@scenerok/cli 1.0.10 → 1.0.11

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@scenerok/cli",
-  "version": "1.0.10",
+  "version": "1.0.11",
   "description": "SceneRok CLI - Create videos from your terminal and agent workflows",
   "type": "module",
   "bin": {

package/skills/shared/SKILL.md

@@ -93,6 +93,8 @@ import eleven from "@elevenlabs/music"
 import motion from "@scenerok/basic-animations"
 
 [-] = video xai.imagine("Cinematic product shot, premium lighting, no text, no words, no letters, no captions, no logos, no watermark, no readable UI copy", aspect_ratio: "9:16", duration: 5)
+[-] = video xai.imageToVideo("https://cdn.example.com/product.png", "Slow premium camera move around the product, no text, no words, no letters, no captions, no logos, no watermark, no readable UI copy", aspect_ratio: "9:16", duration: 6)
+[-] = video xai.referenceToVideo(["https://cdn.example.com/product.png", "https://cdn.example.com/person.png"], "Lifestyle ad shot featuring the referenced product and person, no text, no words, no letters, no captions, no logos, no watermark, no readable UI copy", aspect_ratio: "9:16", duration: 8)
 [-] = audio xai.tts("Welcome to SceneRok", voice: "eve")
 
 # ElevenLabs music package functions require an import alias.
@@ -102,6 +104,10 @@ let bed = eleven.music("Warm premium launch bed", duration: 15, instrumental: tr
 
 **Always** import the package that owns the function: `xai.*` from `@scenerok/xai`, `eleven.*` from `@elevenlabs/music`, and `motion.*` from `@scenerok/basic-animations`. Calls without import fail validation with `Unknown function 'xai.imagine'`.
 
+Use the full xAI visual toolkit, not only `xai.imagine()`: use `xai.imageToVideo(image, prompt, ...)` when you have one strong product/screenshot/logo image to animate, and `xai.referenceToVideo([images...], prompt, ...)` when extracted objects, screenshots, product photos, people, packaging, or brand elements should guide the generated scene. Reference-to-video requires a prompt, accepts up to 7 reference images, and should stay at 10 seconds or less.
+
+xAI TTS voice IDs: `eve` for demos/announcements/upbeat content, `ara` for warm conversational narration, `rex` for business/tutorial delivery, `sal` for balanced general narration, and `leo` for authoritative instructional narration.
+
 For ElevenLabs music, import `@elevenlabs/music` and call `eleven.music(...)`, `eleven.generateMusic(...)`, or `eleven.composeMusic(...)`. Use `let bed = eleven.music(...)` followed by `audio bed, volume: ...` when you need volume or fades.
 
 Read `vidscript-strict.md` for anti-patterns and `examples/system/*.vid` for copy-paste templates (installed with `scenerok skills install`).
@@ -120,7 +126,7 @@ input hero = "{{hero_clip}}"
 2. **Plan the structure** — Time blocks, durations, inputs
 3. **Gather assets** — Video URLs, local paths, generated clips, and selective website screenshots/images; when the user provides a URL, browser screenshots are optional source material, not a requirement to build the whole video from screenshots
 4. **Probe asset type and dimensions** — Inspect every local or downloaded asset before placing it. Use `file` to identify image vs video, `ffprobe` for video/audio, `sips -g pixelWidth -g pixelHeight file` on macOS images, or `identify file` when ImageMagick is available.
-5. **Prepare still images for render** — Plain VidScript input declarations can upload images, but production-safe timeline placement currently uses `video` clips. Do not write `[time] = video some_png_input` directly. Convert still images/screenshots/logos to short H.264 MP4 plates first, then use those MP4s as `video` inputs. Plugin-generated image surfaces are separate and only safe when a plugin explicitly returns a `surface` result.
+5. **Use images directly when useful** — VidScript `input` supports both videos and images. You can place a still image input with `video image_input`; the renderer detects the asset type and treats it as a static visual clip for the block duration.
 6. **Compose VidScript** — Write the full script using measured dimensions, aspect-ratio-preserving scale, centered/safe-area placement, and entry/exit animation beats for each visual asset
 7. **Validate** — Run `scenerok validate script.vid`
 8. **Render** — Run `scenerok render script.vid --watch`
@@ -135,11 +141,11 @@ When the user provides a product, company, landing page, app store listing, or e
 3. Crop or frame screenshots to the specific visual evidence needed. Do not use screenshots as the only visual style by default, and do not build a whole video as a sequence of unreadable full-page captures.
 4. Detect and save usable product images, app screenshots, brand marks, and logos from the page when available. Prefer direct image assets when they are accessible and clearly match the product; use browser screenshots as supporting assets when they communicate something visible at video size.
 5. Probe saved asset type and dimensions before composing. Record file type, width, height, aspect ratio, and duration if video; never guess dimensions from filenames or screenshots.
-6. If a saved asset is a still image (`png`, `jpg`, `webp`, `gif`, `avif`, `svg`) and you want to place it on the timeline, convert it to a short H.264 MP4 plate with matching duration before using it as a `video` input. Keep the original still file too, but do not place it as `video`.
-7. Use captured assets or converted plates as grounded proof points alongside other visual material. A good ad can combine product/logo/app screenshots, generated video clips, motion backgrounds, text primitives, and music.
+6. Use saved still images directly as timeline inputs when the real asset should appear on screen, or feed the strongest stills into `xai.imageToVideo` / `xai.referenceToVideo` when motion would make the output stronger. Keep screenshots focused and readable.
+7. Use captured assets as grounded proof points alongside other visual material. A good ad can combine product/logo/app screenshots, generated video clips, motion backgrounds, text primitives, and music.
 8. Scale assets from their measured aspect ratio to fit the output frame and safe areas. For 1080x1920 ads, keep primary visuals inside roughly 80-88% of frame width and reserve enough top/bottom room for text.
-9. Animate visual assets intentionally: use entry animations such as `motion.popIn`, `motion.riseIn`, or `motion.slideY`; use short exit fade/slide segments when a clean transition is needed. For static plates, split the asset into a main segment and a final 0.4-0.7s segment with `motion.fadeOut(...)` to create a real exit.
-10. Generative visuals such as `xai.imagine` are allowed and often useful for product context, lifestyle scenes, abstract transitions, or polished motion. Use website screenshots as optional evidence, not as a rule that forbids generative clips.
+9. Animate visual assets intentionally: use entry animations such as `motion.popIn`, `motion.riseIn`, or `motion.slideY`; use short exit fade/slide segments when a clean transition is needed.
+10. Generative visuals are encouraged when useful. Choose among `xai.imagine` for text-to-video, `xai.imageToVideo` to animate one extracted image/screenshot/product photo, and `xai.referenceToVideo` to guide a generated scene with up to 7 extracted visual references.
 11. For every generated visual prompt, explicitly require a clean scene with no text, no words, no letters, no captions, no logos, no watermarks, and no readable UI copy. AI video generation often corrupts text; all final titles, offers, captions, CTAs, prices, and labels must be created with VidScript `text` primitives.
 12. Do not invent product claims. Extract copy, pricing, feature names, social proof, and CTA language from the site or ask the user.
 
@@ -151,7 +157,7 @@ When the user provides a product, company, landing page, app store listing, or e
 - **Use website assets judiciously for URL-based ads** — browser screenshots, product images, app screenshots, and logos can ground the ad, but they are optional ingredients, not the whole recipe
 - **Avoid full-page screenshot backgrounds** — use above-fold, cropped, or focused screenshots that remain legible at video size; never rely on long website screenshots where the text becomes unreadable
 - **Probe before placing** — get exact dimensions for every real asset, calculate scale from aspect ratio, and set `width`, `height`, `x`, and `y` explicitly
-- **Match asset type to placement** — use real video files for `video` clips. Convert still screenshots/images to MP4 plates before timeline placement; do not point `video` at `.png`, `.jpg`, or `.webp` files.
+- **Match asset type to placement** — use real videos for motion footage and image inputs for still product shots, screenshots, logos, and brand marks. The `video` primitive can place either media type.
 - **Animate assets, not only text** — give product screenshots/logos/cards a clear entrance and a clean exit; split static visuals into main and fade-out segments if needed
 - **Keep generated media text-free** — prompts for AI-generated images/videos must explicitly say no text, no words, no letters, no captions, no logos, no watermarks, and no readable UI copy; add all final copy with VidScript `text` primitives
 - Use 1080x1920 for vertical content (TikTok/Instagram)
@@ -159,6 +165,7 @@ When the user provides a product, company, landing page, app store listing, or e
 - Hook viewers in the first 3 seconds
 - Use high-contrast text on video backgrounds with `stroke` and `stroke_width`
 - Include a clear call-to-action
+- Treat filters as optional finishing tools. Use `vignette`, `saturation`, `contrast`, etc. only when they improve the composition; do not add them by default.
 - Test with `scenerok validate` before rendering
 - Each render costs 1 credit
 
@@ -184,9 +191,9 @@ If a render fails:
 
 ## Sample Video Types
 
-- **Product Promo** — Hero clip + headline + description + CTA + vignette filter
+- **Product Promo** — Hero clip or generated visual + headline + description + CTA
 - **Social Media Hook** — Fast cuts, bold text, speed adjustments
-- **Testimonial** — Speaker clip + quote text + sepia filter
+- **Testimonial** — Speaker clip + quote text + optional styling/filter pass
 - **Meme Remix** — Reaction clip + top/bottom punchline overlays
 - **Title Sequence** — Background clip + glitch shader + bold typography
 

package/skills/shared/vidscript-guide.md

@@ -10,8 +10,8 @@ VidScript is a declarative DSL for composing short-form videos. Write a script,
 4. **Copy working examples** — see `examples/system/` in this skill folder (e.g. `minimal-text-reel.vid`, `ecom-product-launch.vid`, `rokmilk-chocolate-promo.vid`).
 5. **Use URL assets selectively** — if the user gives a website or product URL and browser screenshot tools are available, you can capture above-fold screenshots, product images, app screenshots, and logos for VidScript `input` assets. Do not treat screenshots as mandatory or as the only visual source.
 6. **Probe asset type and dimensions** — before placing real assets, identify image vs video with `file`; inspect width, height, and duration with `ffprobe`, `sips`, or `identify`; then scale from the measured aspect ratio and set explicit `width`, `height`, `x`, and `y`.
-7. **Use still images correctly** — local image inputs can be uploaded, but plain VidScript timeline placement currently uses `video` clips. Convert screenshots/logos/stills to short H.264 MP4 plates before writing `[time] = video asset`.
-8. **Animate real assets** — visual inputs should have entry motion and, where transitions matter, an exit beat. For static plates, split into a main segment and a short final `motion.fadeOut(...)` segment.
+7. **Use still images directly** — `input` supports videos and images. Place still screenshots, logos, and product photos with `video image_input`; the renderer treats images as static clips for the block duration.
+8. **Use the full xAI visual toolkit** — choose `xai.imagine` for text-to-video, `xai.imageToVideo` for animating one extracted image/screenshot/product photo, and `xai.referenceToVideo` for guiding a scene with up to 7 extracted references.
 9. **Generated media has no text** — prompts for AI-generated images/videos must explicitly ask for no text, no words, no letters, no captions, no logos, no watermarks, and no readable UI copy. Use VidScript `text` primitives for all final copy.
 10. **Strict rules** — see `vidscript-strict.md` for invalid patterns (bare `xai.imagine`, bare `eleven.music(...)` without import, trailing params after direct plugin calls, nested quotes in prompts).
 
@@ -59,20 +59,14 @@ sips -g pixelWidth -g pixelHeight asset.png
 identify asset.webp
 ```
 
-Use real videos as `video` clips. For still images such as screenshots, logos, product photos, or PNG captures, create a video plate first:
-
-```bash
-ffmpeg -y -loop 1 -t 4.5 -i screenshot.png -vf "scale=ceil(iw/2)*2:ceil(ih/2)*2,format=yuv420p" -r 30 screenshot-plate.mp4
-```
-
-Then declare the plate:
+Use real videos as motion footage and still images as static clips. The `video` primitive accepts both; the renderer detects image vs video:
 
 ```vidscript
-input screenshot = "assets/video-plates/screenshot-plate.mp4"
+input screenshot = "assets/screenshots/homepage.png"
 [0s .. 4.5s] = video screenshot, width: 1080, height: 1920, x: 0, y: 0, animate: motion.fadeIn(0.35s)
 ```
 
-Do not write `[0s .. 4s] = video screenshot_png` when `screenshot_png` points to `.png`, `.jpg`, or `.webp`. Plugin-generated image surfaces are separate from local still inputs and are only safe when a plugin explicitly returns a `surface` result.
+For URL-based ads, still assets can also drive generated motion: use `xai.imageToVideo(screenshot, "...")` for one strong source image, or `xai.referenceToVideo([product, logo, person], "...")` to guide a new scene with extracted references.
 
 Use the measured width and height to preserve aspect ratio. For a 1080x1920 vertical ad, a common centered fit is:
 
@@ -278,6 +272,8 @@ import eleven from "@elevenlabs/music"
 import motion from "@scenerok/basic-animations"
 
 [-] = video xai.imagine("Cinematic product shot, premium lighting, no text, no words, no letters, no captions, no logos, no watermark, no readable UI copy", aspect_ratio: "9:16", duration: 5)
+[-] = video xai.imageToVideo("https://cdn.example.com/product.png", "Slow premium camera move around the product, no text, no words, no letters, no captions, no logos, no watermark, no readable UI copy", aspect_ratio: "9:16", duration: 6)
+[-] = video xai.referenceToVideo(["https://cdn.example.com/product.png", "https://cdn.example.com/person.png"], "Lifestyle ad shot featuring the referenced product and person, no text, no words, no letters, no captions, no logos, no watermark, no readable UI copy", aspect_ratio: "9:16", duration: 8)
 [-] = audio xai.tts("Welcome to SceneRok", voice: "eve")
 
 # ElevenLabs music package functions require an import alias.
@@ -290,6 +286,16 @@ let bed = eleven.music("Warm premium launch bed", duration: 15, instrumental: tr
 
 `@scenerok/xai` requires an explicit default import. ElevenLabs music validates as `eleven.music(...)`, `eleven.generateMusic(...)`, or `eleven.composeMusic(...)` after `import eleven from "@elevenlabs/music"`. Plugin calls run at compile time; direct media plugin instructions cannot have trailing audio params, so use a `let` binding when you need `volume`, `fade_in`, or `fade_out`.
 
+xAI visual functions:
+
+| Function | Use when |
+|----------|----------|
+| `xai.imagine(prompt, ...)` | You need text-to-video from a clean prompt. |
+| `xai.imageToVideo(image, prompt, ...)` | You have one source image, screenshot, logo, product photo, data URI, or file id to animate. |
+| `xai.referenceToVideo([images...], prompt, ...)` | You have 1-7 reference images that should influence the generated scene without becoming the first frame. Requires a prompt; keep duration <= 10s. |
+
+xAI TTS voices: `eve` for upbeat demos/announcements, `ara` for warm conversational narration, `rex` for business/tutorial content, `sal` for balanced general delivery, and `leo` for authoritative instruction.
+
 **Invalid (will not validate):**
 
 ```vidscript
@@ -340,7 +346,7 @@ Compiler lowers `animate:` into `IRMotionTrack[]` (property-path keyframes). Leg
 [0s .. 5s] = filter "glitch", intensity: 0.5, animate: motion.fadeIn(1s)
 ```
 
-Built-in filters: `monochrome`, `sepia`, `blur`, `chromatic`, `glitch`, `vignette`, `contrast`, `saturation`, `brightness`.
+Built-in filters: `monochrome`, `sepia`, `blur`, `chromatic`, `glitch`, `vignette`, `contrast`, `saturation`, `brightness`. Filters are optional finishing tools; use them only when they improve the composition.
 
 ### Animation functions (`@scenerok/basic-animations`)
 

package/skills/shared/vidscript-sample.md

@@ -22,8 +22,6 @@ input cta_text = "{{cta_text | visit your nearest grocery store}}"
 
 [8s .. 11s] = text cta_text, font: "Bebas Neue", size: 48, color: "#FFD700", x: "50%", y: "80%", align: center, stroke: "#3E1C00", stroke_width: 4, animate: motion.fadeIn(0.8s)
 
-[0s .. 12s] = filter "vignette", intensity: 0.3
-
 output to "product-promo.mp4", resolution: "1080x1920", fps: 30
 ```
 

package/skills/shared/vidscript-strict.md

@@ -20,7 +20,7 @@ When the user gives a product, company, ecommerce, landing page, or app URL and
 
 Do not use full-page or very long website screenshots as video backgrounds; their text is usually illegible at output size. Crop or frame screenshots to the specific visual proof point, and use them sparingly.
 
-Website screenshots are optional source material, not a requirement to build the whole video from screenshots. You may combine them with `xai.imagine` or other generative video plugins for lifestyle scenes, motion backgrounds, transitions, or product context. Do not invent claims; use website copy or ask the user.
+Website screenshots are optional source material, not a requirement to build the whole video from screenshots. You may combine them with `xai.imagine`, `xai.imageToVideo`, `xai.referenceToVideo`, or other generative video plugins for lifestyle scenes, motion backgrounds, transitions, or product context. Do not invent claims; use website copy or ask the user.
 
 ## Rule 2.5: Probe real asset type and dimensions before placement
 
@@ -33,18 +33,10 @@ sips -g pixelWidth -g pixelHeight asset.png
 identify asset.webp
 ```
 
-Use real video files for `video` clips. Plain VidScript input declarations can upload still images, but direct timeline placement currently does not expose a production-safe `[time] = image input` syntax. Do not point `video` at `.png`, `.jpg`, or `.webp` inputs.
-
-For screenshots, logos, and other stills, convert the still to an H.264 MP4 plate first:
-
-```bash
-ffmpeg -y -loop 1 -t 4 -i screenshot.png -vf "scale=ceil(iw/2)*2:ceil(ih/2)*2,format=yuv420p" -r 30 screenshot-plate.mp4
-```
-
-Then use the plate:
+Use real video files for motion footage and still image inputs for screenshots, logos, product photos, and brand marks. The `video` primitive accepts both videos and images; image inputs render as static clips for the block duration.
 
 ```vidscript
-input screenshot = "assets/video-plates/screenshot-plate.mp4"
+input screenshot = "assets/screenshots/homepage.png"
 [0s .. 4s] = video screenshot, width: 1080, height: 1920, x: 0, y: 0, animate: motion.fadeIn(0.35s)
 ```
 
@@ -84,10 +76,16 @@ import xai from "@scenerok/xai"
 import eleven from "@elevenlabs/music"
 
 [-] = video xai.imagine("Prompt here, no text, no words, no letters, no captions, no logos, no watermark, no readable UI copy", aspect_ratio: "9:16", duration: 5)
+[-] = video xai.imageToVideo("https://cdn.example.com/product.png", "Slow camera move around the product, no text, no words, no letters, no captions, no logos, no watermark, no readable UI copy", aspect_ratio: "9:16", duration: 6)
+[-] = video xai.referenceToVideo(["https://cdn.example.com/product.png", "https://cdn.example.com/person.png"], "Lifestyle scene using the referenced product and person, no text, no words, no letters, no captions, no logos, no watermark, no readable UI copy", aspect_ratio: "9:16", duration: 8)
 [-] = audio xai.tts("Voiceover line", voice: "eve")
 [0s .. 15s] = audio eleven.music("Warm premium music bed", duration: 15, instrumental: true)
 ```
 
+Use `xai.imageToVideo` for one extracted screenshot/product/logo image. Use `xai.referenceToVideo` for 1-7 reference images when extracted objects should guide the generated shot; it requires a prompt and duration must be <= 10s.
+
+xAI TTS voices are only `eve`, `ara`, `rex`, `sal`, and `leo`.
+
 For ElevenLabs music, import `@elevenlabs/music` and use `eleven.music(...)`, `eleven.generateMusic(...)`, or `eleven.composeMusic(...)`.
 
 ## Rule 5: Time ranges use `..`
@@ -135,7 +133,7 @@ let bed = eleven.music("Soft premium ad music", duration: 15, instrumental: true
 [0s .. 15s] = filter "saturation", value: 1.12
 ```
 
-`saturation` uses `value`, not `intensity`.
+Filters are optional finishing tools, not required ingredients. Use them only when they improve the visual result. `saturation` uses `value`, not `intensity`.
 
 ## Rule 10: Always end with output