation
+dot.add_updater(lambda m, dt: m.move_to(
+    axes.c2p(m.get_center()[0], np.sin(self.time))
+))
+```
+
+Use `dt` updaters for physics simulations, continuous motion, and time-dependent effects.
+
+### always_redraw: full rebuild every frame
+
+Creates a new mobject from scratch each frame. More expensive than `add_updater` but handles cases where the mobject's structure changes (not just position/color):
+
+```python
+# Brace that follows a resizing square
+brace = always_redraw(Brace, square, UP)
+
+# Area under curve that updates as function changes
+area = always_redraw(lambda: axes.get_area(
+    graph, x_range=[0, x_tracker.get_value()], color=BLUE, opacity=0.3
+))
+
+# Label that reconstructs its text
+counter = always_redraw(lambda: Text(
+    f"n = {int(x_tracker.get_value())}", font_size=24, font="Menlo"
+).to_corner(UR))
+```
+
+**When to use which:**
+- `add_updater` — position, color, opacity changes (cheap, preferred)
+- `always_redraw` — when the shape/structure itself changes (expensive, use sparingly)
+
+## DecimalNumber: showing live values
+
+```python
+# Counter that tracks a ValueTracker
+tracker = ValueTracker(0)
+number = DecimalNumber(0, font_size=48, num_decimal_places=1, color=PRIMARY)
+number.add_updater(lambda m: m.set_value(tracker.get_value()))
+number.add_updater(lambda m: m.next_to(dot, RIGHT, buff=0.3))
+
+self.add(number)
+self.play(tracker.animate.set_value(100), run_time=3)
+```
+
+### Variable: the labeled version
+
+```python
+var = Variable(0, Text("x", font_size=24, font="Menlo"), num_decimal_places=2)
+self.add(var)
+self.play(var.tracker.animate.set_value(PI), run_time=2)
+# Displays: x = 3.14
+```
+
+## Removing updaters
+
+```python
+# Remove all updaters
+mobject.clear_updaters()
+
+# Suspend temporarily (during an animation that would fight the updater)
+mobject.suspend_updating()
+self.play(mobject.animate.shift(RIGHT))
+mobject.resume_updating()
+
+# Remove specific updater (if you stored a reference)
+def my_updater(m):
+    m.next_to(dot, UP)
+label.add_updater(my_updater)
+# ... later ...
+label.remove_updater(my_updater)
+```
+
+## Animation-based updaters
+
+### UpdateFromFunc / UpdateFromAlphaFunc
+
+These are ANIMATIONS (passed to `self.play`), not persistent updaters:
+
+```python
+# Call a function on each frame of the animation
+self.play(UpdateFromFunc(mobject, lambda m: m.next_to(moving_target, UP)), run_time=3)
+
+# With alpha (0 to 1) — useful for custom interpolation
+self.play(UpdateFromAlphaFunc(circle, lambda m, a: m.set_fill(opacity=a)), run_time=2)
+```
+
+### turn_animation_into_updater
+
+Convert a one-shot animation into a continuous updater:
+
+```python
+from manim import turn_animation_into_updater
+
+# This would normally play once — now it loops forever
+turn_animation_into_updater(Rotating(gear, rate=PI/4))
+self.add(gear)
+self.wait(5)  # gear rotates for 5 seconds
+```
+
+## Practical patterns
+
+### Pattern 1: Dot tracing a function
+
+```python
+tracker = ValueTracker(0)
+graph = axes.plot(np.sin, x_range=[0, 2*PI], color=PRIMARY)
+dot = always_redraw(lambda: Dot(
+    axes.c2p(tracker.get_value(), np.sin(tracker.get_value())),
+    color=YELLOW
+))
+tangent = always_redraw(lambda: axes.get_secant_slope_group(
+    x=tracker.get_value(), graph=graph, dx=0.01,
+    secant_line_color=HIGHLIGHT, secant_line_length=3
+))
+
+self.add(graph, dot, tangent)
+self.play(tracker.animate.set_value(2*PI), run_time=6, rate_func=linear)
+```
+
+### Pattern 2: Live area under curve
+
+```python
+tracker = ValueTracker(0.5)
+area = always_redraw(lambda: axes.get_area(
+    graph, x_range=[0, tracker.get_value()],
+    color=PRIMARY, opacity=0.3
+))
+area_label = always_redraw(lambda: DecimalNumber(
+    # Numerical integration
+    sum(func(x) * 0.01 for x in np.arange(0, tracker.get_value(), 0.01)),
+    font_size=24
+).next_to(axes, RIGHT))
+
+self.add(area, area_label)
+self.play(tracker.animate.set_value(4), run_time=5)
+```
+
+### Pattern 3: Connected diagram
+
+```python
+# Nodes that can be moved, with edges that auto-follow
+node_a = Dot(LEFT * 2, color=PRIMARY)
+node_b = Dot(RIGHT * 2, color=SECONDARY)
+edge = Line().add_updater(lambda m: m.put_start_and_end_on(
+    node_a.get_center(), node_b.get_center()
+))
+label = Text("edge", font_size=18, font="Menlo").add_updater(
+    lambda m: m.move_to(edge.get_center() + UP * 0.3)
+)
+
+self.add(node_a, node_b, edge, label)
+self.play(node_a.animate.shift(UP * 2), run_time=2)
+self.play(node_b.animate.shift(DOWN + RIGHT), run_time=2)
+# Edge and label follow automatically
+```
+
+### Pattern 4: Parameter exploration
+
+```python
+# Explore how a parameter changes a curve
+a_tracker = ValueTracker(1)
+curve = always_redraw(lambda: axes.plot(
+    lambda x: a_tracker.get_value() * np.sin(x),
+    x_range=[0, 2*PI], color=PRIMARY
+))
+param_label = always_redraw(lambda: Text(
+    f"a = {a_tracker.get_value():.1f}", font_size=24, font="Menlo"
+).to_corner(UR))
+
+self.add(curve, param_label)
+self.play(a_tracker.animate.set_value(3), run_time=3)
+self.play(a_tracker.animate.set_value(0.5), run_time=2)
+self.play(a_tracker.animate.set_value(1), run_time=1)
+```
+
+## Common mistakes
+
+1. **Updater fights animation:** If a mobject has an updater that sets its position, and you try to animate it elsewhere, the updater wins every frame. Suspend updating first.
+
+2. **always_redraw for simple moves:** If you only need to reposition, use `add_updater`. `always_redraw` reconstructs the entire mobject every frame — expensive and unnecessary for position tracking.
+
+3. **Forgetting to add to scene:** Updaters only run on mobjects that are in the scene. `always_redraw` creates the mobject but you still need `self.add()`.
+
+4. **Updater creates new mobjects without cleanup:** If your updater creates Text objects every frame, they accumulate. Use `always_redraw` (which handles cleanup) or update properties in-place.