docs(prompting): level 4 — capability chapters framed as additive

Add entry bridges (each naming a specific Level 1-3 artifact the
capability slots into) and literal exit bridges across the 7 Level 4
Substance pages, per the novice-to-advanced restructure plan.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

docs/prompting/overlays-and-lower-thirds.mdx

@@ -3,6 +3,8 @@ title: Overlays and lower thirds
 description: "Prompt named lower-third and social-post overlay blocks with timing, copy, and brand tone."
 ---
 
+Level 1's founder-clip.mp4 got named lower-thirds and card overlays through `/talking-head-recut`, which designs bespoke cards synced to that specific transcript. This chapter is the reverse case: ready-made lower-third and social-overlay blocks you drop into a composition you're building from scratch, no existing footage required — the same vocabulary, pointed at a scene instead of a shot.
+
 ## What overlays do and when they trigger
 
 Overlays are timed blocks that sit on top of your footage or scene — a lower third that names a speaker, a broadcast ticker, or a replica social-media card. Because each is a timed clip, prompts trigger this layer when you ask to *add* something *at* a moment: "add a lower third at 0:03 with the name and title," "show an animated tweet during the intro," "put a Spotify now-playing card in the corner." Give the timestamp, the copy, and the tone; the agent places the block on a track above the footage.
@@ -101,3 +103,5 @@ Quote the exact copy — unquoted names and titles get paraphrased (see [anatomy
 **Don't invent overlay names.** Only the blocks in the [Social Overlays](/catalog/blocks/x-post) and [Lower Thirds](/catalog/blocks/lt-clean-bar) groups exist.
 - ❌ `add a linkedin-post overlay`
 - ✅ pick a real block, or describe the card and let the agent build a custom one in a freeform composition
+
+*Next: [Caption styles](/prompting/captions-catalog) — the same timed-block pattern, tuned to on-screen text instead of name cards and social replicas.*