cue-ai 0.9.2 → 0.9.4

package/resources/skills/skills/media/logo-creator/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: muapi-logo-creator
+version: 0.1.0
+description: Engineer professional-grade brand logos using geometric primitives and negative space — generates minimalist, scalable vector-style marks via muapi.ai
+---
+
+# 🖼️ Logo Creator Skill
+
+**A specialized skill for AI Agents to engineer professional-grade brand identities.**
+The Logo Creator skill translates brand vision into minimalist, scalable, and iconic vector-style marks.
+
+## Core Competencies
+
+1. **Geometric Primitive Construction**: Using basic shapes (circles, squares, triangles) to create memorable icons.
+2. **Negative Space Manipulation**: Integrating secondary meanings through the strategic use of empty space.
+3. **Symbolic Abstraction**: Reducing complex brand concepts into their simplest visual essence.
+4. **Scalability Awareness**: Ensuring designs remain legible from 16px (favicon) to billboards.
+
+---
+
+## 🏗️ Technical Specification
+
+### 1. Logo Taxonomy Table
+
+| Logo Type | Style | Best For | Focus |
+| :--- | :--- | :--- | :--- |
+| **Pictorial Mark** | Symbolic | Established Brands | Iconic Recognition |
+| **Abstract Mark** | Geometric | Tech/Modern | Concept/Feeling |
+| **Lettermark/Monogram** | Typographic | Long Names | Initials/Font Style |
+| **Emblem** | Traditional | Institutions/Cafe | Detail/Badge |
+| **Mascot** | Character | Communities/Gaming | Personality |
+
+### 2. Branding Directives
+- `Color Theory`: Use high-impact monochromatic or dual-tone palettes for professional "weight."
+- `Typography`: Pair marks with clean Geometric Sans-Serif (e.g., Gotham, Helvetica style).
+- `Style`: Flat design ONLY. No gradients, 3D effects, or photorealistic textures.
+
+---
+
+## 🧠 Prompt Optimization Protocol (Agent Instruction)
+
+**Before calling the script, the Agent MUST refine the brand vision into a Geometric Minimalist Brief:**
+
+1. **PRIMITIVE FOCUS**: Reduce the concept to basic shapes: *Circle, Square, Triangle*.
+2. **NEGATIVE SPACE**: Explicitly instruct the model to use *negative space* for secondary meaning (e.g., "The space between the letters forms an arrow").
+3. **PRODUCTION CONSTRAINTS**: Use *Solid colors*, *Monochromatic palettes*, and *Flat design only*. NO gradients or 3D effects.
+4. **CENTERED COMPOSITION**: Always specify *Isolated on white background* and *perfectly centered* for scalability.
+
+---
+
+## 🚀 Protocol: Using the Logo Creator
+
+### Step 1: Define the Brand Brief
+Provide the agent with a brand name, core values, and industry.
+
+### Step 2: Invoke the Script
+The `create-logo.sh` script generates a comprehensive branding brief.
+
+```bash
+# Designing a Fintech Logo
+bash scripts/create-logo.sh \
+  --brand "Aura" \
+  --concept "geometric security shield with a spark" \
+  --style minimalist \
+  --color "black and gold"
+```
+
+---
+
+## ⚠️ Constraints & Guardrails
+
+- **Production-Ready**: **MANDATORY** - Solid white/black background only. No textures, no desks, no mockups (t-shirts/business cards).
+- **Legibility**: Avoid thin lines or complex overlapping that disappears at small scales.
+- **Minimalism**: Limit the mark to a maximum of 3 core geometric elements.
+- **No Artifacting**: Use Flux for accurate brand name rendering within the logo.
+
+---
+
+## ⚙️ Implementation Details
+This skill acts as a "Senior Brand Identity" layer over the `core/media/generate-image.sh` primitive. It generates an `EXPERT_LOGO_BRIEF` that enforces geometric symmetry and negative space principles.

package/resources/skills/skills/media/logo-creator/scripts/create-logo.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+# Expert Skill: Logo Creator
+# Translates brand vision into professional vector-style branding.
+
+BRAND=""
+STYLE="minimalist"
+COLOR="black on white"
+CONCEPT=""
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --brand) BRAND="$2"; shift 2 ;;
+        --style) STYLE="$2"; shift 2 ;;
+        --color) COLOR="$2"; shift 2 ;;
+        --concept) CONCEPT="$2"; shift 2 ;;
+        *) shift ;;
+    esac
+done
+
+if [ -z "$CONCEPT" ]; then
+    echo "Usage: bash create-logo.sh --concept 'description' --brand 'name' [--style minimalist|abstract|mascot] [--color 'palette']"
+    exit 1
+fi
+
+# Branding Logic
+EXPERT_PROMPT="[LOGO_BRIEF]
+BRAND_NAME: \"$BRAND\"
+ICON_CONCEPT: $CONCEPT
+DESIGN_PHILOSOPHY: $STYLE, geometric primitives, negative space, flat design
+TECHNICAL: High scalability, solid $COLOR background, symmetric, centered
+TYPOGRAPHY: Geometric sans-serif wordmark
+[EXECUTE] Generate a clean, professional vector logo. NO 3D rendering, NO realistic shading, NO complex gradients. Pure brand identity mark."
+
+# Call Core Primitive
+SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
+CORE_SCRIPT="$SCRIPT_DIR/../../core-media/generate-image.sh"
+
+bash "$CORE_SCRIPT" --prompt "$EXPERT_PROMPT" --model flux-dev --aspect-ratio 1:1 --json

package/resources/skills/skills/media/logo-generator/SKILL.md

@@ -0,0 +1,56 @@
+---
+slug: muapi-logo-generator
+name: muapi-logo-generator
+version: "1.0.0"
+description: Quickly generate a single polished logo for any brand — fast, focused, single output with clean vector aesthetic and accurate brand name text.
+acceptLicenseTerms: true
+---
+
+
+# Logo Generator
+
+**Quickly generate a single polished logo for any brand — fast, focused, single output with clean vector aesthetic and accurate brand name text.**
+
+## Inputs
+
+| Name | Type | Required | Default | Description |
+|:---|:---|:---|:---|:---|
+| `brand_name` | text | yes | — | The brand or company name to put in the logo. |
+| `style` | text | no | modern wordmark with icon, minimal | Logo style (e.g. "monogram initials", "icon + text horizontal", "bold sans-serif wordmark", "badge/emblem", "abstract mark"). |
+| `industry` | text | no | technology | Industry context to guide the icon metaphor (e.g. "food & beverage", "health & wellness", "finance", "creative agency"). |
+| `colors` | text | no | brand blue and white | Color scheme (e.g. "black and gold", "forest green and cream", "electric purple gradient"). |
+| `background` | text | no | white | Background color for logo — "white", "black", or "transparent". |
+
+
+## Steps
+
+Submit the plan with ONE step:
+
+1. **Logo** — `muapi image generate` (model=`ideogram-v3-t2i`):
+   - Prompt: `Professional logo for "{{brand_name}}" — {{style}}, {{industry}} brand. Color scheme: {{colors}}. {{background}} background. Clean, scalable, vector-quality logo design. Legible brand name text, balanced proportions. Modern 2025 logo design, no drop shadows, no gradients unless requested, isolated on {{background}} background.`
+   - Aspect ratio: 1:1
+   - If `{{style}}` mentions "horizontal" or "wide" layout: aspect ratio 2:1
+
+After generation:
+- Present the logo
+- Ask if they want: a dark mode version, an icon-only version, or a full branding package
+- If they want the full package, suggest the `logo-branding` skill
+
+## Notes
+- Ideogram v3 is the best model for accurate text rendering in logos — always use it for logos with text.
+- Always check: is the brand name spelled correctly? If not, retry with the exact spelling bolded in the prompt.
+- For badge/emblem styles, add "circular badge layout, contained design" to the prompt.
+- For abstract marks (no text), switch to `flux-2-pro` for more creative symbol generation.
+
+## Trigger Keywords
+
+`logo generator`, `make a logo`, `create logo`, `design a logo`, `quick logo`, `generate logo`, `logo for my brand`
+
+
+---
+
+## Notes for the Executing Agent
+
+- This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call `muapi` CLI commands. Use `muapi auth configure` first if `MUAPI_API_KEY` is unset.
+- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with `muapi predict wait <request_id>`.
+- Substitute `{{input_name}}` placeholders with the user's actual inputs before issuing each call.

package/resources/skills/skills/media/multi-angle-reshoot/SKILL.md

@@ -0,0 +1,70 @@
+---
+slug: muapi-multi-angle-reshoot
+name: muapi-multi-angle-reshoot
+version: "1.0.0"
+description: Re-render a subject or scene from multiple dramatic camera angles, such as fish-eye, bird's-eye, low-angle, and macro, while maintaining consistent identity and detail.
+acceptLicenseTerms: true
+---
+
+
+# Multi-Angle Reshoot
+
+**Re-render a subject or scene from multiple dramatic camera angles, such as fish-eye, bird's-eye, low-angle, and macro, while maintaining consistent identity and detail.**
+
+## Inputs
+
+| Name | Type | Required | Default | Description |
+|:---|:---|:---|:---|:---|
+| `subject_description` | text | yes | — | Description of the subject or scene (e.g. "a professional woman in a black suit holding a laptop"). |
+| `reference_image` | image_url | no | — | Optional reference image to maintain consistency across angles. |
+
+
+## Steps
+
+### Phase A — Subject Establishment
+
+If `{{reference_image}}` is not provided, submit the plan with ONE step to create the base subject:
+
+1. **Subject Generation** — `muapi image generate` (model=`nano-banana-pro`):
+   - Prompt: `A high-quality, professional photograph of {{subject_description}}. Clean studio lighting, sharp focus, realistic textures, cinematic quality.`
+   - Aspect ratio: 3:4 or 1:1
+
+Present the base image to the user for approval.
+
+### Phase B — Multi-Angle Reshoot
+
+Once the subject is established, submit the plan using `muapi image edit` (model=`nano-banana-2-edit`) to generate the requested angles. Use the approved image from Phase A as the reference for ALL steps.
+
+1. **Bird's Eye View**
+   - Reference: Base Image
+   - Prompt: `A dramatic bird's eye view (from directly above) of the same subject. High-angle perspective, wide shot, looking down. Maintain exact clothing, face, and setting consistency.`
+2. **Fish Eye Lens**
+   - Reference: Base Image
+   - Prompt: `A high-distortion fish-eye lens photograph of the same subject. Ultra-wide angle, curved edges, dramatic perspective, immersive feel. Maintain exact clothing and face consistency.`
+3. **Low Angle (Hero Shot)**
+   - Reference: Base Image
+   - Prompt: `A low-angle "hero shot" looking up at the subject. Makes the subject appear powerful and dominant. Maintain exact clothing and face consistency.`
+4. **Dutch Angle**
+   - Reference: Base Image
+   - Prompt: `A stylized Dutch angle (tilted horizon) photograph of the same subject. Cinematic, slightly uneasy or dramatic vibe. Maintain exact clothing and face consistency.`
+5. **Macro Close-up**
+   - Reference: Base Image
+   - Prompt: `An extreme macro close-up focused on a specific detail of the subject (e.g., eyes, texture of the suit, or a feature of the laptop). Shallow depth of field, incredible detail. Maintain exact colors and textures.`
+6. **Worm's Eye View**
+   - Reference: Base Image
+   - Prompt: `A worm's eye view from ground level looking straight up at the subject. Dramatic vertical perspective. Maintain exact clothing and face consistency.`
+
+After generating the variations, present the multi-angle gallery to the user. You can also offer to generate specific individual angles based on their feedback.
+
+## Trigger Keywords
+
+`multi angle`, `photo reshoot`, `change camera angle`, `fish eye view`, `birds eye view`, `low angle shot`, `macro photography`, `camera perspective`
+
+
+---
+
+## Notes for the Executing Agent
+
+- This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call `muapi` CLI commands. Use `muapi auth configure` first if `MUAPI_API_KEY` is unset.
+- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with `muapi predict wait <request_id>`.
+- Substitute `{{input_name}}` placeholders with the user's actual inputs before issuing each call.

package/resources/skills/skills/media/multi-angle-shots/SKILL.md

@@ -0,0 +1,73 @@
+---
+slug: muapi-multi-angle-shots
+name: muapi-multi-angle-shots
+version: "1.0.0"
+description: Generate a complete set of multi-angle product shots — front, side, back, top-down, and 45-degree perspective — for comprehensive product visualization.
+acceptLicenseTerms: true
+---
+
+
+# Multi-Angle Shots
+
+**Generate a complete set of multi-angle product shots — front, side, back, top-down, and 45-degree perspective — for comprehensive product visualization.**
+
+## Inputs
+
+| Name | Type | Required | Default | Description |
+|:---|:---|:---|:---|:---|
+| `product_name` | text | yes | — | The product to photograph (e.g. "black leather sneaker", "glass perfume bottle", "smartwatch"). |
+| `product_image` | image_url | no | — | Optional reference product image to use as base. |
+| `background_style` | text | no | pure white studio | Background/environment (e.g. "pure white studio", "dark moody grey", "natural marble surface", "lifestyle context"). |
+| `lighting` | text | no | soft studio lighting, product photography | Lighting style (e.g. "dramatic side lighting", "flat lay top-down", "rim lighting", "natural daylight"). |
+| `category` | text | no | general product | Product category to tailor angle logic (e.g. "footwear", "watch/jewelry", "electronics", "beverage bottle", "skincare"). |
+
+
+## Steps
+
+Submit a single the plan with all angles in parallel.
+
+### All Angles (Parallel)
+
+1. **Front view** — `muapi image generate` (model=`ai-product-photography`) if `{{product_image}}` provided, else `muapi image generate` (model=`nano-banana-pro`):
+   - Prompt: `{{product_name}} — perfectly centered FRONT VIEW, eye-level angle. {{background_style}} background. {{lighting}}. Sharp focus, commercial product photography, ultra detailed, no props.`
+   - Aspect ratio: 1:1
+
+2. **Side / 3/4 angle view** — same model as step 1:
+   - Prompt: `{{product_name}} — elegant 3/4 SIDE ANGLE view, slight perspective showing depth and form. {{background_style}} background. {{lighting}}. Shows product silhouette and side detail, commercial photography.`
+   - Aspect ratio: 1:1
+
+3. **Back view** — same model as step 1:
+   - Prompt: `{{product_name}} — BACK VIEW, centered, showing rear details, finishes, and labels if any. {{background_style}} background. {{lighting}}. Product photography, equal detail to front shot.`
+   - Aspect ratio: 1:1
+
+4. **Top-down / flat lay** — `muapi image generate` (model=`ai-product-shot`) if `{{product_image}}` provided, else `muapi image generate` (model=`bytedance-seedream-v4.5`):
+   - Prompt: `{{product_name}} — perfectly overhead TOP-DOWN flat lay view, camera pointing straight down. {{background_style}} surface. Flat lay product photography, even lighting, no shadows at edges, symmetrically placed.`
+   - Aspect ratio: 1:1
+
+5. **Hero glamour shot** — `muapi image generate` (model=`nano-banana-pro`):
+   - Prompt: `{{product_name}} — dynamic low-angle HERO SHOT, slightly below eye level looking up at product. Dramatic {{lighting}}, slight depth of field, editorial product photography. {{background_style}} background. Premium commercial advertising quality.`
+   - Aspect ratio: 4:5
+
+After generation:
+- Present all 5 angles in a grid layout description
+- Suggest adding a 360° spin video with `kling-v3.0-pro-image-to-video`
+- Offer to upscale any angle with `ai-image-upscaler`
+
+## Notes
+- For footwear: emphasize sole view as a 6th angle if requested.
+- For watches/jewelry: suggest a macro detail shot as an additional step.
+- For electronics: add "showing all ports, buttons, and screen" to front and side prompts.
+- `ai-product-photography` is ideal when a reference image is provided — it preserves product identity.
+
+## Trigger Keywords
+
+`multi angle`, `multiple angles`, `360 product`, `product angles`, `all sides`, `front back side`, `product views`, `angle shots`, `product photography set`
+
+
+---
+
+## Notes for the Executing Agent
+
+- This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call `muapi` CLI commands. Use `muapi auth configure` first if `MUAPI_API_KEY` is unset.
+- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with `muapi predict wait <request_id>`.
+- Substitute `{{input_name}}` placeholders with the user's actual inputs before issuing each call.

package/resources/skills/skills/media/music-video/SKILL.md

@@ -0,0 +1,61 @@
+---
+slug: muapi-music-video
+name: muapi-music-video
+version: "1.0.0"
+description: Build a short music video from a song theme — N keyframes, animate each, generate matching music.
+acceptLicenseTerms: true
+---
+
+
+# Music Video
+
+**Build a short music video from a song theme — N keyframes, animate each, generate matching music.**
+
+## Inputs
+
+| Name | Type | Required | Default | Description |
+|:---|:---|:---|:---|:---|
+| `theme` | text | yes | — | Song / video theme (e.g. "lonely robot finds a friend, hopeful"). |
+| `scenes` | int | no | 3 | Number of scenes (each becomes a 5s clip). |
+| `music_style` | text | no | ambient cinematic, instrumental, slow tempo, warm | Suno-style tags for the soundtrack. |
+| `visual_style` | text | no | cinematic, photoreal, soft volumetric light, 16:9 |  |
+
+
+## Steps
+
+Build one the plan covering:
+
+1. **Layer A (parallel)** — N keyframes + 1 music track all at once.
+   - For each scene 1..N: `muapi image generate` with a beat-specific prompt +
+     `{{visual_style}}`, model=nano-banana-pro (these feed video gen).
+   - One `muapi audio create` (kind=music) using `{{music_style}}`, duration =
+     N × 5 + a 2s tail.
+2. **Layer B (parallel, depends on Layer A)** — animate each keyframe.
+   - For each scene: `muapi video from-image` with `image=$nX.url`, model=veo3.1-image-to-video,
+     duration=5, prompt=scene-specific motion direction.
+3. Return:
+   - The scene keyframes (asset ids in order).
+   - The animation clips (asset ids in order).
+   - The music track asset id.
+   - A short summary describing the cut order.
+
+## Notes
+- Keep character continuity by repeating the character description in every
+  scene prompt verbatim.
+- Don't auto-confirm any single video call > 50 cr — those need the user's
+  nod (the loop will prompt automatically).
+- If a scene's `muapi video from-image` fails after failover, fall back to
+  `muapi video generate` (text-to-video) for that scene only.
+
+## Trigger Keywords
+
+`music video`, `mv`, `video story`, `song visualization`
+
+
+---
+
+## Notes for the Executing Agent
+
+- This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call `muapi` CLI commands. Use `muapi auth configure` first if `MUAPI_API_KEY` is unset.
+- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with `muapi predict wait <request_id>`.
+- Substitute `{{input_name}}` placeholders with the user's actual inputs before issuing each call.

package/resources/skills/skills/media/nano-banana/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: muapi-nano-banana
+version: 0.1.0
+description: Reasoning-driven image generation using structured creative briefs (Gemini 3 style) — generates high-fidelity images via muapi.ai with logic-based prompting
+---
+
+# 🍌 Nano-Banana Expert Skill (Gemini 3 Style)
+
+**A specialized skill for AI Agents to leverage "Reasoning-Driven" image generation.**
+Based on the advanced prompting architecture of Google's Gemini 3 (Nano Banana Pro), this skill moves beyond keyword stuffing to structured, logic-based creative briefs.
+
+## Core Competencies
+
+1. **Reasoning-Driven Prompting**: Using natural language logic to define physics, lighting, and spatial relationships.
+2. **Structured Creative Briefs**: Implementing the "Perfect Prompt" formula: `Subject + Action + Context + Composition + Lighting`.
+3. **Text Rendering Precision**: Explicitly defining typography and signifiers for legible text integration.
+4. **Contextual Grounding**: Using "Search Grounding" logic (simulated) to anchor generations in real-world accuracy.
+
+---
+
+## 🏗️ Technical Specification
+
+### 1. The "Perfect Prompt" Formula
+
+| Component | Description | Example |
+| :--- | :--- | :--- |
+| **Subject** | Detailed entity description | "A stoic robot barista with exposed copper wiring" |
+| **Action** | Dynamic interaction | "Pouring a latte art leaf with mechanical precision" |
+| **Context** | Environment & Atmosphere | "Inside a neon-lit cyberpunk cafe at midnight" |
+| **Composition** | Camera & Lens choice | "Close-up, 85mm lens, f/1.8 aperture" |
+| **Lighting** | Mood & Direction | "Volumetric blue rim light, warm cafe glow" |
+| **Style** | Aesthetic anchor | "Cinematic, photorealistic, 4K production value" |
+
+### 2. Advanced Features
+- **Negative Constraint Logic**: Instead of "no blurry," use "Ensure sharp focus on the subject's eyes."
+- **Identity Consistency**: (Simulated) "Maintain consistent facial structure across variations."
+- **Text Integration**: Use double quotes for specific text: `The sign reads "OPEN 24/7"`.
+
+---
+
+## 🧠 Prompt Optimization Protocol (Agent Instruction)
+
+**Before calling the script, the Agent MUST rewrite the user's prompt into a logic-driven Reasoning Brief:**
+
+1. **NO KEYWORD SOUP**: Remove "8k, masterpiece, ultra-detailed." Use full, descriptive sentences.
+2. **PHYSICAL CONSISTENCY**: Describe how elements interact (e.g., "The light from the crystal shards casts caustic patterns across the obsidian floor").
+3. **TEXT PRECISION**: If the user wants text, define it precisely: `featuring a sign that says "STORE NAME" in a weathered serif font`.
+4. **OPTICAL DIRECTIVES**: Specify lens behavior: *Shallow Depth of Field (f/1.8)*, *Macro Lens*, *Anamorphic Flare*.
+
+---
+
+## 🚀 Protocol: Using Nano-Banana
+
+### Step 1: Define the Creative Logic
+Provide the agent with a subject and a specific scenario.
+
+### Step 2: Invoke the Script
+The `generate-nano-art.sh` script translates the logic into a structured Gemini 3-style prompt.
+
+```bash
+# Generating a reasoning-driven image
+bash scripts/generate-nano-art.sh \
+  --subject "a glass chess piece" \
+  --action "shattering into liquid shards" \
+  --context "on a obsidian table" \
+  --style "macro photography"
+```
+
+---
+
+## ⚠️ Constraints & Guardrails
+
+- **No Keyword Soup**: **MANDATORY** - Do not use "trending on artstation, masterpiece, 8k". Use natural language descriptions.
+- **Physics Logic**: Ensure the prompt describes *physically possible* lighting and reflection interactions.
+- **Full Sentences**: The model parses relationships; use "light reflecting off the water" instead of "water, reflection".
+
+---
+
+## ⚙️ Implementation Details
+This skill applies a "Logic Wrapper" around the `core/media/generate-image.sh` primitive, converting fragmented inputs into a coherent, reasoning-ready narrative prompt.

package/resources/skills/skills/media/nano-banana/scripts/generate-nano-art.sh

@@ -0,0 +1,54 @@
+#!/bin/bash
+# Expert Skill: Nano-Banana (Gemini 3 Style)
+# Implements the "Perfect Prompt" reasoning-driven formula.
+
+SUBJECT=""
+ACTION=""
+CONTEXT=""
+STYLE="cinematic"
+LIGHTING="natural"
+RESOLUTION="1k"
+TEXT=""
+VIEW_FLAG=""
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --subject) SUBJECT="$2"; shift 2 ;;
+        --action) ACTION="$2"; shift 2 ;;
+        --context) CONTEXT="$2"; shift 2 ;;
+        --style) STYLE="$2"; shift 2 ;;
+        --lighting) LIGHTING="$2"; shift 2 ;;
+        --resolution) RESOLUTION="$2"; shift 2 ;;
+        --text) TEXT="$2"; shift 2 ;;
+        --view) VIEW_FLAG="--view"; shift ;;
+        *) shift ;;
+    esac
+done
+
+if [ -z "$SUBJECT" ]; then
+    echo "Usage: bash generate-nano-art.sh --subject 'robot' [--action 'pouring coffee'] [--context 'cafe'] [--style 'photorealistic'] [--resolution 1k|2k|4k] [--text 'CAFE'] [--view]"
+    exit 1
+fi
+
+# Text Logic
+TEXT_PROMPT=""
+if [ -n "$TEXT" ]; then
+    TEXT_PROMPT="featuring a sign that clearly reads \"$TEXT\" in bold typography"
+fi
+
+# Nano-Banana Reasoning-Driven Prompt
+# Formula: Subject + Action + Context + Lighting + Style + Text
+EXPERT_PROMPT="[REASONING_BRIEF]
+SUBJECT: A highly detailed $SUBJECT.
+ACTION: The subject is $ACTION.
+ENVIRONMENT: Situated in $CONTEXT.
+LIGHTING: Illuminated by $LIGHTING lighting.
+STYLE: Use a $STYLE aesthetic. High fidelity, physically accurate reflections and textures.
+EXTRA: $TEXT_PROMPT.
+[EXECUTE] Generate a photorealistic image based on this logic. Ensure precise composition and lighting interactions."
+
+# Call Core Primitive
+SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
+CORE_SCRIPT="$SCRIPT_DIR/../../core-media/generate-image.sh"
+
+bash "$CORE_SCRIPT" --prompt "$EXPERT_PROMPT" --model "nano-banana-pro" --resolution "$RESOLUTION" $VIEW_FLAG --json

package/resources/skills/skills/media/one-shot-video/SKILL.md

@@ -0,0 +1,56 @@
+---
+slug: muapi-one-shot-video
+name: muapi-one-shot-video
+version: "1.0.0"
+description: Generate a single continuous cinematic shot video — no cuts, one seamless flowing scene with dramatic lighting and motion.
+acceptLicenseTerms: true
+---
+
+
+# One-Shot Video
+
+**Generate a single continuous cinematic shot video — no cuts, one seamless flowing scene with dramatic lighting and motion.**
+
+## Inputs
+
+| Name | Type | Required | Default | Description |
+|:---|:---|:---|:---|:---|
+| `scene` | text | yes | — | The scene to render (e.g. "a chef plating food in a moody Michelin-star kitchen"). |
+| `style` | text | no | cinematic, anamorphic lens, shallow depth of field, dramatic lighting | Visual tone and style (e.g. "noir, handheld, golden hour"). |
+| `duration` | text | no | 10s | Target duration (e.g. "5s", "10s"). |
+| `aspect_ratio` | text | no | 16:9 | Output aspect ratio — "16:9", "9:16", or "1:1". |
+| `reference_image` | image_url | no | — | Optional reference image for subject/scene anchoring. |
+
+
+## Steps
+
+### Phase A — Generate the One-Shot Video
+
+Submit the plan with ONE step:
+
+1. **One-shot video** — If `{{reference_image}}` is provided, use `muapi video generate` (model=`veo3.1-image-to-video`); otherwise use `muapi video generate` (model=`veo3.1-text-to-video`).
+   - Prompt: `{{scene}}, one continuous uncut shot, no transitions, camera slowly moves through scene, {{style}}, ultra cinematic, film grain, 4K quality`
+   - Aspect ratio: `{{aspect_ratio}}`
+   - Duration: `{{duration}}`
+
+After generation, present the video and suggest:
+- A second angle variation
+- Adding ambient sound with `mmaudio-v2-video-to-video`
+
+## Notes
+- Emphasize "no cuts, no transitions" in the prompt for true one-shot feel.
+- For portrait/vertical style (9:16), add "vertical format, smartphone framing" to the prompt.
+- If the scene involves a person, suggest `kling-v3.0-pro-image-to-video` as an alternative for better human motion.
+
+## Trigger Keywords
+
+`one shot video`, `single take`, `continuous video`, `one take`, `cinematic shot`, `seamless video`
+
+
+---
+
+## Notes for the Executing Agent
+
+- This recipe is LLM-orchestrated: read each phase, gather any missing inputs from the user, then call `muapi` CLI commands. Use `muapi auth configure` first if `MUAPI_API_KEY` is unset.
+- For model IDs without a CLI alias yet, fall back to the raw endpoint via `curl -X POST https://api.muapi.ai/api/v1/<endpoint> -H "x-api-key: $MUAPI_API_KEY" -H 'content-type: application/json' -d '{...}'` and poll with `muapi predict wait <request_id>`.
+- Substitute `{{input_name}}` placeholders with the user's actual inputs before issuing each call.