@aswless_854771076/ai_short_studio_cli 0.1.98 → 0.1.100

package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/media.md

@@ -0,0 +1,246 @@
+# Preparing media for a production
+
+Read this when admitting files, connecting generated media, choosing streams, or editing a clip
+before using it in a component or a model reference. [Media presentation](media-presentation.md)
+owns independent picture placement and playback; [Tracks](tracks.md) routes other content relationships.
+For a source video at a link, read [video download](video-downloads.md).
+For acquiring website screenshots, page recordings or local HTML graphics, read
+[browser capture](browser-capture.md).
+
+## Choose preparation from the intended use
+
+Keep source facts, preparation and presentation distinct:
+
+| Material or use | What the next consumer needs |
+| --- | --- |
+| Still image, including a transparent cutout | Bytes and its real dimensions for independent placement; the component supplies its display Window. |
+| Video, with or without audio or transparency | Selected streams, local duration and a frame clock when entering prepared-media composition inputs. |
+| Audio | The selected audio stream and prepared local time; its role can be a Script performance, music, narration or an effect. |
+| Compositable surface | Its declared pixels, extent and any animation information; use the producing package's output directly. |
+| Code-authored text, shapes or a scene | The component's data and resources; it can draw directly without an intermediate media file. |
+| A model reference | The exact image, video or audio input accepted by that model's Surface; normalization is not a universal prerequisite. |
+
+Files, generated Outputs and earlier Results are sources of these values. A reference need not
+appear in the film. A video containing a person is not automatically a SemanticTake; the author
+establishes that relationship when it performs a Script passage. [Runs](runs.md) owns explicit Result
+reuse. [Image operations](image-operations.md) owns still-image preparation.
+
+Normalization establishes moving media's frame clock, local duration and selected picture/audio
+streams. A SemanticTake adds one Script passage and its local word/boundary positions.
+[Timeline assembly](timeline.md) then places that Take in the work. Independent material goes to its
+own component without a SemanticTake. Its presentation still uses the same Timeline for event times.
+
+## Files and generated Outputs
+
+File declarations publish a **BlobArtifact**, a reference to the file's bytes, under their own id:
+
+```svml
+<import as="asset" from="@hypit/media@1"/>
+
+<asset:Image id="product" src="./assets/product.png"/>
+<asset:Video id="performance" src="./assets/performance.mp4"/>
+<asset:Audio id="music" src="./assets/music.wav"/>
+```
+
+Use `{product}`, `{performance}` and `{music}` as inputs that accept these BlobArtifacts. A model
+Surface can publish the same kind of value under an output path, such as `{portrait.image}` or
+`{opening.video}`. The package vocabulary gives that path. File paths are relative to their Source;
+[project setup](../creation/project-files.md#establish-the-project-boundary) explains the declared project boundaries.
+
+A supplied recording can be a reference for new work, an independent picture or sound, or material
+the finished work retains. When the intended passage keeps its actual recorded delivery, that
+recording can carry the Script without regenerating it. If only part of the file belongs in the
+work, prepare a new file locally with `hypit media cut`:
+
+```bash
+hypit media probe assets/recording.mp4
+hypit media cut assets/recording.mp4 --start 12.4 --end 19.8 --to assets/opening.mp4
+hypit media cut assets/recording.mp4 --keep 12.4:15.7 --keep 16.2:19.8 --to assets/opening-edited.mp4
+hypit media cut assets/voice.wav --keep 0.3:4.1 --keep 4.6:9.2 --to assets/narration-edited.wav
+```
+
+The first form retains one interval; repeated `--keep` joins selected parts of the *same* recording.
+The command keeps existing audio and picture together and can write an ordinary MP4 or audio-only
+WAV. Import that output as `asset:Video` or `asset:Audio` for its intended use. If the edited
+delivery is a Script performance, normalize and align that result as the SemanticTake below.
+Independent footage can instead enter Media or another visual component, with source sound included
+when the work needs it. A file cut does not choose Script or Segment boundaries. The installed Video
+CLI README owns exact options and output behavior. `hypit transcribe` accepts either audio or video
+when a transcript helps inspect the recording; its word times refer to that input file, while a
+retained edited performance receives its own semantic alignment in the Build.
+
+An image reference can enter a model directly. A still placed by Media Track needs its actual
+IntrinsicExtent as well. Inspect its dimensions with `hypit media probe <file>` and declare them
+with `space:Extent`; [spatial layout](spatial.md) explains extent versus destination Frame.
+
+## Prepare moving media on the program clock
+
+Clips can arrive with different frame rates, several streams or picture and sound of different
+lengths. Normalize selects the intended streams and expresses them on the program's frame clock,
+so their lengths and later playback can be combined precisely.
+
+The following excerpt prepares a performance and an independent soundtrack:
+
+```svml
+<import as="program" from="@hypit/program-space@1"/>
+<import as="pipeline" from="@hypit/media-pipeline@1"/>
+
+<program:Clock id="clock" frame-rate="30"/>
+<pipeline:Normalize id="performance-media" source={performance} clock={clock}
+  video="primary-moving" audio="default" span-authority="video"/>
+<pipeline:Normalize id="music-media" source={music} clock={clock}
+  video="none" audio="default" span-authority="audio"/>
+```
+
+The Clock is an authored rate; the prepared media supplies the resulting length. Share the Clock
+across Takes that will join one program.
+
+- `video` selects the moving-picture stream, or `none` for audio-only material.
+- `audio` selects the embedded audio, or `none` when the material should carry no sound.
+- `span-authority` chooses which stream determines the prepared duration when stream lengths differ.
+
+`primary-moving` excludes attached cover art. The default audio selection uses the default or
+unambiguous audio stream; select an explicit stream when the container has several intended choices.
+`hypit vocabulary @hypit/media-pipeline --tag Normalize` gives the supported selectors.
+
+Normalization inspects the bytes and produces `{performance-media.media}`: a SynchronizedMedia value
+with an exact local frame count, optional picture and optional audio on the chosen Clock. Audio is
+prepared as a 48 kHz render stem with its level preserved. Balance, fades and music ducking remain
+mix decisions in [Audio Track and sound mix](../playbooks/craft/sound-mix.md).
+
+## Associate a performance with Script
+
+For a performance-led work, including pure A-roll and short drama, prefer this path even when the
+picture needs no additional graphics. Script preserves the performed wording and meaningful
+passages; semantic preparation lets later presentation and revisions use their actual times.
+
+For an already declared Script and prepared spoken performance:
+
+```svml
+<import as="whisperx" from="@hypit/whisperx@1"/>
+
+<whisperx:SemanticTake id="opening-semantic" narrative={story}
+  segment={story.segment.opening} media={performance-media.media} language="en"/>
+```
+
+Set `language` to this Take's explicit spoken language code, such as `ko` for Korean. The selected
+WhisperX service chooses its language-specific alignment model; ASR size and local resource
+preparation belong to the Runtime Profile. Follow [local tools](../environment/local-tools.md)
+when preparing a new language. The installed `packages/whisperx/README.md` owns the exact language
+expression and preparation examples.
+
+WhisperX supplies timed speech evidence; alignment locates the authored Script in that evidence.
+Script remains the wording authority, and this step establishes where its words occur in the
+performance. The result `opening-semantic.take` contains the same media and that Segment's local
+timing. [Timeline assembly](timeline.md) places Takes sequentially or at authored starts and
+translates their local positions into Program time.
+Use the performed language supported by the selected package and Endpoint.
+
+Audio-only A-roll follows the same path with audio-only media. Its final speech can be a supplied
+recording, or Voice Clone can produce it from the Segment's Script and the person's Voice Reference.
+Normalize that audio with
+`video="none"`, `audio="default"` and `span-authority="audio"`, then align it to the same Segment.
+The resulting SemanticTake publishes semantic time and sound through Timeline assembly without inventing
+a visual performance; the work's Media, Typography or MG Tracks supply the picture.
+
+## Empty Segments use their media boundaries
+
+An ordinary Script Segment such as `<empty></empty>` can carry a passage without words. Its prepared
+media gives it a duration, so the resulting SemanticTake has the Segment's start/end Anchors and no
+timed Tokens. It enters the same Timeline assembly as a spoken Take. An interval with no performance
+material can instead be left open by Timeline placement or extent, with graphics authored there directly.
+
+The semantic Surface maps an empty Segment directly to its prepared media domain:
+
+```svml
+<whisperx:SemanticTake id="pause" narrative={story}
+  segment={story.segment.pause} media={pause-media.media}/>
+```
+
+This performs boundary materialization without a transcription request because the Segment has no
+Tokens. Action, music or visual rhythm can determine the media duration. The ordinary SemanticTake
+enters Timeline assembly alongside spoken Takes. This supplies Segment boundaries, not automatic
+within-shot action detection. An event such as a silent door opening needs its own observed timing
+if another component must respond to it. A simple material edit does not require inventing a Segment.
+
+## Give a still a duration when that is its role
+
+A still B-roll Item already occupies an authored Window. To make one or several images into a
+time-bearing clip, use StillVideo:
+
+```svml
+<import as="media" from="@hypit/media-pipeline@1"/>
+
+<media:StillVideo id="opening-still" source={product} duration="6" clock={clock}/>
+<pipeline:Normalize id="opening-media" source={opening-still.video}
+  video="primary-moving" audio="none" span-authority="video" clock={clock}/>
+```
+
+StillVideo produces a video-only BlobArtifact. Multiple `media:Still` children divide the authored
+duration by their optional weights. Normalization then makes that clip usable as prepared moving
+media. Choose it when one or more held images need to become a time-bearing video Artifact; its role
+is assigned by the downstream Source relationships just like any other video.
+
+## Edit bytes at an explicit point in the graph
+
+```svml
+<media:Transform id="edited" source={performance-media.media}>
+  <media:Trim tail="0.25s"/>
+  <media:Retime rate="1.05" pitch="preserve"/>
+</media:Transform>
+<media:ExtractAudio id="voice-reference" source={edited.video} audio="default"/>
+<media:ExtractFrame id="frame-reference" source={edited.video}
+  video="primary-moving" at="last"/>
+```
+
+Transform applies its operations in order. These Outputs are BlobArtifacts; normalize an edited
+clip again when feeding it into a prepared-media input, and align the edited performance when its
+timing changed. Extracted audio or a frame can directly feed a compatible model reference port.
+`ExtractFrame` also accepts `first`, `frame:<index>` and `time:<seconds>`.
+
+Use graph operations for repeatable preparation belonging to the production. `hypit media` commands
+are useful for inspection and deliberately exported evidence. Image geometry changes, compositing
+and cutouts have separate installed vocabulary in `@hypit/image-transform`, `@hypit/image-compose`
+and `@hypit/background-removal`; select the operation that matches the asset's intended use.
+
+## Keep original and processed material explicit
+
+A crop, background removal or flattened composite produces a selected asset. Normalization prepares
+that output; it does not make original pixels recoverable through a different presentation Style.
+A transparent video can enter the same SemanticTake/Timeline/Performance path as an opaque video.
+A circular clip or rounded Frame instead masks a presentation geometrically; it does not remove
+the subject's background from the underlying bytes.
+
+If the whole performance should use a processed picture, prepare it before the SemanticTake and
+place that Take. When both the original and processed picture appear, keep both outputs and bind the
+one each presentation needs. For example, Timeline can hold the cutout while an opening Media Item
+explicitly uses the original. [Performance](performance.md#choose-the-picture-actually-held-by-the-timeline)
+explains that presentation boundary.
+
+For a moving portrait, the installed `@hypit/volcengine-matting` package exposes `Portrait` with
+`source={performance.video}` and publishes `cutout.video`; query its vocabulary and README for
+transparent formats and current Provider support. Existing transparent material can enter Normalize
+directly. Removing a still reference's background does not establish transparency in generated video.
+
+Choose an operation for the material it actually accepts: [image background removal](image-operations.md#remove-a-background)
+produces a still cutout; a moving silhouette needs a video matte or suitable keying operation.
+[Video direction](../playbooks/craft/video-direction.md#prepare-footage-for-subject-isolation) explains
+preparing and judging footage for that use. A fixed flattened arrangement of still images can use
+[Image Compose](image-operations.md#flatten-a-fixed-still-image-arrangement) when that is the desired output.
+
+Operation order matters to the selected implementation. The current local Media Provider's Normalize
+preserves input alpha, while its Transform emits opaque MP4. When using that Transform for trimming
+or retiming a cutout performance, perform it before matting. Read the selected operation's output
+behavior rather than assuming every video operation preserves transparency.
+
+A picture-only operation can preserve the accepted local timing when frames still represent the
+same source instants. A project preparation component may explicitly combine that picture with the
+accepted Take's audio and evidence. That is an authored computation with both inputs, not automatic
+variant inheritance. Trimming, retiming or replacing the performance changes the relationship and
+requires timing prepared for that result. [Reuse boundaries](authoring.md#reuse-produced-work-explicitly)
+explain which completed Output can remain selected.
+
+Choose source proportions and framing for the actual footage the work needs. A full-frame spoken
+piece can start from the final aspect ratio; a later inset or split does not dictate the generated
+source shape. [Spatial layout](spatial.md) owns destination geometry. Image and video direction own
+the camera view; pass those requests visible, performable facts rather than unconverted MG instructions.

package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/performance.md

@@ -0,0 +1,114 @@
+# Presenting an existing performance
+
+Read this to present footage already placed on the [Timeline](timeline.md), including a pure A-roll
+work whose picture stays full-frame. Performance obtains that footage and its current source position;
+Uses direct how it appears. [Media Items](media-presentation.md) explicitly receive independent material
+and playback choices. Picture size, subject and transparency do not select between these paths.
+
+For a short drama, spoken scene or direct address, retain Script and the accepted SemanticTakes even
+when a single full-frame Style is the complete visual treatment. A-roll's semantic role continues
+through later reframing or coverage. An audio-only performance needs [Sound](sound.md) but supplies
+no picture for Performance.
+
+## Broad treatment, local Uses
+
+```svml
+<import as="performance" from="@hypit/performance@1"/>
+<performance:Style id="full" frame={layout.full} appearance={recipes.media.presenter}/>
+<performance:Style id="side" frame={layout.side} appearance={recipes.media.presenter}/>
+<performance:Track id="presenter" timeline={program.timeline} canvas={canvas}>
+  <performance:Use style={full}/>
+  <performance:Use during={story.selection.explanation} style={side}/>
+</performance:Track>
+```
+
+The excerpt assumes the Timeline, Canvas, Frames and Media appearance Recipe exist. The ordinary
+Style shares Media fitting, crop anchors, rounded clipping, border and sample appearance. Include
+`presenter.visual` and a [Sound](sound.md) presentation separately in Film. Sound obtains the same
+placed material and handles gain, silence and explicit source blending.
+
+An unqualified Use sets the broad treatment. Later matching Uses replace the whole choice locally;
+this is the same broad/local rule as Caption styling. Performance selects frame Windows; Caption
+selects authored display units. Separate presentation Tracks remain independent.
+
+Use supports `during`, `at` + `for`, `until` + `for`, and `start` + `end`. A Moment can start a
+fixed-duration change. No matching rule contributes no picture; an intentionally empty winning
+rule stays empty. Source gaps and audio-only Takes need no visual stand-in. Extend Timeline's end
+for a code-authored closing passage, and place its graphics there directly.
+
+## Preserve source playback and the original Use time
+
+Timeline placement determines which source frame is current. If a Take starts at program second 5,
+a Use beginning at second 7 sees source second 2. Hiding and showing footage does not restart it.
+The Style also retains the original Use Window for its animation, even where another Use covers
+part of it or a Take boundary cuts through it. Visibility, source playback and animation progress
+are separate facts.
+
+The ordinary Style draws available visual sources in Timeline declaration order, later above
+earlier. Timeline itself retains them all. An audio-only Take contributes no picture; a gap remains
+empty. Overlapping sources do not automatically crossfade, and separate Performance Tracks can
+intentionally show the same content in multiple places.
+
+For simultaneous views of the current performance, share this Timeline mapping and let each visual
+owner choose its crop and treatment. A close foreground and enlarged background can therefore show
+the same source instant. A replay starting from a chosen earlier moment has a different playback
+relationship: supply that prepared source to Media or the scene explicitly. Neither use requires
+another copy of the speech in Film.
+
+## Choose the picture actually held by the Timeline
+
+A Take contains the selected prepared picture, including any background removal already performed.
+Changing its Frame, crop or Style does not restore an original background. Keep the original output
+and bind it explicitly when a presentation needs it. [Media preparation](media.md#keep-original-and-processed-material-explicit)
+owns that material choice and any preparation adapter.
+
+For example, a cutout can continue in a lower corner through Performance while an opening Media Item
+shows the retained original from the start of the same passage. If the handoff occurs later inside
+a Take, both pictures need the corresponding source position. A project Style or scene can receive
+the original explicitly and use the Timeline projection to sample it, when the two inputs share
+that frame mapping. It does not search for hidden variants or assume two independent clips align.
+Route the intended voice once through Sound. A direct cut between those materials needs no animated
+journey between their Frames. If the intended effect instead dissolves an original into its cutout,
+both views must depict the corresponding source instant and align the subject through their fitting,
+crop and transforms. Equal destination Frames alone do not establish equal subject geometry.
+
+## Give a new visual behavior a Style
+
+A recurring presenter motion can be a project Style. It receives the Timeline, Canvas and original
+Use Window, plus its own explicit parameters. Think of a specific reusable behavior, such as a
+full-frame viewport moving into a side Frame. The family owns its trajectory and exposes the inputs
+that make it useful; arbitrary Styles do not automatically morph into one another.
+
+For a direct switch, a local Use selects the new treatment at its semantic event. For a continuous
+handoff, declare the initial treatment, then the settled treatment starting at the event, then the
+short movement Use last. It covers the start of the settled treatment and reveals that treatment
+when finished. Match both endpoint Frames and their source fitting/crop through shared values so the
+subject meets the intended view. The source video continues playing throughout; partial coverage
+does not reset its animation clock. Additional actions that answer other words receive their own
+projected events, as described in
+[component design](component-design.md#let-meaning-drive-the-behavior).
+
+An overlap transition is also a Use. For two Takes, its Window can run from the next Segment's start
+to the previous Segment's end:
+
+```svml
+<performance:Use style={mix}
+  start-source={story.segment.next} start="segment.start"
+  end-source={story.segment.previous} end="segment.end"/>
+```
+
+Define `mix` in the chosen family with explicit outgoing/incoming sources. Those roles are separate
+from the occurrence Window. The ordinary Style layers simultaneous footage in declaration order;
+an overlap by itself does not create a transition.
+
+For implementation, a Style uses `performanceStyle(fragment, bindings)` from
+`@hypit/hypit/performance`. The fragment receives `timeline`, `canvas`, `window` and family-owned typed
+inputs, and exports `visual: VisualTrack`. Bind extra inputs to resolved author references; they
+become explicit graph dependencies at each Use. Use `projectTimelineMedia` for source identities,
+program spans and source offsets, and the shared temporal helpers for additional events. All existing
+structural/browser drawing capabilities remain available. [Track authoring](track-authoring.md) and
+[component drawing](component-visuals.md) explain that implementation path.
+
+When presenter and graphics share a larger coordinated scene, give that scene its own component.
+Choose the abstraction by the behavior worth reusing; a project Style does not have to become an
+official preset before it can be used.

package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/prompt-kits.md

@@ -0,0 +1,165 @@
+# Choosing and authoring Prompt Kits
+
+Read this when choosing a reusable prompt treatment, assembling its Text inputs, or preserving useful
+direction in a new Kit. A Kit can preserve proven wording even for one image or Take. Ordinary
+`text:Value` elements carry the parts authored specifically for the current work.
+
+A Prompt Kit is a data-only TextTemplate Source. It owns reusable wording and meaningful choices;
+it does not own a model, Provider, media reference, output size, or production workflow. Keep fluent
+shot direction fluent. Turn something into a Kit when preserving the exact text or exposing a small
+repeated choice improves real productions, rather than splitting every sentence into a parameter.
+
+## Choose an existing treatment by its relationship
+
+[Image direction](../playbooks/craft/image-direction.md) and
+[video direction](../playbooks/craft/video-direction.md) guide what the prompt should accomplish.
+Choose a Kit whose fixed assumptions serve that intention:
+
+| Direction needed | Where to look |
+| --- | --- |
+| The fixed phone-video capture wording, followed by Person, Shot and Setting | The installed `@hypit/gpt-image-kits` README and its `phone-ugc-v1` template |
+| A selected character, scene or prop setting board; or a single-frame, temporal or shot-board image | The installed `@hypit/gpt-image-kits` README and its `asset-sheet-v1` or `storyboard-v1` template |
+| A difficult changing state such as a countdown, device display, hand contact or exact pose, represented in a six-cell board by default and passed to the video model | The installed `@hypit/gpt-image-kits` README and its `storyboard-v1` template |
+| A speaking performer, podcast, street encounter, video call, B-roll with native sound or an explicit silent waiver, or motion/camera transfer | The installed `@hypit/seedance-kits` README and its corresponding exported template |
+| A Seedance recreation shot with selected asset boards, mandatory depth and video prompt, plus audio or a storyboard when the shot plan requires them | The installed `@hypit/seedance-kits` README and its `recreation-shot-v1` template |
+| A MiniMax H3 Ref2VA recreation shot with the approved references and the required six ordered sections | The installed `@hypit/minimax-h3` README and its `reference-shot-v1` template |
+
+These are packaged Sources, so their README and exported `.svs` files supply the template names,
+Text slots, defaults and Recipe choices. A package's Surface vocabulary serves a different role:
+`hypit vocabulary @hypit/text --tag Render` describes assembly, and the selected model's vocabulary
+describes generation. Read the chosen template when its fixed text or a choice's exact wording matters.
+
+For an ordinary speaking passage, connect the Segment's `.dialogue` and this passage's action;
+the selected Recipe supplies recurring performance choices. For an image, bring Person, Shot and
+Setting direction from Craft. Keep reference responsibilities consistent with the actual media
+connected to the model. The owning package documents that order.
+
+Fit includes assumptions as well as available knobs. A two-view conversation and a combined
+split-screen opening may need different prompt structures. Keep the useful Kit for passages it
+serves, and use authored Text or a project template for a different relationship. A Prompt Kit is
+also distinct from a Run Fragment that supplies substitute media; [Runs](runs.md) owns that use.
+
+## Declare the reusable text program
+
+An `.svs` file selects Text's Recipe Frontend and declares one template root. This example preserves
+one fixed capture direction, requires the current shot and direction, offers a reusable camera choice,
+and includes a screen note only when the render selects it:
+
+```svs
+<?svml using="@hypit/text/svs@1"?>
+
+<sheet version="1" id="phone-shot">
+  text-template.phone-shot {
+    separator: paragraph;
+    default-camera: handheld;
+    default-screen: false;
+  }
+
+  text-template.phone-shot.block.capture {
+    kind: fixed;
+    order: 10;
+    text: "A frame from naturally captured phone video, with coherent texture and lighting.";
+  }
+
+  text-template.phone-shot.block.camera {
+    kind: axis;
+    order: 20;
+    parameter: camera;
+  }
+  text-template.phone-shot.choice.camera.handheld {
+    text: "The camera has a believable handheld relationship to the subject.";
+  }
+  text-template.phone-shot.choice.camera.locked {
+    text: "The camera remains still while the subject carries the action.";
+  }
+
+  text-template.phone-shot.block.screen-note {
+    kind: variant;
+    order: 30;
+  }
+  text-template.phone-shot.choice.screen-note.present {
+    when-param-screen: true;
+    text: "Keep the supplied interface physically contained and readable on its screen.";
+  }
+
+  text-template.phone-shot.block.shot {
+    kind: slot;
+    order: 40;
+    slot: shot;
+  }
+  text-template.phone-shot.block.direction {
+    kind: slot;
+    order: 50;
+    slot: direction;
+  }
+  text-template.phone-shot.block.references {
+    kind: slot;
+    order: 60;
+    slot: references;
+    optional: true;
+    label: "REFERENCE ROLES:";
+  }
+</sheet>
+```
+
+The root joins blocks by one blank line. Its `default-<name>` properties supply scalar bindings.
+Blocks are ordered by unique non-negative `order` values:
+
+| Block | What it contributes |
+| --- | --- |
+| `fixed` | Exact reusable Text from `text` |
+| `slot` | Text connected at render time; `optional: true` omits an absent slot, and `label` adds one literal heading |
+| `axis` | Exactly the choice whose id equals the scalar named by `parameter` |
+| `variant` | A choice whose `when-param-<name>` or `when-select-<name>` scalar conditions all match |
+
+Choices live at `text-template.<template>.choice.<block>.<choice>`. Defaults, conditions, axis
+parameters and literal `text:Param` values are finite text, number or boolean scalars. Text that is
+produced elsewhere remains a graph edge rather than being copied into a scalar binding.
+
+## Render it in an Author Source
+
+```svml
+<?svml using="@hypit/markup@1"?>
+<svml>
+  <import as="text" from="@hypit/text@1"/>
+  <import as="kit" source="./phone-shot.svs"/>
+  <import as="recipes" source="./look.svs"/>
+
+  <text:Value id="shot">A close half-body vertical view with room above the presenter.</text:Value>
+  <text:Value id="direction">A confident presenter speaks in a lived-in studio.</text:Value>
+  <text:Value id="reference-roles">The first image supplies the presenter's identity.</text:Value>
+
+  <text:Render id="prompt" template={kit.phone-shot} recipe={recipes.prompt.main}>
+    <text:Param name="camera" value="locked"/>
+    <text:Param name="screen" value="true" type="boolean"/>
+    <text:Set name="shot" text={shot}/>
+    <text:Set name="direction" text={direction}/>
+    <text:Set name="references" text={reference-roles}/>
+  </text:Render>
+</svml>
+```
+
+Save the template above as `phone-shot.svs`. For this example, `look.svs` can be:
+
+```svs
+<?svml using="@hypit/svs@1"?>
+<sheet version="1">
+  prompt.main { camera: handheld; }
+</sheet>
+```
+
+The optional Recipe supplies scalar properties consumed by the template. Template defaults apply
+first, Recipe values replace those defaults, and explicit `text:Param` children replace Recipe
+values. `text:Set` replaces one Text binding through a graph edge; `text:Append` adds another Text
+after that binding. Their order is authored and visible.
+
+The rendered `{prompt}` is an ordinary Text Output. Connect it to a model's prompt port, or target it
+in a small Run and inspect or export that Result before using the Kit elsewhere. This checks the
+assembled words without calling the image or video model. The model Surface still owns aspect ratio,
+duration, resolution and reference Resource children; prose describing what a reference supplies
+does not create the reference edge.
+
+Keep a Kit project-local while it serves one project. When its owner wants the same program in other
+projects, export the `.svs` file from an ordinary versioned data package and import that package Source
+directly. [Component sharing](component-sharing.md#data-packages-remain-data) owns that distribution
+boundary; no activation code or Hypit-specific registry is involved.