@docyrus/animaguru 0.6.0

package/package.json

@@ -0,0 +1,37 @@
+{
+  "name": "@docyrus/animaguru",
+  "version": "0.6.0",
+  "description": "Agent-friendly AnimaGuru CLI built with CrustJS",
+  "type": "module",
+  "bin": {
+    "animaguru": "dist/animaguru.js"
+  },
+  "files": [
+    "dist/animaguru.js",
+    "skills/",
+    "templates/",
+    "vendor/pixijs-skills/",
+    "README.md",
+    "NOTICE.md"
+  ],
+  "engines": {
+    "node": ">=24"
+  },
+  "license": "UNLICENSED",
+  "homepage": "https://animaguru.com",
+  "author": "Docyrus",
+  "keywords": [
+    "animaguru",
+    "sprites",
+    "cli",
+    "agents",
+    "crustjs"
+  ],
+  "publishConfig": {
+    "access": "public",
+    "registry": "https://registry.npmjs.org/"
+  },
+  "scripts": {
+    "prepack": "node ../scripts/build-cli.mjs"
+  }
+}

package/skills/animaguru/SKILL.md

@@ -0,0 +1,115 @@
+---
+name: animaguru
+description: Use the AnimaGuru CLI to create and animate assets, scaffold video workspaces, and submit finished HTML5 animations or MP4s for public or selected-user sharing.
+---
+
+# AnimaGuru
+
+Use the `animaguru` CLI to generate media assets, create video workspaces, and share finished animations on AnimaGuru. Successful commands print JSON to stdout; instructions and errors go to stderr. Errors exit nonzero.
+
+## Discover and authenticate
+
+For a new animation video workspace, run `animaguru create NAME`. This command takes only the new folder name and installs PixiJS, a branded player, HTML5/MP4 export and Codex/Claude skills. It leaves category and style unset. On the first creative message, read the `animaguru-video` skill: first offer **Explainer**, **Advertisement** or **General Video**, wait for the answer, then offer available visual styles and wait, then gather the creative brief. Honor explicit choices already supplied by the user. `animaguru templates` and the generated `animaguru.templates.json` describe available choices; all style skills are installed locally.
+
+Share the [animation-style gallery](https://animaguru.com/animation-styles), or open that URL in the internal browser when available, while asking the user to choose a style. Read the installed `animaguru.templates.json` for available styles and their skill names; `animaguru templates` lists the current CLI catalog. Offer the local catalog's choices so users select a skill actually installed in their workspace. Templates define appearance and motion; derive audience, message and story from the brief. Local scaffolding is separate from `projects create`, which creates a remote asset project. Never run `create` over an existing workspace.
+
+- Run `animaguru schema` for the installed command structure and flags, and `animaguru catalog` for styles, subject kinds, actions, asset types, models, video settings, and speech voices. Use `--help` on a leaf command for details.
+- Check `animaguru auth status` and `animaguru credits` before generation. If sign-in is needed, run `animaguru auth login --no-browser` and let the user approve the printed browser URL. Do not read or print stored credentials. Agent runners may inject `ANIMAGURU_TOKEN` as a secret.
+- The default service is `https://animaguru.com`. Respect an existing `ANIMAGURU_URL` or pass `--url` to the leaf command when the user chooses another service. HTTP is supported only for loopback development.
+
+## Choose the project and submit work
+
+Reuse the user's chosen project. Otherwise inspect `animaguru projects list` before creating one. Read `animaguru projects get PROJECT_ID` for subjects, character identifiers, generation estimates, and current job state. Use identifiers returned by the service rather than guessing slugs.
+
+```sh
+animaguru projects create --name "Forest cast" --style pixel
+animaguru generate PROJECT_ID --name "Knight" \
+  --description "A blue knight with a red scarf" --actions idle,walk --yes
+```
+
+Read the project ID from `projects create` and job IDs from submission responses. Supported actions depend on the subject kind. Use `--kind` for a different subject kind, based on the catalog.
+
+Generation and reference imports spend credits and require `--yes`. Use it for work the user has authorized, respecting any budget or model constraints. Creating or installing this skill grants no spending authorization. Estimates are ranges; actual provider usage determines charges. Project deletion also requires `--yes` and should follow the user's request to delete that project.
+
+`generate`, `jobs submit`, and `files import` accept optional `--image-model` and `--video-model` flags. These select models for that operation and its explicitly queued animations. Use `animaguru models PROJECT_ID --image-model IMAGE_ID --video-model VIDEO_ID` only when the user wants to change defaults for future jobs. Omitted selections use project defaults, then service defaults. Discover available identifiers from `catalog` rather than hardcoding model names.
+
+## Animate, redraw, or import
+
+Write a JSON file and submit it with `animaguru jobs submit PROJECT_ID --file job.json --yes`. Replace the character identifier with one returned by `projects get`.
+
+Built-in animations:
+
+```json
+{"kind":"animate","character":"CHARACTER_ID","actions":["run","jump"]}
+```
+
+Revise an existing subject:
+
+```json
+{"kind":"redraw","character":"CHARACTER_ID","change":"Give the knight a green helmet"}
+```
+
+Custom motion:
+
+```json
+{"kind":"custom","character":"CHARACTER_ID","name":"Wave hello","prompt":"The character raises one arm, waves twice and lowers it back to its starting pose, staying in place.","frames":["Arm resting by the side","Arm raised with open hand","Hand waving to the right","Arm resting by the side"],"loop":false,"returns":true,"fps":12}
+```
+
+Custom motions require 2–12 frame descriptions, a 20–600 character prompt, and 4–24 fps. Explicit model flags override selections in the JSON file.
+
+Import reference artwork with `animaguru files import PROJECT_ID --file knight.png --name Knight --description "Keep the blue armor" --yes`. PNG, JPEG, and WebP are accepted up to 10 MB. When configured, the service redraws the reference and charges credits; otherwise it imports the original artwork.
+
+## Standalone images, video, music and speech
+
+CLI 0.4.0 adds `assets generate`, `assets submit`, `assets list`, and `assets download`. Use `assets list PROJECT_ID` to discover saved assets and configured provider models. New asset projects can be created with `projects create --name NAME --style hd-cartoon`; that style does not constrain standalone prompts.
+
+```sh
+animaguru assets generate PROJECT_ID --type image --name "Forest" \
+  --prompt "A moonlit watercolor forest" --aspect-ratio 3:2 --yes
+animaguru assets generate PROJECT_ID --type video --name "Forest breeze" \
+  --prompt "Leaves drift slowly in the breeze" --reference IMAGE_BLOB_SHA \
+  --seconds 5 --resolution 768p --mode quality --yes
+animaguru assets generate PROJECT_ID --type music --name "Adventure theme" \
+  --prompt "An instrumental adventure theme with flute and strings" --yes
+animaguru assets generate PROJECT_ID --type speech --name "Welcome" \
+  --prompt "Welcome, traveler." --voice Kore --delivery "Warm and welcoming" --yes
+```
+
+Use `--model` to select a model for any asset type; discover the choices with `catalog` and the server's configured subset with `assets list`. Asset defaults are per type, independently of sprite project defaults. Image backgrounds are retained unless `--transparent` is supplied. Videos require an image asset's `file` SHA from `assets list`, or a character's `art` SHA from `projects get`, in the same project. Validate video options against the selected model's `videoProfiles` in `catalog`; omitted video settings use five seconds and that provider's first resolution/mode. For Gemini speech, `--prompt` is spoken verbatim and `--delivery` is a separate instruction. Music uses Lyria; the Gemini TTS models are for speech.
+
+For ElevenLabs speech, choose `eleven_v4` or `eleven_v4_turbo`, pass an ElevenLabs voice ID with `--voice` (George is the default), and put audio tags in `--prompt` rather than using `--delivery`. For sound effects, use `--type sfx`; the only model is `eleven_text_to_sound_v2`. SFX supports `--seconds` from 0.5 to 30 (default 5), `--loop`, and `--prompt-influence` from 0 to 1 (default 0.3). These additions require CLI 0.5.0 or newer; check `catalog` before using them with an installed CLI.
+
+Use `--dry-run` for local request validation and estimated credits without sign-in or paid work. The estimate does not prove the server has the provider, the credits, or the reference image. Use `--yes` only within the user's existing spending authorization. For file-based requests, write the API asset request as JSON and use `assets submit PROJECT_ID --file asset.json --yes`; `--model` overrides the file's selection. Jobs use the existing `jobs wait PROJECT_ID JOB_ID` workflow. After completion, read the asset id from `assets list` and download with `assets download PROJECT_ID ASSET_ID --output welcome.wav`, or export the complete project ZIP.
+
+## Wait and export
+
+```sh
+animaguru jobs wait PROJECT_ID JOB_ID --timeout 600
+animaguru jobs list PROJECT_ID
+animaguru projects get PROJECT_ID
+animaguru files list PROJECT_ID
+animaguru files export PROJECT_ID --output forest-cast.zip
+```
+
+`jobs wait` tracks only the specified job. Drawing can queue follow-up animations: inspect `jobs list` and wait for the relevant jobs before exporting. A timeout or CLI exit does not cancel server work. Inspect existing jobs before retrying a paid submission to avoid duplicate charges. Report failed jobs and their errors instead of repeatedly submitting the same work.
+
+`files export` downloads a ZIP and refuses to overwrite an existing file. Choose a fresh output path. Inspect the exported manifest and actual assets before integrating them into the game or app; use their real dimensions, frame ordering, and animation metadata.
+
+## Submit a finished animation to AnimaGuru
+
+`submit` hosts a finished animation, separate from paid asset generation and `files export`. In a scaffolded video project, `animaguru submit --yes` builds its portable HTML5 ZIP and uploads it privately. Use `--file` for an existing AnimaGuru HTML5 export or MP4; only the export is uploaded, never the source workspace. `--dry-run` inspects the file, metadata and audience locally without signing in or uploading.
+
+```sh
+animaguru submit --share "reviewer@example.com" --yes
+animaguru submit --visibility public --poster public/assets/cover.png --yes
+animaguru submit --file production/exports/film.mp4 --title "My film" --yes
+animaguru videos list --scope mine
+animaguru videos list --scope shared
+animaguru videos get VIDEO_ID
+```
+
+Submissions default to private. `--share` is a comma-separated list of verified AnimaGuru account emails; selected viewers sign in to watch. `--visibility public` lists the animation at [Videos](https://animaguru.com/videos) and permits anyone to watch, download its export, and embed an HTML5 player. Choose the audience from the user's request; a request to make or export a film alone does not authorize sharing it. `--yes` acknowledges the upload and selected audience, and spends no generation credits.
+
+The JSON result returns the video ID and watch URL. Owners manage details and recipients on that page, or run `animaguru videos share VIDEO_ID --visibility private --share "reviewer@example.com" --yes`; this replaces the entire recipient list. Public sharing uses `--visibility public` without `--share`. Removing a recipient or making a public film private blocks previous playback URLs immediately. `animaguru videos delete VIDEO_ID --yes` removes the hosted files.
+
+Uploads use checksum-verified parts. After an interrupted submission, inspect the printed ID first. If all parts arrived, `animaguru videos complete VIDEO_ID` safely retries finalization and returns the existing result when already complete. Otherwise cancel that draft with `videos delete --yes` before submitting again. Do not silently delete a potentially successful publication after a network timeout.

package/skills/animaguru-advertising/SKILL.md

@@ -0,0 +1,25 @@
+---
+name: animaguru-advertising
+description: Develop and produce product, launch, offer, editorial and creator-led advertising in an AnimaGuru video workspace. Use after the Advertisement purpose is selected.
+---
+
+# AnimaGuru advertising
+
+Read sibling `animaguru-video` and the selected visual skill. Purpose describes the video's job; visual style remains independently selectable. For new work, run the shared compact interview once and fold workflow-specific missing questions into it. Reuse explicit answers, saved project choices and completed briefs; honor a requested interview skip.
+
+Infer a suitable workflow from the request or clarify it in that interview. Do not add a mandatory menu when the user's intent is clear. Save a listed workflow ID in `animaguru.project.json` only when it fits; leave it null for a custom brief. Read only the applicable reference:
+
+- **Product Proof Ad** (`product-proof`): Demonstrate an actual product interaction, mechanism or output. Read [the workflow](references/product-proof.md).
+- **Product Launch & Feature Reveal** (`product-launch`): Introduce what is newly available with accurate product evidence. Read [the workflow](references/product-launch.md).
+- **Comparison & Transformation** (`comparison`): Show a supported comparison under matched conditions. Read [the workflow](references/comparison.md).
+- **Offer & Promotion** (`offer-promotion`): Present the actual offer, terms and next step. Read [the workflow](references/offer-promotion.md).
+- **Creator & Testimonial Edit** (`creator-testimonial`): Edit supplied speech and media without changing its meaning. Read [the workflow](references/creator-testimonial.md).
+- **Editorial Advertorial** (`editorial-advertorial`): Explain a buyer-relevant topic and integrate a product with sourced claims. Read [the workflow](references/editorial-advertorial.md).
+- **Brand Identity & Bumper** (`brand-bumper`): Stage the supplied mark and identity through a short signature film. Read [the workflow](references/brand-bumper.md).
+- **Game & Reward Promo** (`game-reward`): Show actual gameplay or a clearly illustrative reward reveal. Read [the workflow](references/game-reward.md).
+
+Develop an original sequence from the user's sources, audience, tone, duration and desired outcome. Avoid importing fixed scene counts, mandatory emotional arcs, default audiences or a compulsory CTA. Respect supplied narration/music preferences. Discover AnimaGuru generation models and costs through the local main skill; this purpose selection does not authorize paid jobs.
+
+Use `src/studies/media.ts` for optional deterministic source-time/trim mapping and cue comparison; prepare footage locally and await decoded frames before capture. `npm run review` collects actual canvas text bounds, deterministic seek comparisons and review frames through the browser. Preserve resource timing and the HTML5 embed/export contract. Review moving playback and audio as well as numerical checks.
+
+Legacy `category: "advertorial"` means Advertisement with editorial intent. Reuse its selected style/brief; when no workflow is saved, use `editorial-advertorial` as the compatible interpretation. Do not re-interview a finished project merely to rename its category.

package/skills/animaguru-advertising/references/brand-bumper.md

@@ -0,0 +1,11 @@
+# Brand Identity & Bumper
+
+Stage the supplied mark and identity through a short signature film.
+
+Fold this missing information into the shared quick interview: **Which correct mark/wordmark, transformations and loop or ending requirements should guide the piece?** Reuse supplied answers. Save the chosen angle, constraints and evidence in `production/brief.md`; a workflow is not a fixed story template.
+
+- Use the actual vector mark or a verified high-resolution source. Keep brand geometry recognizable and record any permitted alterations.
+- Select a material-native transformation: print, carve, fold, assemble, mask or shape match. Avoid turning every brand into the same particle reveal.
+- For loops, match image state and velocity through the boundary. If a closing lockup is requested, allow enough time to recognize it.
+
+Completion: Mark accuracy, wordmark spacing, required brand hold and loop continuity. Use `animaguru-video` for the common production, budget, review and HTML5/MP4 contract.

package/skills/animaguru-advertising/references/comparison.md

@@ -0,0 +1,11 @@
+# Comparison & Transformation
+
+Show a supported comparison under matched conditions.
+
+Fold this missing information into the shared quick interview: **What is the comparison basis, and do we have matched inputs, outputs, units and timeframes?** Reuse supplied answers. Save the chosen angle, constraints and evidence in `production/brief.md`; a workflow is not a fixed story template.
+
+- Record the criteria and conditions before designing split frames or transformations. A visual before/after must not quietly change scale, crop or starting inputs.
+- Separate measured facts from illustrative scenarios. Keep units, baselines, sample scope and relevant limitations attached to the evidence.
+- Preserve semantic identities during comparison: the same object or metric follows one transform/camera model. Show the actual difference rather than magnifying it through arbitrary animation.
+
+Completion: Matched conditions and units; no fabricated metrics or misleading crop/scale changes. Use `animaguru-video` for the common production, budget, review and HTML5/MP4 contract.

package/skills/animaguru-advertising/references/creator-testimonial.md

@@ -0,0 +1,11 @@
+# Creator & Testimonial Edit
+
+Edit supplied speech and media without changing its meaning.
+
+Fold this missing information into the shared quick interview: **Which supplied recordings, statements and people should appear, and what may be trimmed?** Reuse supplied answers. Save the chosen angle, constraints and evidence in `production/brief.md`; a workflow is not a fixed story template.
+
+- Create a transcript and source-time edit list; preserve sentence meaning and never cut within a word. Use mediaCue() for deterministic trim/rate mapping.
+- Treat real testimony as attributed evidence. A scripted synthetic presenter is a narrator, not a fabricated customer; avoid invented endorsements or implied independent experience.
+- Compose captions, product evidence and faces into safe regions. Use the chosen visual style for inserts; retain the original source and produce edited files separately.
+
+Completion: Listen to cuts, check word boundaries and attribution, verify captions and face/product visibility. Use `animaguru-video` for the common production, budget, review and HTML5/MP4 contract.

package/skills/animaguru-advertising/references/editorial-advertorial.md

@@ -0,0 +1,11 @@
+# Editorial Advertorial
+
+Explain a buyer-relevant topic and integrate a product with sourced claims.
+
+Fold this missing information into the shared quick interview: **Which buyer-relevant topic, sources and product relationship should the video explain?** Reuse supplied answers. Save the chosen angle, constraints and evidence in `production/brief.md`; a workflow is not a fixed story template.
+
+- Build the factual explanation from the source material. Distinguish fact, opinion, product claim and illustrative scenario in the internal source map.
+- Choose structure from the topic and intended placement; integrate the product where it helps the explanation. Do not disguise unsupported promotion as sourced evidence.
+- Use any chosen style. Diagram, editorial print, cutout and real-media treatments can all work; no compulsory presenter, case-file framing or fixed emotional arc.
+
+Completion: Facts and product relationship are clear, every substantive claim is supported, and the topic remains understandable. Use `animaguru-video` for the common production, budget, review and HTML5/MP4 contract.

package/skills/animaguru-advertising/references/game-reward.md

@@ -0,0 +1,11 @@
+# Game & Reward Promo
+
+Show actual gameplay or a clearly illustrative reward reveal.
+
+Fold this missing information into the shared quick interview: **Which real gameplay or reward assets are available, and what may be dramatized?** Reuse supplied answers. Save the chosen angle, constraints and evidence in `production/brief.md`; a workflow is not a fixed story template.
+
+- Select an actual action or clearly illustrative reward choreography, and preserve asset identity across anticipation, action and result.
+- Keep highlights readable: deliberate anticipation, a controlled peak, then a clean reveal stage. Effect intensity is a parameter, not a requirement to fill the screen with flashes.
+- This workflow creates a deterministic video. A playable ad requires an explicitly requested interaction deliverable with a state machine, controls and separate interaction review.
+
+Completion: Gameplay truth, reward clarity and no lingering motion or effect obscuring the result. Use `animaguru-video` for the common production, budget, review and HTML5/MP4 contract.

package/skills/animaguru-advertising/references/offer-promotion.md

@@ -0,0 +1,11 @@
+# Offer & Promotion
+
+Present the actual offer, terms and next step.
+
+Fold this missing information into the shared quick interview: **What are the exact offer, eligibility, price, dates and destination, and what wording is required?** Reuse supplied answers. Save the chosen angle, constraints and evidence in `production/brief.md`; a workflow is not a fixed story template.
+
+- Keep one authoritative offer record in production/brief.md. Use those values in narration, on-screen text and the end card.
+- Design a hierarchy for the actual buyer decision. Place essential terms where they remain readable at the target placement and aspect ratio.
+- Use urgency only when supplied dates or availability justify it. Verify the requested link or next action before writing the final CTA.
+
+Completion: Offer details match supplied terms and essential copy is readable in the final card. Use `animaguru-video` for the common production, budget, review and HTML5/MP4 contract.

package/skills/animaguru-advertising/references/product-launch.md

@@ -0,0 +1,11 @@
+# Product Launch & Feature Reveal
+
+Introduce what is newly available with accurate product evidence.
+
+Fold this missing information into the shared quick interview: **What is newly available, what should viewers remember, and which capabilities are still planned?** Reuse supplied answers. Save the chosen angle, constraints and evidence in `production/brief.md`; a workflow is not a fixed story template.
+
+- Read positioning and current release material. Distinguish shipped capability, release candidate, forthcoming feature and illustrative concept.
+- Find the product-specific visual action that carries the message, then build a sequence around that action. Do not default to a fixed problem/solution scene count.
+- Use brand assets and actual interface states. A feature label alone is weaker than an interaction or output that explains its value; let the brief determine narration and CTA.
+
+Completion: Release status, names and features match sources; the final message has a readable hold. Use `animaguru-video` for the common production, budget, review and HTML5/MP4 contract.

package/skills/animaguru-advertising/references/product-proof.md

@@ -0,0 +1,11 @@
+# Product Proof Ad
+
+Demonstrate an actual product interaction, mechanism or output.
+
+Fold this missing information into the shared quick interview: **Which benefit can viewers see demonstrated, and which real interaction or output proves it?** Reuse supplied answers. Save the chosen angle, constraints and evidence in `production/brief.md`; a workflow is not a fixed story template.
+
+- Inspect the product URL, supplied screens or mechanism references before choosing the proof moment. Trace the intended state change to actual product behavior.
+- Write concise cue-level claims and map them to a visible interaction, a source fact or a measured output. The strongest useful demonstration may need fewer features than a comprehensive tour.
+- Use Interface Motion, media framing, technical geometry or any chosen visual style. Preserve labels, inputs and outcomes; identify illustrative demonstrations when no real capture is available.
+
+Completion: The important input, action and result are readable; every product claim has support. Use `animaguru-video` for the common production, budget, review and HTML5/MP4 contract.

package/skills/animaguru-analog-film-tape/SKILL.md

@@ -0,0 +1,29 @@
+---
+name: animaguru-analog-film-tape
+description: Build Analog Film & Tape visuals and motion in an AnimaGuru PixiJS video workspace. Use when this visual style is chosen for an explainer, advertisement or general video.
+---
+
+# Analog Film & Tape
+
+Projected-film cadence or camcorder texture over original scenes, with controlled weave, exposure and medium-specific transitions. Subject, audience, emotional tone and story come from the user's brief. This style supports Explainer, Advertisement and General Video.
+
+## Establish direction
+
+Follow sibling `animaguru-video` for purpose → style → compact interview before new production. Reuse explicit choices and completed briefs; honor a requested interview skip. Share [the style gallery](https://animaguru.com/animation-styles#analog-film-tape). Fold missing visual questions into the shared interview:
+
+- Do you want projected film or camcorder tape, and which intensity?
+- What frame shape, overlays or intertitles should be used?
+
+## Build the look and movement
+
+Read `pixijs` and the relevant Graphics, Text, Container, Assets or Mesh skills. Read `animaguru` before generating assets; discover current models and estimates, respect the user's budget, and reuse completed media. Essential text and exact numerical geometry belong in authored canvas content.
+
+- Select film or tape, then keep its artifacts coherent. Film can use gate weave, shutter/flicker and scratches; tape uses luma/chroma distortion, tracking and optional OSD.
+- Compute every artifact from absolute time and fixed seeds. Sampling subject motion and adding output-frame damage are separate clocks.
+- Moderate effects over essential text. The source examples do not require horror, empty corridors, slapstick, a pianist or a particular period story.
+
+Use the [production recipe](references/recipe.md) for the bundled original study and port-specific decisions. It is a technique example, not a prescribed film. Keep motions a function of absolute seconds; separate drawing cadence from camera/light cadence when the material calls for it. Prepare assets locally, preserve async seeking and register actual resource/cue times. Keep essential type editable and localized.
+
+## Review and delivery
+
+Inspect text readability and accidental blank frames; replay stability and correct medium-specific artifacts. Check representative full-resolution frames, moving playback, desktop/mobile fit and cold seeks. Follow `animaguru-video` for production records, audio mixing and HTML5 delivery; export MP4 when requested. Describe the actual 2D/2.5D rendering method accurately. Physically rendered 3D remains deferred.

package/skills/animaguru-analog-film-tape/references/recipe.md

@@ -0,0 +1,23 @@
+# Analog Film & Tape production recipe
+
+The workspace includes an executable original study in `src/studies/scenes.ts`, selected with `analog-film-tape`. Its drawing commands are consumed by `src/studies/pixi-renderer.ts`; geometry and time sampling are shared with the gallery renderer. All copy lives in `shared/locales/en/style-studies.json`.
+
+In an untouched starter, run `npm run example -- analog-film-tape`, then `npm run dev`. The command refuses to replace an authored film, retains starter backups in `production/example-backup/`, and writes an 8-second study with its own resource tracks. `npm run export:html` and `npm run export:mp4` use this installed film normally. To use the recipe inside an existing film, import `studyFrame()` and `StudyRenderer`, then compose the selected scene into the project's timeline instead of running the installer.
+
+## Adaptation decisions
+
+- Select film or tape, then keep its artifacts coherent. Film can use gate weave, shutter/flicker and scratches; tape uses luma/chroma distortion, tracking and optional OSD.
+- Compute every artifact from absolute time and fixed seeds. Sampling subject motion and adding output-frame damage are separate clocks.
+- Moderate effects over essential text. The source examples do not require horror, empty corridors, slapstick, a pianist or a particular period story.
+
+The study is silent, original procedural art. Photographic studies use illustrated media cards and product studies use an illustrative object; replace these with actual supplied/generated assets for production. It demonstrates material, transforms and layout rather than proving real product claims. Configure an original subject, palette, scene sequence, duration and soundtrack from the brief.
+
+Use `src/studies/timing.ts` for deterministic easing, seeded variation, measured stroke truncation and cue helpers. `window.animaguru.texts` exposes visible study text bounds for `npm run review`; text declarations alone do not count as visual proof. Inspect the actual frames as well.
+
+## Sources and attribution
+
+Inspired by the following pinned references; source-specific 3D/media dependencies are not bundled. New study art and scene geometry are original. The workspace's `VIDEO-STYLE-NOTICES.txt` preserves the repository notices and clarifies third-party asset scope.
+
+- [styles/silent-film/STYLE.md](https://github.com/lemomo-ai/lemo-opuscar/blob/b65efe6ea393fdc71212898ea4c57c754cfefa46/styles/silent-film/STYLE.md)
+- [styles/silent-film/demo/engine/film.js](https://github.com/lemomo-ai/lemo-opuscar/blob/b65efe6ea393fdc71212898ea4c57c754cfefa46/styles/silent-film/demo/engine/film.js)
+- [styles/backrooms/STYLE.md](https://github.com/lemomo-ai/lemo-opuscar/blob/b65efe6ea393fdc71212898ea4c57c754cfefa46/styles/backrooms/STYLE.md)

package/skills/animaguru-animated-data-visualization/SKILL.md

@@ -0,0 +1,39 @@
+---
+name: animaguru-animated-data-visualization
+description: Build animated chart videos from supplied data with traceable values, honest scales and readable comparisons. Use for the Animated Data Visualization visual style in an AnimaGuru video workspace.
+---
+
+# Animated Data Visualization
+
+Use charts, numbers and annotations as the visual language of an Explainer, Advertisement or General Video film. The brief determines the question and narrative; the data determines which claims the film can support.
+
+## Establish the direction
+
+Follow the sibling `animaguru-video` category → style → quick interview flow before new production. Reuse supplied answers and completed briefs; honor an explicit request to skip the interview. Share [the style preview](https://animaguru.com/animation-styles#animated-data-visualization). Include missing essentials in the shared interview:
+
+- What data file or source should be used, and what do its units, categories and dates mean?
+- Which comparison or finding matters, and is there an approved claim to verify?
+- What visual density, palette, labeling and source attribution suit the audience and placement?
+
+## Establish the data contract
+
+Read [the data contract](references/data-contract.md) when ingesting data and before delivery. Preserve the source, transformations and chart-ready values in `production/`. If real data is missing, request it or use conspicuously labeled illustrative data with the user's agreement. Do not invent business metrics to fill a scene.
+
+## Design and build
+
+- Read `pixijs`, graphics and text guidance. Choose chart geometry for the relationship: bars for categorical magnitude, lines for ordered time, dots for comparisons, scatterplots for relationships. Record a short reason for the choice.
+- Keep bar baselines at zero; use meaningful, explicit domains for other charts. A scale change needs a visible transition or annotation. Use common scales for direct comparisons. Preserve negative values, missingness and uncertainty where relevant.
+- Directly label essential values and units. Reserve space for source/date notes. Choose accessible highlight colors; reinforce distinctions with labels or shapes.
+- Stage the chart: establish its frame, reveal series, then emphasize the supported comparison. The story can take any order suited to the brief, but the visualization must not suggest evidence the source lacks.
+- Derive positions, displayed numbers and annotations from one chart model. Count-up values are temporary interpolation states, not observations; finish at the exact formatted source value. Do not smoothly interpolate discrete observations in a way that implies measured intermediate data.
+- Keep label layout stable while marks animate. Compute text bounds and chart domains before capture. Avoid fake depth and decorative movement that distorts perceived magnitude.
+- Generate charts in code. AnimaGuru may supply authorized narration, music or contextual illustrations; generated imagery must not contain the authoritative plotted numbers.
+- Follow the shared absolute timeline and resource metadata contract, registering series, annotations and captions separately where useful.
+
+## Review and completion
+
+Verify every final plotted value and claim against the transformed data programmatically, then manually check representative extremes, missing values and at least five values when available. Inspect chart transitions, label collisions and small-screen legibility. Deliver the source and transformation record, chart-ready data, validation notes and working HTML5 film. Follow `animaguru-video` for requested MP4 delivery.
+
+## Additional visual treatments
+
+Read [the material and motion variants](references/variants.md) when the brief calls for a specialized treatment. Choose the relevant recipe without imposing its example story.

package/skills/animaguru-animated-data-visualization/references/data-contract.md

@@ -0,0 +1,16 @@
+# Data contract for an animated chart
+
+Keep enough evidence to reproduce the figure. Use the user's existing data conventions when present; these are the minimum fields to record, not a required file format.
+
+- Source filename or URL, access date, sheet/table/range, and source hash for local files.
+- Row meaning, dimensions, measures, units, date range, timezone and population covered.
+- Parsing decisions: decimal separators, currency/percent interpretation, dates, missing values and duplicate rows.
+- Filtering, aggregation, conversion, sorting and rounding steps, with original values preserved.
+- Chart-ready values keyed by stable series/category IDs; chart domains and display formatting.
+- Each numerical claim and its supporting calculation. Identify estimates, uncertainty, projections or illustrative data explicitly.
+
+Validate numerics before rendering. Reject non-finite values. Distinguish zero from absent data. Confirm whether percentages arrive as 0–1 fractions or 0–100 values. Do not add percentages or rates across groups without an appropriate denominator; weighted and unweighted averages answer different questions. Compare dates in a consistent timezone and sort chronologically.
+
+Keep calculations separate from animation interpolation. At each reveal's settled frame, compare the plotted model and displayed label with the expected chart-ready value. Verify totals and rank labels after filtering, and check ties rather than inventing a unique winner. If source and requested claim conflict, describe the discrepancy and use a supported claim or wait for corrected data.
+
+For sensitive source data, the static HTML5 export only needs approved chart-ready values and attribution. Raw source files can stay in `production/`; do not automatically copy them to `public/assets/` or the embedded package.

package/skills/animaguru-animated-data-visualization/references/variants.md

@@ -0,0 +1,17 @@
+# Pinned annotations and sonification
+
+Choose one coherent treatment from the brief; these are visual/motion recipes, not mandatory stories. They apply to Explainer, Advertisement and General Video.
+
+## Data-space annotations
+
+Store annotation anchors as actual data coordinates and project them through the same scale/camera as marks. Reserve a memory zone if a note persists after its original point leaves focus. Later data must not collide with old notes.
+
+## Identity-preserving mark transforms
+
+Maintain IDs as points become bars or another compatible representation. Domains, missingness, baselines and units stay explicit. If a representation changes meaning, make that change legible rather than hiding it with a morph.
+
+## Optional sonification
+
+Derive note timing or pitch from a documented mapping and one shared cue table. Sonification can emphasize structure but does not prove a factual claim. Test actual values and ordering against the input before adding it.
+
+Use the bundled absolute-time helpers in `src/studies/timing.ts` where appropriate. Keep actual resources and cues in the timeline, then inspect cold seeks, full-speed motion and exported frames. The shared video skill governs interviews, generation scope and delivery.

package/skills/animaguru-art-deco-motion/SKILL.md

@@ -0,0 +1,29 @@
+---
+name: animaguru-art-deco-motion
+description: Build Art Deco Motion visuals and motion in an AnimaGuru PixiJS video workspace. Use when this visual style is chosen for an explainer, advertisement or general video.
+---
+
+# Art Deco Motion
+
+Geometric ornament, metallic keylines and lacquer-like planes opening through symmetry and mechanical motion. Subject, audience, emotional tone and story come from the user's brief. This style supports Explainer, Advertisement and General Video.
+
+## Establish direction
+
+Follow sibling `animaguru-video` for purpose → style → compact interview before new production. Reuse explicit choices and completed briefs; honor a requested interview skip. Share [the style gallery](https://animaguru.com/animation-styles#art-deco-motion). Fold missing visual questions into the shared interview:
+
+- Should the treatment be restrained or ornate?
+- Which metal, accent and type direction fits the subject?
+
+## Build the look and movement
+
+Read `pixijs` and the relevant Graphics, Text, Container, Assets or Mesh skills. Read `animaguru` before generating assets; discover current models and estimates, respect the user's budget, and reuse completed media. Essential text and exact numerical geometry belong in authored canvas content.
+
+- Anchor metallic bands and sheen to the ornament surface; a screen-fixed shine sliding over everything loses material identity.
+- Build transitions from mirrored doors, fans, stepped arches or dial geometry. Keep the composition axis stable until a motivated change.
+- Count lights from cue times and preserve glyph silhouettes. Period settings, luxury claims and deadline plots are not style requirements.
+
+Use the [production recipe](references/recipe.md) for the bundled original study and port-specific decisions. It is a technique example, not a prescribed film. Keep motions a function of absolute seconds; separate drawing cadence from camera/light cadence when the material calls for it. Prepare assets locally, preserve async seeking and register actual resource/cue times. Keep essential type editable and localized.
+
+## Review and delivery
+
+Inspect symmetry, metallic texture attachment and ornament hierarchy; bulb letterform legibility and mechanical alignment. Check representative full-resolution frames, moving playback, desktop/mobile fit and cold seeks. Follow `animaguru-video` for production records, audio mixing and HTML5 delivery; export MP4 when requested. Describe the actual 2D/2.5D rendering method accurately. Physically rendered 3D remains deferred.

package/skills/animaguru-art-deco-motion/references/recipe.md

@@ -0,0 +1,22 @@
+# Art Deco Motion production recipe
+
+The workspace includes an executable original study in `src/studies/scenes.ts`, selected with `art-deco-motion`. Its drawing commands are consumed by `src/studies/pixi-renderer.ts`; geometry and time sampling are shared with the gallery renderer. All copy lives in `shared/locales/en/style-studies.json`.
+
+In an untouched starter, run `npm run example -- art-deco-motion`, then `npm run dev`. The command refuses to replace an authored film, retains starter backups in `production/example-backup/`, and writes an 8-second study with its own resource tracks. `npm run export:html` and `npm run export:mp4` use this installed film normally. To use the recipe inside an existing film, import `studyFrame()` and `StudyRenderer`, then compose the selected scene into the project's timeline instead of running the installer.
+
+## Adaptation decisions
+
+- Anchor metallic bands and sheen to the ornament surface; a screen-fixed shine sliding over everything loses material identity.
+- Build transitions from mirrored doors, fans, stepped arches or dial geometry. Keep the composition axis stable until a motivated change.
+- Count lights from cue times and preserve glyph silhouettes. Period settings, luxury claims and deadline plots are not style requirements.
+
+The study is silent, original procedural art. Photographic studies use illustrated media cards and product studies use an illustrative object; replace these with actual supplied/generated assets for production. It demonstrates material, transforms and layout rather than proving real product claims. Configure an original subject, palette, scene sequence, duration and soundtrack from the brief.
+
+Use `src/studies/timing.ts` for deterministic easing, seeded variation, measured stroke truncation and cue helpers. `window.animaguru.texts` exposes visible study text bounds for `npm run review`; text declarations alone do not count as visual proof. Inspect the actual frames as well.
+
+## Sources and attribution
+
+Inspired by the following pinned references; source-specific 3D/media dependencies are not bundled. New study art and scene geometry are original. The workspace's `VIDEO-STYLE-NOTICES.txt` preserves the repository notices and clarifies third-party asset scope.
+
+- [styles/art-deco/STYLE.md](https://github.com/lemomo-ai/lemo-opuscar/blob/b65efe6ea393fdc71212898ea4c57c754cfefa46/styles/art-deco/STYLE.md)
+- [styles/art-deco/demo/engine/deco.js](https://github.com/lemomo-ai/lemo-opuscar/blob/b65efe6ea393fdc71212898ea4c57c754cfefa46/styles/art-deco/demo/engine/deco.js)

package/skills/animaguru-ascii-crt/SKILL.md

@@ -0,0 +1,29 @@
+---
+name: animaguru-ascii-crt
+description: Build ASCII & CRT visuals and motion in an AnimaGuru PixiJS video workspace. Use when this visual style is chosen for an explainer, advertisement or general video.
+---
+
+# ASCII & CRT
+
+Real glyph-grid imagery, terminal text and restrained phosphor glow with deliberate typing and screen behavior. Subject, audience, emotional tone and story come from the user's brief. This style supports Explainer, Advertisement and General Video.
+
+## Establish direction
+
+Follow sibling `animaguru-video` for purpose → style → compact interview before new production. Reuse explicit choices and completed briefs; honor a requested interview skip. Share [the style gallery](https://animaguru.com/animation-styles#ascii-crt). Fold missing visual questions into the shared interview:
+
+- Which phosphor hue and balance of text versus imagery fits?
+- How much screen aging should be visible?
+
+## Build the look and movement
+
+Read `pixijs` and the relevant Graphics, Text, Container, Assets or Mesh skills. Read `animaguru` before generating assets; discover current models and estimates, respect the user's budget, and reuse completed media. Essential text and exact numerical geometry belong in authored canvas content.
+
+- Build a glyph atlas and choose characters by measured coverage, with blank cells below a threshold. Negative space makes images recognizable.
+- Derive afterglow from known earlier cue samples, never a history buffer that changes with playback order. Snap grid content while camera scaling may be smooth.
+- Match artifacts to the medium: monochrome phosphor has no RGB grille, and CRT is not VHS tape. Keep required copy readable through the treatment.
+
+Use the [production recipe](references/recipe.md) for the bundled original study and port-specific decisions. It is a technique example, not a prescribed film. Keep motions a function of absolute seconds; separate drawing cadence from camera/light cadence when the material calls for it. Prepare assets locally, preserve async seeking and register actual resource/cue times. Keep essential type editable and localized.
+
+## Review and delivery
+
+Inspect glyph legibility and stable cell placement; cold seeks, afterglow and loop boundary continuity. Check representative full-resolution frames, moving playback, desktop/mobile fit and cold seeks. Follow `animaguru-video` for production records, audio mixing and HTML5 delivery; export MP4 when requested. Describe the actual 2D/2.5D rendering method accurately. Physically rendered 3D remains deferred.

package/skills/animaguru-ascii-crt/references/recipe.md

@@ -0,0 +1,22 @@
+# ASCII & CRT production recipe
+
+The workspace includes an executable original study in `src/studies/scenes.ts`, selected with `ascii-crt`. Its drawing commands are consumed by `src/studies/pixi-renderer.ts`; geometry and time sampling are shared with the gallery renderer. All copy lives in `shared/locales/en/style-studies.json`.
+
+In an untouched starter, run `npm run example -- ascii-crt`, then `npm run dev`. The command refuses to replace an authored film, retains starter backups in `production/example-backup/`, and writes an 8-second study with its own resource tracks. `npm run export:html` and `npm run export:mp4` use this installed film normally. To use the recipe inside an existing film, import `studyFrame()` and `StudyRenderer`, then compose the selected scene into the project's timeline instead of running the installer.
+
+## Adaptation decisions
+
+- Build a glyph atlas and choose characters by measured coverage, with blank cells below a threshold. Negative space makes images recognizable.
+- Derive afterglow from known earlier cue samples, never a history buffer that changes with playback order. Snap grid content while camera scaling may be smooth.
+- Match artifacts to the medium: monochrome phosphor has no RGB grille, and CRT is not VHS tape. Keep required copy readable through the treatment.
+
+The study is silent, original procedural art. Photographic studies use illustrated media cards and product studies use an illustrative object; replace these with actual supplied/generated assets for production. It demonstrates material, transforms and layout rather than proving real product claims. Configure an original subject, palette, scene sequence, duration and soundtrack from the brief.
+
+Use `src/studies/timing.ts` for deterministic easing, seeded variation, measured stroke truncation and cue helpers. `window.animaguru.texts` exposes visible study text bounds for `npm run review`; text declarations alone do not count as visual proof. Inspect the actual frames as well.
+
+## Sources and attribution
+
+Inspired by the following pinned references; source-specific 3D/media dependencies are not bundled. New study art and scene geometry are original. The workspace's `VIDEO-STYLE-NOTICES.txt` preserves the repository notices and clarifies third-party asset scope.
+
+- [styles/ascii-crt/STYLE.md](https://github.com/lemomo-ai/lemo-opuscar/blob/b65efe6ea393fdc71212898ea4c57c754cfefa46/styles/ascii-crt/STYLE.md)
+- [styles/ascii-crt/demo/term.js](https://github.com/lemomo-ai/lemo-opuscar/blob/b65efe6ea393fdc71212898ea4c57c754cfefa46/styles/ascii-crt/demo/term.js)

package/skills/animaguru-blueprint-drafting/SKILL.md

@@ -0,0 +1,29 @@
+---
+name: animaguru-blueprint-drafting
+description: Build Blueprint Drafting visuals and motion in an AnimaGuru PixiJS video workspace. Use when this visual style is chosen for an explainer, advertisement or general video.
+---
+
+# Blueprint Drafting
+
+Measured line work, construction marks, sections and dimensions on a drafting surface with progressive assembly. Subject, audience, emotional tone and story come from the user's brief. This style supports Explainer, Advertisement and General Video.
+
+## Establish direction
+
+Follow sibling `animaguru-video` for purpose → style → compact interview before new production. Reuse explicit choices and completed briefs; honor a requested interview skip. Share [the style gallery](https://animaguru.com/animation-styles#blueprint-drafting). Fold missing visual questions into the shared interview:
+
+- Which drawings, units and labels must be technically accurate?
+- Should the paper feel clean, aged or purely digital?
+
+## Build the look and movement
+
+Read `pixijs` and the relevant Graphics, Text, Container, Assets or Mesh skills. Read `animaguru` before generating assets; discover current models and estimates, respect the user's budget, and reuse completed media. Essential text and exact numerical geometry belong in authored canvas content.
+
+- Keep parts, outlines, construction lines and labels in a semantic model. Draw in meaningful order, then animate separation along defined axes.
+- Dimensions and leader endpoints follow the same world-to-screen transform as the parts. Scale line weights for the framing without losing their hierarchy.
+- Use actual units only when supplied or verified; conceptual dimensions are clearly illustrative. Exploded components need prepared interiors and collision-free destinations.
+
+Use the [production recipe](references/recipe.md) for the bundled original study and port-specific decisions. It is a technique example, not a prescribed film. Keep motions a function of absolute seconds; separate drawing cadence from camera/light cadence when the material calls for it. Prepare assets locally, preserve async seeking and register actual resource/cue times. Keep essential type editable and localized.
+
+## Review and delivery
+
+Inspect line completion and dimensional truth; leader attachment and readable line weights across camera moves. Check representative full-resolution frames, moving playback, desktop/mobile fit and cold seeks. Follow `animaguru-video` for production records, audio mixing and HTML5 delivery; export MP4 when requested. Describe the actual 2D/2.5D rendering method accurately. Physically rendered 3D remains deferred.

package/skills/animaguru-blueprint-drafting/references/recipe.md

@@ -0,0 +1,22 @@
+# Blueprint Drafting production recipe
+
+The workspace includes an executable original study in `src/studies/scenes.ts`, selected with `blueprint-drafting`. Its drawing commands are consumed by `src/studies/pixi-renderer.ts`; geometry and time sampling are shared with the gallery renderer. All copy lives in `shared/locales/en/style-studies.json`.
+
+In an untouched starter, run `npm run example -- blueprint-drafting`, then `npm run dev`. The command refuses to replace an authored film, retains starter backups in `production/example-backup/`, and writes an 8-second study with its own resource tracks. `npm run export:html` and `npm run export:mp4` use this installed film normally. To use the recipe inside an existing film, import `studyFrame()` and `StudyRenderer`, then compose the selected scene into the project's timeline instead of running the installer.
+
+## Adaptation decisions
+
+- Keep parts, outlines, construction lines and labels in a semantic model. Draw in meaningful order, then animate separation along defined axes.
+- Dimensions and leader endpoints follow the same world-to-screen transform as the parts. Scale line weights for the framing without losing their hierarchy.
+- Use actual units only when supplied or verified; conceptual dimensions are clearly illustrative. Exploded components need prepared interiors and collision-free destinations.
+
+The study is silent, original procedural art. Photographic studies use illustrated media cards and product studies use an illustrative object; replace these with actual supplied/generated assets for production. It demonstrates material, transforms and layout rather than proving real product claims. Configure an original subject, palette, scene sequence, duration and soundtrack from the brief.
+
+Use `src/studies/timing.ts` for deterministic easing, seeded variation, measured stroke truncation and cue helpers. `window.animaguru.texts` exposes visible study text bounds for `npm run review`; text declarations alone do not count as visual proof. Inspect the actual frames as well.
+
+## Sources and attribution
+
+Inspired by the following pinned references; source-specific 3D/media dependencies are not bundled. New study art and scene geometry are original. The workspace's `VIDEO-STYLE-NOTICES.txt` preserves the repository notices and clarifies third-party asset scope.
+
+- [styles/blueprint/STYLE.md](https://github.com/lemomo-ai/lemo-opuscar/blob/b65efe6ea393fdc71212898ea4c57c754cfefa46/styles/blueprint/STYLE.md)
+- [styles/blueprint/demo/draw.js](https://github.com/lemomo-ai/lemo-opuscar/blob/b65efe6ea393fdc71212898ea4c57c754cfefa46/styles/blueprint/demo/draw.js)