Update to JuicyLucy Ads

{
  "description": "Overlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of the film, never a reserved bottom band you shift content up to avoid. Load when adding captions/subtitles to a talking-head or launch video, when deciding whether a phrase should be dropped, ride the verbatim rail, or be promoted to a scarce embedded climax, when laying out a composition that will carry captions (do NOT reserve a keep-out band), or when centering a composition on the true frame center under captions. Quotes the rail+embed model from embedded-captions and constraint",
  "included_files": [],
  "name": "captions-overlay",
  "skill_md_contents": "---\nname: captions-overlay\ndescription: Overlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of the film, never a reserved bottom band you shift content up to avoid. Load when adding captions/subtitles to a talking-head or launch video, when deciding whether a phrase should be dropped, ride the verbatim rail, or be promoted to a scarce embedded climax, when laying out a composition that will carry captions (do NOT reserve a keep-out band), or when centering a composition on the true frame center under captions. Quotes the rail+embed model from embedded-captions and constraint #13 (captions overlay, keep-out band retired) from the product-launch-video scene agent. Applies ON TOP of embedded-captions.\n---\n\n> Modified by Juicy Lucy AI, UAB for JuicyLucy Ads: CLI invocation, the review-approval reference and/or frontmatter (description layout, upstream-only metadata) adjusted at build time. See the plugin root NOTICE for details.\n\n\n# Captions Overlay Doctrine\n\n> **Overlay doctrine — supplements the upstream `embedded-captions` skill. Applies ON TOP of it; do not expect it folded into the upstream skill.**\n\nTwo ideas combine here. First, the **caption model** — every spoken phrase is `drop`,\n`rail`, or `embed`, and embed is the scarce earned peak, not the default. Second, the\n**overlay law** — a caption line is composited ON TOP of the film as an overlay; it is\nNOT a reserved zone, so you never shift content up or leave a dead band to \"make room\"\nfor it. The two reinforce each other: because captions ride as an overlay (the verbatim\nrail in front, the occasional embed behind the subject), the composition keeps its full\nframe and centers on the true vertical center.\n\n## The caption model — drop / rail / embed\n\nEvery spoken phrase is one of three things (verbatim from `embedded-captions`):\n\n|           | What                                             | How it's shown                                                                                                                                                    |\n| --------- | ------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| **drop**  | filler — um/uh, stutters, self-corrections       | not shown                                                                                                                                                         |\n| **rail**  | the default — ordinary spoken content (verbatim) | clean lower-third subtitle, **in front**, readable. A punch word can get an inline `emphasis` highlight (accent colour / active-word pop) — it stays on the rail. |\n| **embed** | a promoted peak — the headline beat              | one big word composited **behind the subject** (matte occlusion), designed entrance + exit                                                                        |\n\n**The rail carries most of the text; embed is the scarce, earned peak** — ≤1 per beat,\nnever two adjacent/co-visible, spaced ≥ a beat apart. A short clip → usually one embed;\na long explainer → ~one per section. Embedding every word is the common mistake.\n\nThis is the **Standard** mode shape (rail = the verbatim lower-third; embed = the climax\ncomposited behind the subject). **Cinematic** mode drops the rail and makes everything\nembed-style — use it only for pure-cinematic asks, never for explainer / voiceover where\nthe words must read.\n\n### Rail-first, embed-scarce (the load-bearing rules)\n\nQuoted from the `embedded-captions` non-negotiables:\n\n- **Rail-first for talking-head / explainer.** Don't embed the whole transcript — most\n  text is the rail; embed only peaks. Embedding everything is the default mistake.\n- **Embed is scarce + spaced.** ≤1 embed per sentence/beat, never two adjacent or\n  co-visible, ≥ a beat apart, at most one `apex`. climax = per-beat peak, **not** \"the\n  single payoff of the entire clip.\"\n\n## The overlay law — captions are NOT a reserved band\n\nIn a generated launch composition, when captions are enabled, finalize composites a\n**small, minimal word-by-word caption line** as an overlay layer ON TOP of the whole\nfilm (a single text line, bottom-centered, roughly the bottom ~5-8% of canvas height).\nIt is an overlay, not a reserved zone (verbatim from constraint #13 of the\nproduct-launch-video scene agent):\n\n- **Center the composition on the TRUE vertical center — y = H / 2** (landscape 540,\n  portrait 960). Do not shift content up to \"make room\" for captions; a composition\n  centered at 0.42 × H with a dead lower band is the bug, not the fix.\n- Content may extend to the canvas bottom. Full-bleed subjects, rails, and backgrounds\n  all welcome.\n- **One soft courtesy rule:** avoid parking _critical small readable text_ (a URL line,\n  a legal line, a sub-caption) exactly in the bottom ~80px center span where the caption\n  line sits — the overlay would fight it. Large imagery / cards / ambient content under\n  the captions is fine; the caption skin is designed to read over content.\n- There is no machine keep-out gate (the old `captions.mjs keepout` check is retired).\n  Finalize snapshot QA judges caption-over-content legibility visually.\n\n**When captions are disabled:** identical positioning freedom — the overlay simply\ndoesn't exist.\n\n## Why these two rules are one doctrine\n\nThe model says the rail rides **in front** and an embed is a rare word composited\n**behind the subject** — both are layers added to footage that ships untouched. The\noverlay law says the caption line is a layer composited **on top** of the whole film,\nnot a band carved out of the layout. So in both the captioning pipeline and the\nlaunch-video pipeline, captions are an overlay you add, not a zone you reserve:\n\n- Keep the full frame; center on true center; let content run to the edges.\n- Make the rail (or the small overlay caption line) carry the verbatim words.\n- Promote a word to an embed only at a genuine peak — scarce, spaced, never two at once.\n- Reserve nothing; judge legibility of captions-over-content visually, not by a keep-out gate.\n"
}