diff --git a/docs/prompting/anatomy.mdx b/docs/prompting/anatomy.mdx index 7ff58673f..4e8262839 100644 --- a/docs/prompting/anatomy.mdx +++ b/docs/prompting/anatomy.mdx @@ -3,6 +3,8 @@ title: Anatomy of a one-shot prompt description: "The six-part skeleton — route, spec, beats, copy, technique, negatives — that removes the decisions agents most often get wrong." --- +Your Level 1 prompts worked because the workflow filled the gaps for you — the palette, the pacing, the structure. This is Level 2: the skeleton is how you take that control yourself. + The [copy-paste examples](/prompting/examples) share one skeleton. Each part removes a decision agents most often get wrong on a first try: ```text @@ -28,6 +30,9 @@ Assembled: *Rendered from the prompt above, unedited.* + + The skeleton isn't just prompting style — the framework enforces a version of it on itself. Since the composition-structure mandate (`0aaac7aa3`, PR #2599), a `hyperframes feedback` report on a visual defect requires a `COMPOSITION_STRUCTURE:` block — element census, attribute presence, timeline shape — auto-filled from the composition's own HTML; the CLI soft-warns (never blocks) when it's missing. Same idea as the six parts above: name the shape explicitly, and both you and the framework reason about it faster. + ## The beat formula @@ -70,3 +75,5 @@ The fixes that come up most, as before/after pairs — each exists because of ho **Format-blind numbers.** An odometer needs fixed digit columns — "counts $0 → $4.2M" forces an awkward "$0.0M" start. - ❌ `counts from $0 to $4.2M` - ✅ `counts up to $4.2M` + +*Next: [The specification dial](/prompting/specification-dial) — how much of the skeleton to fill in, and when density stops being optional.* diff --git a/docs/prompting/examples.mdx b/docs/prompting/examples.mdx index 73aaa7a67..61923fdc5 100644 --- a/docs/prompting/examples.mdx +++ b/docs/prompting/examples.mdx @@ -3,6 +3,8 @@ title: Verified example prompts description: "18 copy-paste prompts, every one run end-to-end to a finished video that passes check." --- +This is the level's gallery, not a new lesson — read these with the vocabulary you just picked up: the [six-part skeleton](/prompting/anatomy), the [specification dial](/prompting/specification-dial), and the [word list](/prompting/vocabulary) or [full visual spec](/prompting/visual-specs) it maps to. Spot the skeleton parts in each prompt below as you read it. + Every prompt below has been run end-to-end and one-shots a finished video that passes `check`. Swap the copy, colors, and inputs for your own. ### With registry blocks and workflows @@ -106,3 +108,5 @@ Every prompt below has been run end-to-end and one-shots a finished video that p *Rendered from the prompt above, unedited.* + +*Next: [Motion that reads premium](/prompting/motion) — Level 3: the grammar rules behind why these moves read as professional instead of generic.* diff --git a/docs/prompting/specification-dial.mdx b/docs/prompting/specification-dial.mdx index b384eefca..585ec6e41 100644 --- a/docs/prompting/specification-dial.mdx +++ b/docs/prompting/specification-dial.mdx @@ -3,7 +3,7 @@ title: The specification dial description: "Spec density controls how far the result drifts from what you imagined — not whether it works." --- -How much you specify sets how much you delegate — it controls how far the result can drift from what you imagined, not whether it works. Mood-level prompts ("snappy", "cinematic") get a designer's interpretation: coherent, but the agent picks the colors, staging, and details. Dense specs — hexes, timestamps, easings, pinned techniques — get *your* frame. +The [skeleton](/prompting/anatomy) tells you where each decision lives; this page tells you how hard to turn each one. How much you specify sets how much you delegate — it controls how far the result can drift from what you imagined, not whether it works. Mood-level prompts ("snappy", "cinematic") get a designer's interpretation: coherent, but the agent picks the colors, staging, and details. Dense specs — hexes, timestamps, easings, pinned techniques — get *your* frame. Three settings: @@ -15,3 +15,5 @@ Density never hurts — a stronger model just uses less of its own taste. It mat - **3D**: any real depth, lighting, or camera motion → say **"Three.js via the adapter"**. CSS perspective transforms read flat on lighting-critical scenes, and Three.js is a supported seek-safe runtime. - **Sequencing**: resolve simultaneity in the text. "The counter fades out and READY stamps in at 4s" produces an overlap; "fades out fully by 4.2s; at 4.2s READY stamps in" doesn't. + +*Next: [Vocabulary that changes output](/prompting/vocabulary) — the exact words that turn a mood into a specific framework setting.* diff --git a/docs/prompting/visual-specs.mdx b/docs/prompting/visual-specs.mdx index ce35b6a1b..202f795b0 100644 --- a/docs/prompting/visual-specs.mdx +++ b/docs/prompting/visual-specs.mdx @@ -3,7 +3,7 @@ title: High-fidelity looks description: "Write a visual spec — every element named, positioned, colored, and timed — to carry a specific look in words." --- -You can carry a specific look in words alone when the prompt reads like a designer's spec — every element named, positioned, colored, and timed. Compare a loose description ("dark night scene, mountain, glowing ring, title fades in") with a spec: +This is the dial's third setting, [full visual spec](/prompting/specification-dial), pushed all the way: not a word from the [vocabulary](/prompting/vocabulary) list, but every element of a scene written out like a designer's spec. You can carry a specific look in words alone when the prompt reads like a designer's spec — every element named, positioned, colored, and timed. Compare a loose description ("dark night scene, mountain, glowing ring, title fades in") with a spec: > 8-second 1920x1080 title card. Scene, back to front: #0a0e2a night sky with faint grain; a huge concentric ring system (5 rings, 1px strokes at 8% white opacity, innermost ring glowing #4a5fd9) centered 40% from the top; behind the rings an orange radial glow (#ff6a2b core → transparent, ~300px) igniting at the peak's right shoulder from 2s; a low-poly mountain (6-8 dark navy facets, #141a3d–#1e2650) filling the lower third, a white road S-curving up its face with a soft glow; thin horizontal cloud streaks (white, 6% opacity) drifting right at two heights; a man's silhouette, pure black, ~90px tall, bottom-right, fading in at 2.5s. At 3.5s "SHOWREEL" — thin geometric sans, ~140px, 0.35em tracking, white at 90% — fades in per letter across the ring center, the orange glow bleeding through the O. Slow 4% push-in across the full 8s. No audio. @@ -26,3 +26,5 @@ The same density applied to a product-UI piece and a typographic piece — both *Rendered from the spec above, unedited.* +*Next: [Verified example prompts](/prompting/examples) — the level's gallery: 18 prompts to read with the vocabulary you now have.* + diff --git a/docs/prompting/vocabulary.mdx b/docs/prompting/vocabulary.mdx index c15b72029..c0c7480c2 100644 --- a/docs/prompting/vocabulary.mdx +++ b/docs/prompting/vocabulary.mdx @@ -3,7 +3,7 @@ title: Vocabulary that changes output description: "Natural-language adjectives the skills map to specific framework settings — easing, captions, transitions, audio, voices." --- -The skills map natural-language adjectives to specific framework settings. Using the right word gets you the right result without specifying technical details. +[The dial](/prompting/specification-dial) told you *how much* to specify; this page is the word list for the cheap-precision setting — style tokens that cost you nothing to say and remove real ambiguity. The skills map natural-language adjectives to specific framework settings. Using the right word gets you the right result without specifying technical details. ### Motion & easing @@ -188,3 +188,5 @@ TTS runs locally via Kokoro (no API key needed). Describe the content and the ag "Render at high quality" "Export as transparent WebM" ``` + +*Next: [High-fidelity looks](/prompting/visual-specs) — past single words, into full visual specs that carry an entire look.*