@aswless_854771076/ai_short_studio_cli 0.1.98 → 0.1.100

package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/reference-recreation-canvas.md

@@ -0,0 +1,8 @@
+# 无限画布复刻流程
+
+1. 将参考片连接到 `recreation-shot-extract`，按动作边界填写 `startSeconds` 和 `durationSeconds`；每镜最长 15 秒，逐镜确认时长、画面和方向。
+2. 连接 `recreation-subtitle-remove` 清理画面字幕；每次只提交一个镜头，完成后回读真实视频。
+3. 连接 `recreation-depth-preprocess` 或 `depth-video` 生成深度视频，再进入动作、镜头和连续性分析。
+4. 只使用已确认的 selected version 生成后续镜头，不把参考片整段直接当作生成结果。
+
+节点会调用 StarRouter 的 Comfly 复刻接口。提交前必须确认 StarRouter 配置、HTTPS 媒体地址和管理员发布的模型价格；外部任务提交后网络超时不能自动重复提交。

package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/short-drama-workflow.md

@@ -0,0 +1,165 @@
+# Short-drama production workflow
+
+Use this workflow for an original or adapted short drama without a reference video to recreate. For
+reference-led recreation, use the native `hypit recreate` workflow instead. This page turns
+[Short drama](short-drama.md) into auditable project work. The complete project contract, module router,
+prompt library, recovery tools and Dashboard are bundled with the installed CLI. Run
+`hypit short-drama root`, then read `skills/short-drama/SKILL.md` under the returned directory before
+continuing. Resolve every reference returned by `hypit short-drama modules required` from that same
+directory; do not replace those contracts with this summary. This indirection is required because the
+Hypit Skill may be installed independently from the npm package. Hypit Runtime remains the preferred
+owner of paid media generation, Results and deterministic editing where an equivalent component exists.
+
+```bash
+hypit short-drama init <project-id> --profile standard
+hypit short-drama status
+hypit short-drama check
+hypit short-drama dashboard
+hypit short-drama root
+hypit short-drama modules required <stage>
+hypit short-drama advance <next-stage>
+hypit short-drama rewind <earliest-affected-stage>
+```
+
+Run only the current stage. The `.short-drama/` project, versioned documents, module runs, immutable
+prompt requests, asset/task ledgers and delivery manifest are the single source of truth. Every module
+run binds real inputs and outputs by SHA-256; later checks fail closed if an input, selected version,
+reference contract or evidence file changes.
+
+## Analysis
+
+- `manage-drama-projects`: establish the workspace, profile, source rights, target format and the
+  existing Hypit production files that own the work.
+- `analyze-drama-source`: cover the full source. Separate sourced fact, user constraint, interpretation
+  and unresolved question; record chronology, conflict, people, places, props, visual risks and precise
+  evidence locations.
+- `define-drama-brief`: lock goal, audience, genre, tone, conflict, languages, aspect ratio, episode
+  count, duration target, rating, supplied material and forbidden changes.
+- `design-drama-bible`: establish world rules, motives, relationships, character arcs, conflict
+  escalation, plants, payoffs and ending without changing the approved Brief.
+- `outline-drama-series`: give every episode a stable id, opening handoff, causal event, information or
+  satisfaction gain, closing hook, key assets and honest duration range.
+
+## Script
+
+- `short-drama`: apply goal–obstacle–strategy–change to every passage. Silent listeners still have an
+  active judgment, concealment, waiting or relationship task.
+- `write-drama-episode`: output scene headings, visible action, exact dialogue/voice-over, present
+  characters and props. Adaptations add no unsourced events; original work stays inside the Bible and
+  Outline. Keep each turn's spoken language explicit and separate from subtitle language.
+- `humanizer`: create a new version. Remove explanatory repetition, generic slogans and equal sentence
+  rhythms while preserving plot facts, intent, language and required lines.
+- `review-drama-script`: approve only when source coverage, opening, causality, rhythm, payoff, dialogue,
+  continuity, compliance and generatability pass with no P0/P1 issue. Bind the report to the exact
+  script version; a rewrite invalidates it.
+
+## Director book
+
+`write-drama-director-book` turns the selected script into scene intent, not final shot numbers. For
+each scene record dramatic objective, beats, every character's objective/obstacle/strategy, subtext and
+listening task, blocking, gaze and exits, axis and camera side, motivated light, color movement, sound
+perspective, transition intention, continuity in/out and asset needs. Mark ordinary versus choreographed
+action. Do not add plot facts or Provider parameters.
+
+## Asset analysis and generation
+
+- `plan-drama-assets`: inventory every visible character, scene, continuity-bearing dressing, prop,
+  voice and recurring sound. Normalize aliases; version costume, makeup, age, damage, contents, time of
+  day and persistent prop state. Unknown identity, age, ownership or state remains unresolved.
+- `generate-drama-art-style`: define palette, motivated lighting, material/texture, contrast, camera
+  character, motion language, narrative color arc and negative constraints.
+- `generate-character-profiles` is required when characters exist. Bind explicit age evidence,
+  identity, body and face anchors, grooming/makeup, costume signature, expression, posture, voice and
+  forbidden drift.
+- `manage-drama-assets` selects immutable Hypit Results or admitted local media. Configure
+  `generatedAssetKinds`; missing kinds require `generate-character-images`, `generate-scene-assets` or
+  `generate-prop-assets`, using `drama-generation-service` through the existing Runtime.
+
+Use selected asset boards only when they control a real continuity risk. Character, scene and prop
+boards follow [Asset and shot preproduction](../craft/asset-and-shot-preproduction.md); they are semantic
+references, never a visible grid in the final video.
+
+## Production plan
+
+- Configure `hasStructuredFight` for `design-fight-video` when action needs cross-shot positions, force,
+  contact, pursuit, weapons, falls or multi-person choreography. Describe bodies, cause and result; an
+  attack name is not choreography.
+- `build-drama-storyboard`: split atomic shots with one time/place, continuous camera behavior and one
+  main causal action. Preserve coverage, blocking, axis, gaze, entry/exit, hands, prop state and language.
+- Configure `hasUnresolvedStoryboard` for `revise-drama-storyboards`. Revisions create new evidence;
+  they do not overwrite or cosmetically patch a failed board.
+- `plan-drama-production`: choose generated duration versus intended edit, Endpoint/model, joint
+  picture-and-sound policy, candidate limit, ordered references, fallback and acceptance risks per shot.
+  Show quantities—not a guessed price—before paid work.
+- `plan-shot-continuity`: record start/tail pose, position, screen direction, gaze, held object, prop
+  state, entry/exit edge, axis, camera side and key-light direction. Bind a previous tail only when the
+  setup genuinely continues.
+- `write-drama-video-prompts`: compile model-independent facts into the selected dialect. H3 follows
+  [H3 prompt writing](../craft/h3-prompt-writing.md); Seedance uses its Endpoint's actual ordered labels.
+  Do not mix dialects.
+
+Every final generated shot requires an independently generated temporal storyboard, an independently generated shot board, video prompt and audio reference. Do not manufacture a source clip or depth pass: add Blender previz only when the two still boards cannot prove a complex route, multi-person interaction, exact contact, axis risk, or continuous camera move, then bind that previz as the motion reference. `generate-storyboard-images` remains mandatory for every shot; optional asset boards are selected
+per shot. Configure independent audio only when applicable. The
+selected production plan and video prompt documents record those references by immutable asset version;
+the vendored workflow gates verify their paths, hashes, approvals and selection state before a paid call.
+For exact countdown or device states, isolate each state in a reviewed temporal-storyboard cell and
+regenerate the smallest failing shot; never paint, inpaint or splice-repair rejected generated video.
+
+## Media production
+
+- `drama-generation-service`: use the selected Hypit Runtime and Provider. The request carries the same
+  ordered Resources and labels as the shot contract.
+- Run `hypit short-drama production plan ep-001 --runtime <profile> --workspace <project>` first. Its
+  `generation_groups` are derived from consecutive `previous-tail` links: different groups may expose
+  one ready shot each, while one group advances strictly one shot at a time. After the current shot is
+  reviewed and selected, call the bundled `prepare_previous_tail` tool for the next shot, then plan and
+  build again. The tool reuses an unchanged tail and rejects an unreviewed, stale or replaced source.
+- Submit only with `hypit short-drama production build ep-001 --runtime <profile> --confirmed --workspace <project>`.
+  A continued shot keeps its full depth/previz, temporal-board, shot-board,
+  character and audio reference set; the prepared previous tail is an additional first-frame anchor,
+  not a replacement for those references.
+- `generate-drama-videos`: default to joint picture-and-audio generation, including ambience and action
+  sounds. Every dialogue turn names speaker, exact source-language text, confirmed language code,
+  measured delivery, mouth state and acoustic perspective. Dialogue must not appear as subtitles.
+- `monitor-drama-tasks`: recover existing Builds and Results rather than resubmitting an unknown remote
+  request. Keep every candidate independent.
+- `review-drama-shots`: watch and listen to the whole candidate. Check narrative event, identity,
+  character count, performance, anatomy/contact, prop state, camera/axis, light/look, language, voice,
+  sync, native sound, incidental text, grid leakage and continuity. Record symptom, likely mechanism and
+  one changed variable. Stop equivalent paid retries after two failures.
+
+Only accepted Results enter the Timeline. A new selected speaking shot invalidates older word timing,
+captions and lip-sync evidence derived from it.
+
+## Editing and delivery
+
+- `remotion-best-practices` and `edit-drama-timeline` use Hypit's semantic Timeline, Film, Sound and
+  Caption components, not a copied renderer. Compile edit points from dialogue phrases, action
+  peaks/impacts, gazes, sound cues, atmosphere changes and musical beats. Use action/eyeline cuts only
+  when continuity supports them; use 6–12-frame fades/dissolves only for a real time/place/mood change.
+- Preserve J/L cuts and ambience bridges with independent audio. Adjacent ambience/native clips use
+  equal constant-power fades. BGM has a narrative volume envelope and explicit dialogue ducking.
+- Captions come from selected final audio and are reviewed downstream. Use restrained movie styling,
+  safe area, semantic line breaks and frame-aligned timing. Generated subtitles, watermarks and stray
+  glyphs reject the shot.
+- `edit-deliver-drama`: run deterministic QC, inspect every exact cut, then watch and listen end-to-end.
+  Deliver approved video plus requested subtitle files and a manifest of hashes, format, selected
+  Results and review evidence. Exclude caches and rejected candidates.
+
+## Reusable prompt contracts
+
+These are Codex output contracts, not calls to another text model:
+
+1. **Source analysis:** separate fact, constraint, interpretation and unresolved question; cover every
+   segment; cite the source span for every identity, event, asset and limit.
+2. **Brief/Bible/Outline:** preserve confirmed facts; make conflict causal; allocate escalation, payoff
+   and hooks; expose every decision needing confirmation.
+3. **Episode/Review:** write playable visible action and exact speech; label language per turn; report
+   P0/P1/P2 with scene/line evidence and bind approval to the exact version.
+4. **Director/Storyboard:** for every beat state objective, obstacle, strategy, listener task, blocking,
+   axis, motivated camera/light/sound and continuity; split shots with independent causes.
+5. **Asset/Production:** inventory identities and persistent states first; select references with one
+   primary responsibility; record actual Provider limits, candidate budget and fallback.
+6. **Video/Review:** describe first state → onset → contact/change → response → stable tail; preserve
+   exact dialogue language and joint sound; reject non-whitelisted text, identity drift and failed
+   physical causality.

package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/short-drama.md

@@ -0,0 +1,88 @@
+# Short drama
+
+For a complete multi-stage production, read [Short-drama production workflow](short-drama-workflow.md)
+before creating project evidence or submitting paid generation.
+
+Short drama is performance-led storytelling. Characters do more than deliver information: their
+wants, reactions, actions, relationships and surroundings make one event lead to the next. This is
+rich A-roll. A domestic scene, a staged encounter, a podcast exchange or a street interview can all
+use this dramatic shape when the human event carries the story.
+
+## Give each passage a dramatic job
+
+Direct from the Treatment's causal movement: someone wants something, another person changes its
+meaning, an action creates a consequence, or a reveal changes what the viewer understands. Dialogue,
+silence, reaction and physical business can all carry that movement.
+
+A Segment is a performable dramatic passage, not a required camera shot or speaker turn. One Segment
+can contain several people and cuts; several generated Takes can also reuse the same camera views when
+the passage is better produced in parts. Choose the shape that lets the intended action and exchange
+remain legible.
+
+Measure the Script to understand speaking density, then leave the time that the intended pause,
+reaction and action need. The selected video model's supported request lengths constrain what can be
+generated together without defining the story's scenes. [Script and time](../../creation/script-and-time.md#measure-before-choosing-durations)
+owns measurement, while [generated video direction](../craft/video-direction.md#size-the-request-around-the-delivery)
+owns how the selected model's request range informs the performable passage.
+
+## Establish the story's useful camera views
+
+Reference-conditioned generation is a strong starting point when the work depends on recognizable
+people, a shared world, staging or composition. A key image can establish the character, a complete
+story view with the characters in their setting, or both. Direct images and Takes in natural language
+for the current dramatic intention. Free direction suits the variety of dramatic scenes; a reusable
+Prompt Kit becomes useful when repeated productions reveal a stable prompt relationship worth preserving.
+
+The first useful image can be a character reference or a view of the encounter itself. Build later
+views from the images that hold the facts they need:
+
+- a character image can carry identity into a view that establishes a new place and dramatic state;
+- a shared two-person view can establish the bodies, gaze axis and encounter before closer views;
+- one story view can carry a costume, prop or spatial relationship into the next;
+- a supplied image can serve directly when it already expresses the intended character and shot.
+
+Within one location, a small set of useful views can support many Takes. In a living-room dialogue,
+one view for each conversational side may preserve everything the passage needs; modest reframing,
+performance and camera changes can happen in video. Another image becomes useful when a new view must
+establish an important fact, such as a changed relationship, decisive prop state or plot-bearing part
+of the space.
+
+Decide separately which views to establish and which dramatic action to generate together. One Take
+can move among several shots or places while key images establish the people, objects, composition
+or continuity that need explicit visual direction; one view can also guide several Takes. A new
+place merits an image when the story needs that particular view established, while other moves and
+cuts can develop within the video passage. The image graph follows those visual dependencies rather
+than the count of locations or edits.
+
+[Reference relationships](../craft/generated-dependencies.md) owns these image edges. The
+[two-person podcast](two-person-podcast.md) and [street interview](street-interview.md) show two
+different ways of establishing a conversational world. [Video direction](../craft/video-direction.md#direct-camera-and-cuts-as-part-of-the-passage)
+owns the generated passage's shots and reference relationship.
+
+## Let every camera see the same world differently
+
+The background carries story. It can reveal intimacy or status, explain why people are together,
+support a comic contrast, plant a useful object, or make a new scene immediately readable. Direct its
+vibe with the same conviction as the character rather than leaving the model to produce generic space.
+
+Related views share the facts that make the location recognizable: atmosphere, materials, palette,
+social setting and spatial relationship. Each camera also sees its own plausible part of that place.
+One camera can reveal the part of the place surrounding one character while another reveals a
+different sector around their partner. [Image direction](../craft/image-direction.md#establish-the-place-with-a-few-details)
+owns this relationship between person, setting and view.
+
+## Let performance carry the event
+
+Action direction should preserve cause and attention: who initiates, who notices, what changes hands,
+what a reaction answers, and why attention or the camera moves now. It can describe the behavior and
+views the current passage needs. A glance, interruption, withheld response or turn away matters when
+it changes the dramatic relationship.
+
+Caption, typography, MG, effects and B-roll can sharpen that event without replacing its human spine.
+A text message can reveal information, an insert can prove what a character sees, and a graphic can
+make a payoff readable. Keep the A-roll performance and its sound meaningful even when another layer
+covers the picture.
+
+Review the finished work for dramatic causality and coherent people, places and action: the viewer
+should know who is acting, what changed, and why the next view or scene follows. A new short-drama
+form can combine these relationships differently while keeping that responsibility.

package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/street-interview.md

@@ -0,0 +1,92 @@
+# Street interview
+
+An interviewer encounters someone with their own life, asks something, and receives an answer worth
+watching. The guest usually carries the story; the interviewer helps the viewer discover it.
+
+## Establish the encounter, then derive attention
+
+For the three-view method, generate a shared image containing both people and their real spatial
+relationship. Derive the guest close view and interviewer close view directly from it. In the
+interviewer view, retaining part of the guest at the opposite edge keeps the exchange legible.
+The guest looks toward the interviewer, and the interviewer looks back across the same screen axis.
+That attention and a comfortable microphone position give the reusable views their
+[idle state](../craft/image-direction.md#choose-an-idle-state-for-the-encounter). Opening, reaction
+and departure actions can then develop from this encounter in their respective video passages.
+
+```text
+shared street scene ──> guest close view
+                    └─> interviewer close view, retaining part of guest
+```
+
+The [worked image directions](../craft/examples/conversation-images.md#street-interview-views)
+show how little the derived prompts need to add once the shared image is doing its job.
+
+`street-interview-v1` uses this supplied set: interviewer A, guest B, shared view, then the two voices
+in A/B order. All ordinary Takes reuse it. Its three-view limit is the design of this Kit, not a
+restriction on every street interview or on Hypit. The interviewer keeps the microphone and moves
+it toward whoever speaks; extending it to the guest is not handing over ownership.
+
+## Cut toward the person who matters now
+
+Guest answers can favor the guest close view. A brief neutral interviewer question
+can stay in the shared view; disbelief or an emotionally important challenge earns the interviewer
+close view. This directs attention rather than alternating cameras on a timer.
+
+Action can specify cuts between the Kit's supplied setups. Several questions and answers fit in one
+Segment and one generated Take. Keep the chosen framing behavior within each setup and let the cut
+move directly to the next; an invented travel shot between cameras changes the scene's grammar.
+
+## Give the encounter a before and an after
+
+At the opening, the guest is occupied with something plausible: looking into a bag, checking an
+object, or looking down. The interviewer takes a small step forward and asks; the guest looks up
+or turns toward them in response. Begin the exchange naturally rather than imposing a fixed silent
+delay before every line.
+
+At the end, return attention to the guest and let them begin to turn away after the final thought.
+These small actions imply life outside the clip. They work because of their cause, not because
+every interview must contain the same bag check and exit direction.
+
+For example, action alongside the Script can make an opening's causal sequence concrete:
+
+```text
+BOY is interviewer A; WIFE is guest B. Open in the shared reference setup. She is looking into her
+bag as he takes a small step toward her and begins the question. She looks up toward him in response.
+Cut directly to her supplied close view for her answer. Use the shared view for his brief follow-up,
+and his supplied close view when the surprising answer earns his disbelief. Keep the reaction
+interested and spontaneous rather than theatrical; he continues to hold and position the microphone.
+```
+
+On the final passage, a short additional direction can return to her close view and let her begin
+turning away after the punchline. The opening and ending actions belong to those actual passages;
+intermediate Takes carry the behavior of their own exchange.
+
+For the middle, give a few readable gestures a purpose: amused certainty, a compact shrug, a glance
+that registers a surprising answer. Avoid exaggerated emotion, constant motion and exact numerical
+finger poses. The performer should seem to respond, not execute an animation checklist.
+
+## Make a reveal one event across several layers
+
+A single answer Moment can update one slot in an emoji strip, start a short sound and trigger
+a colored flash. Earlier answers remain visible; future answers remain question marks. Reuse the
+same Script Moment for these consumers so a changed delivery still makes the reveal land together.
+
+Design Caption colors, placeholder and answer icons, flash colors and sound character as one visual
+and rhythmic treatment. An icon's role can supply an accent color; not every layer needs the same
+color. Use actual image assets when matching icon shape and color matters.
+
+This answer strip is a normal project component. Its outer Window owns visibility; child Moments
+own reveals; its implementation owns the resulting persistent state. See
+[Track authoring](../../production/track-authoring.md) for that distinction and other Track roles.
+
+## Caption can follow the guest's head
+
+When tracked placement serves the work, produce the speaking footage with ordinary Caption placement
+available first. Face detection on that footage can then supply boxes; expand the chosen person's
+boxes to head regions and render again with Caption anchored above them, reusing the paid media.
+
+Use [Caption tracking](../craft/caption-tracking.md) when this placement serves the piece. It is a
+specific production loop with an external measurement step, not a required first step for interviews.
+Fixed interviewer Caption and tracked guest Caption can coexist. Fine styles handle these examples;
+a new structural Caption treatment can be a project Caption family using the shared Script,
+Caption data and semantic timing.

package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/talking-head.md

@@ -0,0 +1,82 @@
+# UGC and talking-head performance
+
+A compelling person speaks to the viewer. Their attitude carries the piece; Caption, evidence and MG
+help the viewer follow it. A ranking board is one possible companion, not a requirement of UGC.
+For that relationship, combine this page with [Ranking](ranking-listicle.md).
+When evolving demonstrations and MG carry much of the argument, use
+[Presenter-led visual explainers](presenter-led-explainer.md) for their relationship to that performance.
+This relationship follows the speaking performance, whether its footage is newly made or retained
+from a recording.
+
+## One useful image can carry the whole performance
+
+Make a character-and-scene image with the presence, camera distance, posture and available graphic
+space the video needs. For a performance expected to stay mostly full-frame, its final aspect ratio
+is a useful starting point. Preserve the body and gesture room needed across its later uses;
+destination viewports can change around the same footage. [Image direction](../craft/image-direction.md)
+owns that craft. A person placed slightly right can leave room for an icon on the left; the image
+prompt describes the person and visible setting, while the icon belongs to its component. A table
+or the direction of their seated body can make that placement feel inhabited. Choose it for this work.
+
+For a reusable frontal speaking image, explicitly keep the face toward the lens, with no head tilt
+or rotation. A vivid attitude and an easy speaking gesture give this settled view life. The
+[idle principle](../craft/image-direction.md#choose-an-idle-state-for-the-encounter) relates that pose
+to addressing the viewer; the generated performance can move and react within the encounter.
+
+Cast the person's vocal appeal with [Voice direction](../craft/voice-direction.md).
+Use that same image and the person's recurring voice reference for every ordinary talking Take.
+Each Take can return to the same useful visual premise and contribute another piece of the edited
+performance.
+
+Natural cuts are part of the desired result. A small change in pose between passages can make the
+video feel like a creator's edited recording. Stable character-and-scene references can support each
+Take independently because this work wants edited speech rather than an unbroken simulated recording.
+
+## Use the tested Speaker Kit when its shape fits
+
+For a single presenter returning to one useful camera image through natural edited cuts, `speaker-v1`
+from `@hypit/seedance-kits` is a tested fit. It combines that character-and-scene image, one voice
+reference, Script dialogue, a Recipe for recurring direction, and optional action Text for the passage.
+The installed Kit package owns its exact assembly, reference order and Recipe choices.
+[Generated video direction](../craft/video-direction.md) explains what the image, voice, dialogue and
+passage direction each contribute. A work whose camera, cast, or performance relationship differs can
+use another Kit or ordinary authored direction.
+
+For this edited talking-head form, start with the Speaker Recipe's
+`edit-rhythm: pause-trim-jump-cuts`. The camera can stay fixed while the performer remains expressive.
+[Video direction](../craft/video-direction.md#direct-camera-and-cuts-as-part-of-the-passage) explains
+choosing the rhythm for the passage; the installed Kit documents the wording this option supplies.
+
+Action supplies what the scene means to this person. For a teasing ranking host, amused disbelief,
+a knowing look and a compact dismissive gesture are more useful than a limb-by-limb animation plan.
+Give a few actions a reason: a shrug dismisses an argument; a quick lean makes a punchline personal.
+Let speech, Caption or MG carry exact numbers while the hand makes a readable emphatic gesture.
+
+One useful action direction, alongside Script dialogue, is:
+
+```text
+Play this as an affectionate roast from someone who knows the subject well. Start with amused
+certainty, let the comparison earn a brief disbelieving look, and land the last line with a small
+knowing shrug. The free hand makes relaxed emphatic gestures; keep the microphone easy and steady.
+```
+
+This illustrates attitude and a few visible beats; it does not prescribe every creator's personality.
+See [Generated video direction](../craft/video-direction.md) for listeners, gestures and cuts.
+
+## Let speech and graphics do different work
+
+Write natural stages in Script. For newly generated Takes, measure each Segment before choosing a
+literal generation duration. When the work retains recorded speech, its edited delivery supplies
+the actual duration; [media preparation](../../production/media.md) explains how to prepare and
+align it. A Segment can contain several edited shots, Caption Cue Breaks, graphic changes and
+speaking turns. Choose its boundaries from the performance it carries.
+
+Normalize the produced speaking media, align its own audio to its Segment, and assemble the
+SemanticTakes. Keep that performance's sound when B-roll covers its picture. Place evidence on
+Selections and reveals on the component's declared timing inputs. A persistent board can continue
+through a cut while the current portrait, evidence image and Caption change.
+
+Watch whether the person feels engaged and whether the visual layers support that engagement.
+Stable identity and a coherent setting matter; identical pose at every seam does not. A static
+expression, mechanically repeated gestures or relentless intensity can undermine the result even
+when every requested word is present.

package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/two-person-podcast.md

@@ -0,0 +1,101 @@
+# Two-person podcast
+
+The relationship between two people carries the argument: a question invites a claim, a reaction
+changes its meaning, and a reply pays it off. Let that relationship motivate framing and performance.
+
+## Build the pair from a useful first view
+
+Generate the main host in the actual setting first. Use that image to derive the other host's
+complementary view: opposite screen position and gaze, microphone entering from the other side,
+and another visible sector of the same location. The first host view establishes the shared world;
+the complementary view changes what the other camera can see.
+
+These [idle views](../craft/image-direction.md#choose-an-idle-state-for-the-encounter) hold an easy
+conversational posture: each host turns toward their partner, with their face readable from the
+chosen camera. Their attitude is already present and can develop through different speaking turns.
+
+The worked restaurant example has this reference structure:
+
+```text
+main host in restaurant ──> other host in restaurant
+main host + product ──────> main host holding product
+other host + product ─────> other host holding product
+main host (+ logo) ───────> each lifestyle scene
+both host views ──────────> optional split-screen opening image
+```
+
+Most new views are one hop from their useful parent. Derive lifestyle scenes from the main host,
+not from one another. Product-holding views inherit their own host's camera and add the actual
+product reference. Preserve gaze, the established setting and microphone placement while changing
+the intended prop state. File imports are valid inputs even when those images were generated outside
+Source.
+
+[Podcast and interview image examples](../craft/examples/conversation-images.md) preserve the
+concrete English production directions and explain what each reference is responsible for.
+
+## Direct conversation inside a Take
+
+`podcast-v1` takes two final camera views and two voices, in matching A/B order. Map the Script's
+actual Role names to those hosts explicitly in action direction. Script remains the sole dialogue
+text; a single Segment can contain several turns and speaker cuts.
+
+The Kit's Recipe supplies recurring framing, editing, pace, performance, reaction and gesture choices.
+Action adds this passage's attention and interaction: who is making the claim, who is skeptical,
+when a reaction earns the other view, and who holds the product. Keep silent listeners physically
+alive through a posture adjustment, a brief glance down and back up, or an attentive expression while
+preserving their silence.
+
+A handoff needs legible possession. The main host offers the product toward their partner; the
+partner receives it in the complementary view; later shots reflect who now has it. A few clear
+relations are more useful than prescribing every finger. Cuts can carry this exchange without
+requiring serialized frame-continuation generation.
+
+For example, action accompanying a product-offer passage can say:
+
+```text
+GIRL is Host A and GUY is Host B. She treats the recommendation with amused certainty; his reaction
+is playful disbelief, not outrage. She offers the product toward the left edge of her view. In his
+complementary view it arrives from the right; he receives it and keeps it. When returning to her,
+the product is no longer in her hand. Keep the exchange casual, with compact gestures and no
+extra dialogue.
+```
+
+This particular direction assumes those view and prop inputs. A phone link sent digitally calls for
+the corresponding screen or conversational interaction instead of a physical handoff.
+
+## An opening can establish both people at once
+
+A top/bottom split screen can immediately reveal the pair before the first question finishes. The
+speaker can occupy one panel while the listener in the other looks down, adjusts their seat and
+looks back up. Those small silent actions establish a conversation already in progress.
+
+```text
+Keep the supplied top-and-bottom composition. The man in the upper panel delivers the question to
+his partner. In the lower panel, the woman briefly looks down, settles into her seat and looks back
+toward him as she listens. She remains silent. Let both panels feel like the same conversation
+already underway, without large gestures or a frozen listener.
+```
+
+The split reference and its matching video direction form one authored opening Take that can carry
+both people and a speaker change. The ordinary two-view Podcast Kit suits the later exchange. Use a
+split-screen opening when that attention device serves the work; use another component or Take shape
+for a different layout.
+
+## Coverage can follow a thought rather than every noun
+
+The example generates three lifestyle scenes together as a short silent montage, then places that
+one clip over a Selection spanning the host's examples and the start of the partner's response.
+The viewer understands the broader habit even when each visual cut is not synchronized to its noun.
+Give the montage enough room to play through once at native speed, so its last scene is not cut off.
+The Selection may slightly outlast the clip; let the underlying picture return when playback ends.
+The partner's incoming voice can precede that return: a useful J-cut relationship. Avoid a frozen
+tail or retiming merely to fill the Selection. Use the B-roll craft's current playback guidance
+rather than treating an existing project's Recipe as a required choice.
+
+Use separate clips when exact scene-to-cue correspondence matters, especially in reconstruction.
+Generate each within the selected model's actual range and consume only the needed section. Read
+[B-roll](../craft/b-roll.md) for source duration, `stretch`, short windows and gap-free boundaries.
+
+Host-colored Caption can clarify the speaker even over full-frame B-roll. Coordinate it with the
+scene palette and product treatment; choose the colors for this pair. Judge the whole exchange for
+responsive timing, restrained reactions, prop continuity and a payoff that feels earned.

package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/index.md

@@ -0,0 +1,77 @@
+# Production playbooks
+
+Read this when the current work needs format or craft knowledge beyond the Creation and Production
+references. Playbooks help the Agent direct a work; the Source and Run remain the author's.
+
+## Combine two scales
+
+A **format** describes a recurring whole-work relationship: who carries the argument, how attention
+moves, and what kind of reveal or payoff holds the piece together. A **craft** addresses one local
+directing problem that can appear in many formats: Caption, B-roll, continuity, image generation,
+sound, or graphic composition.
+
+Use the reference Analysis and Timeline, the target Brief and Treatment, and the visible Source to
+choose what is relevant now. One work may draw from several formats and several crafts. A new or
+hybrid form may need craft pages without matching any format page.
+
+The pages below own stable cross-work directing knowledge. When none fits the current question, use
+the project's Analysis, Timeline, Brief, Treatment, Source, and visible Results directly. A work does
+not need a matching playbook before it can be understood or made.
+
+## Craft
+
+| Read | When the current question concerns |
+| --- | --- |
+| [Directing generated images](craft/image-direction.md) | directing the picture a work needs, including people, places, products and icons; phone-video capture, casting, camera relationships and references |
+| [Directing a voice](craft/voice-direction.md) | casting an appealing voice, choosing its vocal character, writing Voice Design direction or selecting a sample line |
+| [Voice and performance](craft/voice-and-performance.md) | what performance carries a passage, recurring voice identity, changing visual use of the same material, or genuinely independent narration |
+| [Directing generated video](craft/video-direction.md) | choosing a generation relationship, deciding when source footage should carry performed action or camera behavior, directing visible speech or silent action, cuts, subject-isolation footage or request duration |
+| [Asset and shot preproduction](craft/asset-and-shot-preproduction.md) | completing character, scene, prop and voice assets; choosing single, temporal, shot-board or spatial previz; binding depth, boards and continuity into each generated shot |
+| [Shot production contracts](craft/shot-production-contracts.md) | writing copyable asset, shot, ordered-reference and generation-gate records for reference-led or multi-shot work |
+| [Reference relationships](craft/generated-dependencies.md) | what existing images or footage contribute to a new request: people, places, conversational views, continuing props and new-scene branches |
+| [Material-led pictures and B-roll](craft/b-roll.md) | what an image or video contributes to a passage; full-frame or framed views, exact evidence versus a visual thought, and picture/performance handoffs |
+| [Screen demonstrations](craft/screen-demonstrations.md) | what a website, app, terminal or editor must show; captured states and interactions versus authored explanations, and how viewers follow them |
+| [Caption](craft/captions.md) | speech-linked text, reading rhythm, Fine styles, or a new Caption family |
+| [Caption tracking](craft/caption-tracking.md) | the user's reference visibly uses head-following Caption or the user asks for it; matching face observations to Roles, picture placement and Cue time |
+| [Sound and mix](craft/sound-mix.md) | what existing material already sounds like, which music or effects the work needs, and how those sounds share time and attention |
+| [Graphic composition](craft/graphic-compositions.md) | attention and coexistence of material and graphics, source framing, boards, spatial hierarchy and coordinated palette |
+| [Motion graphics](craft/motion-graphics.md) | how graphics, effects and scenes change over time, carry objects through handoffs, establish a motion language and meet the performance |
+
+Read every craft whose question genuinely appears in the work, including questions discovered after
+a Studio preview or completed Result. Repeated use of the same craft does not require rereading it
+unless the decision has changed.
+
+For authoring those decisions, [Performance](../production/performance.md) presents current Timeline
+footage and [Media](../production/media-presentation.md) supplies independent pictures and playback.
+[Media preparation](../production/media.md#keep-original-and-processed-material-explicit) owns source
+processing, including transparency; [Spatial layout](../production/spatial.md) owns fitting and crop.
+These choices compose according to the intended use of the material.
+
+## Examples
+
+| Read | When a concrete directing example would help |
+| --- | --- |
+| [Image direction examples](craft/examples/image-direction.md) | four-paragraph production prompts for the balcony portrait and five reviewed character portraits |
+| [Conversation image examples](craft/examples/conversation-images.md) | complementary podcast and interview views, product references, lifestyle B-roll, and changing camera relationships |
+
+## Formats
+
+| Read | When the work's shape includes |
+| --- | --- |
+| [UGC and talking-head performance](formats/talking-head.md) | one person directly addressing the viewer, with natural edited performance |
+| [Short drama](formats/short-drama.md) | characters, relationships, actions and changing dramatic settings carrying the story as rich A-roll |
+| [Two-person podcast](formats/two-person-podcast.md) | complementary host views, conversational reactions, product interaction or lifestyle coverage |
+| [Street interview](formats/street-interview.md) | a motivated encounter, guest/interviewer/shared views, reveals or tracked Caption |
+| [Ranking and listicle](formats/ranking-listicle.md) | a persistent comparison or board whose state changes with the argument |
+| [Presenter-led visual explainer](formats/presenter-led-explainer.md) | spoken performance joining evolving demonstrations and MG, with the presenter moving between full-frame, inset and covered views |
+| [Narration-led work](formats/narration-led-demo.md) | independent narration organizing products, hands, screens, demonstrations, montage, or MG |
+
+A format page is useful when its relationships illuminate this work. It is not a category the
+project must declare, and its examples do not limit what the work may combine or invent.
+
+## Continue at the owner
+
+Once a playbook identifies the needed role or relationship, use `hypit vocabulary <package>` and the
+owning package README for exact Surfaces, ports, fields, and model options. Creation references own
+the work's understanding and intention; Production references own Source, Run, preview, Build, and
+Result behavior. Project files own the facts and decisions of the current work.