diff --git a/skills/marimo-pair/SKILL.md b/skills/marimo-pair/SKILL.md
index 07777ae..1d6e69f 100644
--- a/skills/marimo-pair/SKILL.md
+++ b/skills/marimo-pair/SKILL.md
@@ -250,6 +250,10 @@ Submit the code that belongs in the cell.
 - **Define public names intentionally** - use public names for values later
   cells should reference. Use private `_name` bindings or function locals for
   same-cell intermediates.
+- **Define each public name once** - a public name has one owning cell.
+  Reassigning it in another cell fails with `Multiply-defined names`; edit the
+  owning cell or give the result a new name. See
+  [gotchas.md](reference/gotchas.md).
 - **Run cells deliberately** - `create_cell` and `edit_cell` change structure
   only. Queue `ctx.run_cell(...)` when the cell should execute.
 
@@ -286,6 +290,6 @@ For designing custom visual or interactive output, see
 
 - [execution-context.md](reference/execution-context.md) — scripts, MCP, auth, startup, and shell quoting
 - [finding-marimo.md](reference/finding-marimo.md) — choosing the right marimo invocation
-- [gotchas.md](reference/gotchas.md) — cached module proxies and notebook traps
+- [gotchas.md](reference/gotchas.md) — name redefinition, cached module proxies, and notebook traps
 - [rich-representations.md](reference/rich-representations.md) — custom widgets and visualizations
 - [notebook-improvements.md](reference/notebook-improvements.md) — improving existing notebooks
diff --git a/skills/marimo-pair/reference/gotchas.md b/skills/marimo-pair/reference/gotchas.md
index d6e6a22..aee8683 100644
--- a/skills/marimo-pair/reference/gotchas.md
+++ b/skills/marimo-pair/reference/gotchas.md
@@ -17,11 +17,33 @@ mo.ui.table(_df)               # NameError: name '_df' is not defined
 
 **Fix:** Either merge both into one cell, or use a non-private name (`df`).
 
+## Redefining a public name across cells
+
+Each public name has one owning cell. Defining it again in another cell fails
+with `Multiply-defined names`. This is easy to hit when building a notebook
+incrementally — a second cell reassigns `df`, `results`, `data`, etc.
+
+```python
+# Cell A
+df = pd.read_csv("data.csv")
+
+# Cell B — FAILS: df already defined in Cell A
+df = df.dropna()               # Multiply-defined names: df
+```
+
+**Fix — pick one:**
+
+- **Edit the owning cell** if the step belongs there (`ctx.edit_cell`).
+- **Use a new name** when later cells need the result (`clean = df.dropna()`).
+- **Use a private `_` name** for a throwaway intermediate (`_clean = df.dropna()`).
+
+`ctx.graph.cells[cid].defs` shows what a cell already owns.
+
 ## Duplicate public imports across cells
 
-marimo enforces single-definition: a public name (like `pd`) can only be
-defined in one cell. If two cells both `import pandas as pd`, you get a
-`Multiply-defined names` error at validation.
+The same single-definition rule applies to imports: a public name (like `pd`)
+can only be defined in one cell. If two cells both `import pandas as pd`, you
+get a `Multiply-defined names` error at validation.
 
 **Fix:** Use a `_` prefix on the second import (`import pandas as _pd`) or
 consolidate imports into a shared cell.
diff --git a/skills/marimo-pair/reference/notebook-improvements.md b/skills/marimo-pair/reference/notebook-improvements.md
index c6d8999..c57e966 100644
--- a/skills/marimo-pair/reference/notebook-improvements.md
+++ b/skills/marimo-pair/reference/notebook-improvements.md
@@ -18,8 +18,14 @@ cells. It's the place for module imports. Consolidating imports here keeps
 the notebook clean and ensures every cell can rely on those modules being
 available.
 
-First check if the notebook already has a cell named `"setup"`. If not,
-create one and hoist scattered imports into it:
+**The setup cell cannot reference other cells' variables.** It runs first, so
+it must be self-contained: imports, constants, and definitions that depend only
+on each other. Reading a name defined elsewhere (e.g. `df`, a UI element) fails
+with `The setup cell cannot have references`.
+
+First check if the notebook already has a cell named `"setup"`. If not, create
+one and hoist scattered imports into it. `name="setup"` auto-positions the cell
+first — no `before`/`after` needed:
 
 ```python
 cid = ctx.create_cell('''import polars as pl
@@ -29,8 +35,8 @@ import traitlets''', name="setup")
 ctx.run_cell(cid)
 ```
 
-If a setup cell already exists, use `ctx.edit_cell("setup", code=...)` and
-`ctx.run_cell("setup")` to modify and re-run it.
+If a setup cell already exists, `create_cell(name="setup")` raises `ValueError`;
+use `ctx.edit_cell("setup", code=...)` and `ctx.run_cell("setup")` instead.
 
 ## Lift reusable functions into their own cells