cue-ai 0.9.2 → 0.9.3

package/resources/skills/skills/media/brand-kit/SKILL.md

@@ -0,0 +1,72 @@
+---
+slug: muapi-brand-kit
+name: muapi-brand-kit
+version: "1.0.0"
+description: Generate a cohesive brand visual kit — logo concept, color palette moodboard, and typography pairing suggestions.
+acceptLicenseTerms: true
+---
+
+
+# Brand Kit
+
+**Generate a cohesive brand visual kit — logo concept, color palette moodboard, and typography pairing suggestions.**
+
+## Inputs
+
+| Name | Type | Required | Default | Description |
+|:---|:---|:---|:---|:---|
+| `brand_name` | text | yes | — | Name of the brand. |
+| `industry` | text | yes | — | Industry or niche (e.g. "sustainable fashion", "fintech startup", "artisan bakery"). |
+| `personality` | text | no | modern, trustworthy, approachable | 3–5 brand personality adjectives (e.g. "bold, edgy, youthful" or "elegant, minimal, luxury"). |
+| `color_preference` | text | no | — | Optional color direction (e.g. "earthy greens and terracotta", "monochrome with gold accents"). |
+
+
+## Steps
+
+Generate a multi-asset brand exploration in one parallel plan.
+
+### Phase A — Visual exploration (parallel)
+
+Submit ONE the plan with:
+
+1. **Logo concept A** — `muapi image generate` (model=gpt-image-2-text-to-image, aspect_ratio=1:1):
+   - Style: minimalist wordmark or lettermark on white background, flat design.
+   - Prompt: "Minimalist logo for '{{brand_name}}', {{industry}} brand, {{personality}} personality. Clean vector-style, white background, professional. {{color_preference}}".
+
+2. **Logo concept B** — `muapi image generate` (model=nano-banana-2, aspect_ratio=1:1):
+   - Style: icon + wordmark combination.
+   - Prompt: "Modern logo mark + wordmark for '{{brand_name}}', {{industry}}, {{personality}}. Bold, distinctive, scalable icon design, white background. {{color_preference}}".
+
+3. **Moodboard / Color palette** — `muapi image generate` (model=nano-banana-pro, aspect_ratio=16:9):
+   - A flat design moodboard showing: 5 brand colors (as swatches with hex-like labels), lifestyle photography inspo tiles, texture samples.
+   - Prompt: "Brand moodboard for a {{personality}} {{industry}} brand called '{{brand_name}}'. Show 5 color palette swatches, 4 lifestyle photo tiles, typography samples. Flat lay design, white background. {{color_preference}}".
+
+4. **Pattern / texture asset** — `muapi image generate` (model=nano-banana-2, aspect_ratio=1:1):
+   - A seamless brand pattern or texture for use in backgrounds, packaging, stationery.
+   - Prompt: "Seamless brand pattern for {{brand_name}}, {{industry}}, {{personality}} aesthetic. Subtle, tileable, modern. {{color_preference}}".
+
+### Phase B — Deliverables summary
+
+After the plan completes, return:
+- Asset references (logo A, logo B, moodboard, pattern).
+- **Color palette recommendation**: 5 hex codes with roles (Primary, Secondary, Accent, Neutral Light, Neutral Dark).
+- **Typography pairing**: 2 Google Font pairings appropriate for the brand personality.
+- **Usage guidance**: when to use each logo variant, color do/don'ts.
+
+## Notes
+- If the user has reference images in the session, analyze their style before generating.
+- Suggest logo A for digital-first brands, logo B for physical/retail brands.
+- All four assets run in parallel for speed.
+
+## Trigger Keywords
+
+`brand kit`, `brand identity`, `logo`, `branding`, `brand design`, `visual identity`
+
+
+---
+
+## 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/brochures/SKILL.md

@@ -0,0 +1,65 @@
+---
+slug: muapi-brochures
+name: muapi-brochures
+version: "1.0.0"
+description: Generate a professional multi-page brochure design — cover, inner spread, and back cover — for business, real estate, events, or product launches.
+acceptLicenseTerms: true
+---
+
+
+# Brochure Designer
+
+**Generate a professional multi-page brochure design — cover, inner spread, and back cover — for business, real estate, events, or product launches.**
+
+## Inputs
+
+| Name | Type | Required | Default | Description |
+|:---|:---|:---|:---|:---|
+| `brand_name` | text | yes | — | The company or brand name featured in the brochure. |
+| `topic` | text | yes | — | What the brochure is about (e.g. "luxury apartments in Dubai", "annual company report 2024", "new product catalog", "health clinic services"). |
+| `style` | text | no | modern, professional, premium | Brochure visual style (e.g. "minimalist luxury", "bold colorful", "corporate formal", "creative editorial"). |
+| `color_scheme` | text | no | navy blue and gold | Primary color palette (e.g. "forest green and cream", "black and white with red accents"). |
+| `format` | text | no | tri-fold | Brochure format — "tri-fold", "bi-fold", "single page", "A4 portrait". |
+| `brand_logo` | image_url | no | — | Optional brand logo to include in the design. |
+
+
+## Steps
+
+Submit the plan with THREE parallel steps (front, inside, back).
+
+### All Pages in Parallel
+
+1. **Front cover** — If `{{brand_logo}}` provided, use `muapi image edit` (model=`gpt4o-edit`); else `muapi image generate` (model=`gpt4o-text-to-image`):
+   - Prompt: `Professional {{format}} brochure FRONT COVER for {{brand_name}} — {{topic}}. {{style}} design, {{color_scheme}} color scheme. Bold headline area, hero image, brand name prominently displayed, luxury print-quality design. A4 portrait format, high resolution, commercial print ready. Clean professional layout.`
+   - Aspect ratio: 2:3 (portrait A4)
+
+2. **Inner spread / main content** — `muapi image generate` (model=`bytedance-seedream-v4.5`):
+   - Prompt: `Professional {{format}} brochure INNER SPREAD for {{brand_name}} — {{topic}}. {{style}} interior layout with: headline section, 3 columns of body text placeholder, feature icons/images, pull quote, infographic element. {{color_scheme}} accents. Balanced grid layout, professional typography hierarchy. Print-ready design.`
+   - Aspect ratio: For tri-fold: 3:2 (landscape showing all 3 panels). For A4/bi-fold: 2:1 (landscape double spread).
+
+3. **Back cover** — `muapi image generate` (model=`bytedance-seedream-v4.5`):
+   - Prompt: `Professional {{format}} brochure BACK COVER for {{brand_name}}. {{style}}, {{color_scheme}}. Includes: contact information section, QR code placeholder, address/website/social media icons area, subtle brand pattern or texture. Clean, minimal back cover design. A4 portrait format.`
+   - Aspect ratio: 2:3
+
+After generation:
+- Present all three panels in order: Cover → Inner → Back
+- Offer to adjust color, layout, or add specific content to any panel
+- Suggest exporting as a canvas composition with all pages arranged
+
+## Notes
+- Always use placeholder text blocks ("Lorem ipsum") rather than generating false content.
+- For real estate brochures, add property photography prompts as a 4th step.
+- For event brochures, emphasize date/venue hierarchy in the front cover prompt.
+
+## Trigger Keywords
+
+`brochure`, `flyer`, `leaflet`, `pamphlet`, `bi-fold`, `tri-fold`, `company brochure`, `marketing brochure`, `product brochure`
+
+
+---
+
+## 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/cartoon-dance-animation/SKILL.md

@@ -0,0 +1,62 @@
+---
+slug: muapi-cartoon-dance-animation
+name: muapi-cartoon-dance-animation
+version: "1.0.0"
+description: Convert a photo of a person into a Pixar-style 3D cartoon character, then animate it using a reference dance or motion video.
+acceptLicenseTerms: true
+---
+
+
+# Cartoon Dance Animation
+
+**Convert a photo of a person into a Pixar-style 3D cartoon character, then animate it using a reference dance or motion video.**
+
+## Inputs
+
+| Name | Type | Required | Default | Description |
+|:---|:---|:---|:---|:---|
+| `user_image` | image_url | yes | — | A clear full-body or medium-shot photo of the person to be cartoonified. |
+| `reference_video` | video_url | no | — | A video containing the specific dance or motion to apply to the character. |
+
+
+## Steps
+
+### Phase A — Cartoon Character Generation
+
+If `{{user_image}}` is not provided, ask the user to upload their photo.
+
+Once the photo is available, submit the plan with ONE step to cartoonify the image:
+
+1. **Image Generation** — `muapi image edit` (model=`nano-banana-2-edit`):
+   - Reference Image: `{{user_image}}`
+   - Prompt: `Use the uploaded input photo as the exact same person in the final render. Preserve identity accurately: same face shape, eyes, nose, lips, jawline, skin tone, hairstyle, hairline, expression, age, and overall vibe. Do NOT change the person into a different face. Keep it clearly recognizable as the same person. Create one full-size ultra-high-quality 3D stylized character illustration, Pixar-inspired but original, based on the input person. Smooth plastic-like skin, soft rounded facial features, big expressive eyes, small nose, subtle blush (very minimal), cozy wholesome aesthetic. High-end character sculpting with stylized proportions while maintaining the real person’s likeness. 👕 Outfit / Costume (MUST MATCH INPUT) Keep the costume/outfit EXACTLY the same as the input image. Do not change colors, fabric type, accessories, layers, patterns, logos, or fit. No added glasses, no headphones, no new jacket, no new styling. 💇 Hair (Exact Match) Hair must remain the same as the input image: same hairstyle, same length, same hairline, only converted into clean stylized 3D hair shapes. 🎨 Render Quality Premium character sculpting, soft studio lighting, global illumination, subsurface scattering, soft shadows, cinematic depth of field, crisp edges. Octane/Arnold render look, ultra-clean, high-quality shading, 8K detail. 🎯 Composition Single full-size image (NOT a grid). Full-body or medium shot matching the input pose and vibe. Minimal clean studio background (solid color), no clutter.`
+   - Negative Prompt: `No outfit change, no costume change, no new clothes, no extra accessories, no glasses, no headphones, no makeup, no cosmetics, no lipstick, no eyeliner, no facial redesign, no different face, no extra limbs, no deformed hands, no scary look, no photoreal skin pores, no wrinkles, no blur, no noise, no watermark, no logo, no text.`
+   - Aspect ratio: Maintain the aspect ratio of the input image or default to 9:16.
+
+Present the generated cartoon character to the user for approval.
+
+### Phase B — Motion Control Animation
+
+After the character is approved, ask the user to upload a `reference_video` (if not already provided) containing the dance or movement they want the character to perform.
+
+Once the video is provided, submit the plan with ONE step:
+
+1. **Motion Control Video Generation** — `muapi video from-image` or `edit_video` (model=`kling-v2.6-std-motion-control`):
+   - Reference Image: The cartoon image generated in Phase A.
+   - Reference Video: `{{reference_video}}`
+   - Prompt: `Smooth, fluid 3D character animation. The 3D character perfectly replicates the movements and dance from the reference video. High frame rate, dynamic motion, consistent character details, Pixar animation quality.`
+
+After generation, present the final animated dance video to the user.
+
+## Trigger Keywords
+
+`cartoon dance`, `3d animation`, `pixar character`, `animate my photo`, `motion control video`, `dance video`, `cartoonify and animate`
+
+
+---
+
+## 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/character-story-video/SKILL.md

@@ -0,0 +1,84 @@
+---
+slug: muapi-character-story-video
+name: muapi-character-story-video
+version: "1.0.0"
+description: Create a multi-part animated story video by first establishing a consistent character and then generating sequential scenes and animating them.
+acceptLicenseTerms: true
+---
+
+
+# Character Story Video
+
+**Create a multi-part animated story video by first establishing a consistent character and then generating sequential scenes and animating them.**
+
+## Inputs
+
+| Name | Type | Required | Default | Description |
+|:---|:---|:---|:---|:---|
+| `character_description` | text | yes | — | Description of the main character (e.g. "a cute piglet wearing a leather aviator jacket and goggles"). |
+| `story_premise` | text | yes | — | The overall story arc (e.g. "building a jetpack and flying to space"). |
+| `reference_image` | image_url | no | — | Optional starting image of the character to maintain consistency. |
+
+
+## Steps
+
+This skill involves multiple phases to build a cohesive narrative.
+
+### Phase A — Character Establishment
+
+If `{{reference_image}}` is NOT provided, submit the plan with ONE step to create the character:
+1. **Character Creation** — `muapi image generate` (model=`nano-banana-pro`):
+   - Prompt: `{{character_description}}, introducing the main character, cinematic lighting, highly detailed, Pixar 3D animation style.`
+   - Aspect ratio: 4:5 or 1:1
+
+If `{{reference_image}}` IS provided, use it as the established character and proceed to Phase B.
+
+After generation, ask the user to confirm the character design before proceeding.
+
+### Phase B — Sequential Scene Generation
+
+Once the character is established, create the story beats (e.g., Scene 1, Scene 2, Scene 3).
+Submit the plan using `muapi image edit` (model=`nano-banana-2-edit` or `flux-kontext-pro-i2i`) to maintain character consistency. Use the established character image as the reference for ALL these steps.
+
+1. **Scene 1 (Beginning)**
+   - Reference: Character Image
+   - Prompt: `The character ({{character_description}}) in the first scene of the story: [Describe the beginning of {{story_premise}}]. Cinematic lighting, Pixar 3D animation style, storybook illustration.`
+2. **Scene 2 (Middle)**
+   - Reference: Character Image
+   - Prompt: `The character ({{character_description}}) in the second scene: [Describe the climax or middle action of {{story_premise}}]. Cinematic lighting, Pixar 3D animation style, storybook illustration.`
+3. **Scene 3 (End)**
+   - Reference: Character Image
+   - Prompt: `The character ({{character_description}}) in the final scene: [Describe the resolution of {{story_premise}}]. Cinematic lighting, Pixar 3D animation style, storybook illustration.`
+
+*Note: All scenes should be generated in parallel or sequentially depending on the story flow.*
+
+After generating the scenes, present them to the user and ask if they are ready to animate the story.
+
+### Phase C — Animation (Sequel Part 1, Part 2, Part 3)
+
+Submit the plan to animate the generated scenes using an image-to-video model (e.g., `kling-v3.0-pro-image-to-video` or `veo3.1-image-to-video`).
+
+1. **Part 1 Video**
+   - Input: Scene 1 Image
+   - Prompt: `Cinematic animation of the scene, character comes to life, subtle natural movements, high quality 3D animation.`
+2. **Part 2 Video**
+   - Input: Scene 2 Image
+   - Prompt: `Cinematic animation of the scene, character comes to life, dynamic action, high quality 3D animation.`
+3. **Part 3 Video**
+   - Input: Scene 3 Image
+   - Prompt: `Cinematic animation of the scene, character comes to life, triumphant resolution, high quality 3D animation.`
+
+After generating the videos, present them to the user as a multi-part story sequence. You may also suggest using the `muapi predict result` + ffmpeg concat tool to merge them into a single movie if requested.
+
+## Trigger Keywords
+
+`character story`, `story video`, `animated story`, `sequel video`, `multi part video`, `sequential story`
+
+
+---
+
+## 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/chibi-collage-effect/SKILL.md

@@ -0,0 +1,63 @@
+---
+slug: muapi-chibi-collage-effect
+name: muapi-chibi-collage-effect
+version: "1.0.0"
+description: Turn a real lifestyle photo into a polished "chibi clone sticker diary" image — the original person stays photorealistic, surrounded by 5–8 kawaii chibi mini-clones, scrapbook doodles, and handwritten-style captions that match the scene.
+acceptLicenseTerms: true
+---
+
+
+# Chibi Collage Effect
+
+**Turn a real lifestyle photo into a polished "chibi clone sticker diary" image — the original person stays photorealistic, surrounded by 5–8 kawaii chibi mini-clones, scrapbook doodles, and handwritten-style captions that match the scene.**
+
+## Inputs
+
+| Name | Type | Required | Default | Description |
+|:---|:---|:---|:---|:---|
+| `person_image` | image_url | yes | — | A clear lifestyle photo of the person. Setting, outfit, mood, and activity are read from this image and drive the chibi poses and captions. |
+
+
+## Steps
+
+### Phase A — Chibi Collage Generation
+
+If `{{person_image}}` is not provided, ask the user to upload a lifestyle photo (café, outdoor, cozy at home, travel, etc.). The scene context is what makes the chibi clones feel native to the moment, so a generic studio headshot will give weaker results than a real lifestyle shot.
+
+Once the photo is available, submit the plan with ONE step to generate the chibi collage:
+
+1. **Chibi Collage Generation** — `muapi image edit` (model=`gpt-image-2-image-to-image`):
+   - Reference Image: `{{person_image}}`
+   - Image size: `2160x3840` (9:16 portrait) — high-resolution social-media-ready output
+   - Background: `auto`
+   - Output format: `png`
+   - Quality: `auto`
+   - Moderation: `low`
+   - Prompt:
+     ```
+     Create a high-quality "chibi clone sticker diary photo" based on the uploaded real-life image. Preserve the original person's identity, face, hairstyle, hair color, outfit, body proportions, pose, lighting, and background. Do not alter facial features or turn the subject into a full illustration—maintain a realistic photo look.
+     Analyze the uploaded image carefully: identify the setting, mood, activity, clothing style, and overall vibe of the scene. Use this analysis to determine the theme of the chibi stickers, poses, emotions, and text phrases — everything should feel native to the actual moment captured in the photo.
+     Add 5–8 chibi mini clones of the same person around the subject, designed in a consistent kawaii sticker style (big head, small body, large expressive eyes, clean digital finish). Each clone must clearly resemble the real person (same hair, outfit, colors).
+     Design each chibi with different actions and emotions that are directly relevant to what the person is doing or feeling in the photo — inferred naturally from the scene (e.g. if they're at a café: sipping coffee, reading, daydreaming, chatting; if outdoors: exploring, laughing, taking photos; if cozy at home: cuddling, reading, relaxing). Ensure all poses are unique and contextually matched to the image.
+     Render each chibi as a sticker with white outlines, soft shadows, and a slightly floating effect. Arrange them around the subject and edges without covering the face or main body.
+     Add light hand-drawn doodles (hearts, sparkles, arrows, motion lines, circles, stars) in white with subtle pink accents, keeping a clean scrapbook diary feel. Doodle style should complement the mood of the scene.
+     Include 5–8 short handwritten-style phrases that match the mood and context of the uploaded photo — cute, expressive, and scene-appropriate. Use mostly white text with slight pink highlights and small decorative marks.
+     Composition: keep the real person as the central focus, surrounded by chibi stickers and doodles. The result should feel like a polished, playful, high-resolution social media lifestyle diary image — clean, balanced, and visually rich without clutter.
+     ```
+
+Present the generated chibi collage to the user. Suggest variations they can try: different source photos (travel, café, cozy-at-home), or asking to bias the captions toward a specific tone (cute, sassy, journal-style).
+
+## Trigger Keywords
+
+`chibi collage`, `chibi sticker diary`, `mini me stickers`, `kawaii clone collage`, `sticker diary photo`, `scrapbook chibi`
+
+
+---
+
+## 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.
+- Source schema reference: `gpt-image-v2-edit` maps to `gpt-image-2-image-to-image` in the muapi catalog.
+- The output is intentionally 9:16 (2160×3840) so it's ready for IG Stories / Reels / TikTok / YT Shorts without re-cropping.

package/resources/skills/skills/media/cinema-director/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: muapi-cinema-director
+version: 0.1.0
+description: Direct high-fidelity cinematic video with AI — translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai
+---
+
+# 🎬 AI Cinema Director Skill
+
+**A specialized skill for AI Agents to direct high-fidelity cinematic video.**
+The Cinema Director skill translates high-level creative intent into technical cinematographic directives for state-of-the-art video models (Veo3, Kling, Luma).
+
+## Core Competencies
+
+1. **Shot Composition Analysis**: Mapping emotional beats to appropriate framing (e.g., Extreme Close-Up for intimacy, Wide Shot for isolation).
+2. **Camera Movement Orchestration**: Directing complex physical movements (Dolly, Truck, Crane) and lens-based effects (Rack Focus, Dolly Zoom).
+3. **Lighting & Atmosphere Design**: Specifying temporal and stylistic lighting (Golden Hour, Chiaroscuro, Volumetric God Rays).
+4. **Technical Parameter Optimization**: Automatically selecting optimal frame rates, aspect ratios, and model-specific biases.
+
+---
+
+## 🏗️ Technical Specification
+
+### 1. Intent Mapping Table
+
+| Creative Intent | Framing | Movement | Lighting |
+| :--- | :--- | :--- | :--- |
+| **Heroic Reveal** | Low Angle / Wide | Crane Up / Orbit | Rim Lighting / High Contrast |
+| **Tense/Uneasy** | Dutch Angle | Handheld Shake | Low Key / Harsh Shadows |
+| **Introspective** | Close-Up | Slow Push In | Soft Rembrandt / Window Light |
+| **Majestic/Epic** | Extreme Wide | Drone Flyover | Golden Hour / Volumetric |
+| **Melancholic** | Profile / Medium | Slow Pull Out | Blue Hour / Desaturated |
+
+### 2. Physical Camera Movements
+- `Dolly In/Out`: Physical camera movement on a track toward/away from the subject.
+- `Truck Left/Right`: Lateral physical movement.
+- `Crane/Jib`: Sweeping vertical movement from a height.
+- `Orbit`: Circular movement around a center point.
+- `Pedestal`: Vertical elevation change (without tilting).
+
+### 3. Lens & Optical Controls
+- `Shallow DOF`: Background blur (Bokeh).
+- `Anamorphic`: Horizontal flares and wide-screen cinematic feel.
+- `Rack Focus`: Shifting focus between planes within the shot.
+
+---
+
+## 🧠 Prompt Optimization Protocol (Agent Instruction)
+
+**Before calling the script, the Agent MUST expand the user's raw prompt using these Director's Rules:**
+
+1. **TECHNICAL INFUSION**: Transform "cool action" into a technical shot. 
+   - *Formula*: `[Shot Type] + [Subject/Action] + [Environment] + [Lighting] + [Camera Movement] + [Lens Effect]`
+2. **MOTION DYNAMICS**: Use cinematic verbs: *Dolly In* (intimacy), *Crane Up* (majestic), *Orbit* (heroic), *Truck* (parallel motion).
+3. **LIGHTING RECIPES**: Apply specific illumination: *Volumetric God Rays*, *Teal-and-Orange Grade*, *Cyberpunk Rim Lighting*, *Rembrandt Portrait Lighting*.
+4. **PHYSICS LOGIC**: Describe light relationships (e.g., "Neon reflections shimmering on rain-slicked asphalt") to trigger model reasoning.
+
+---
+
+## 🚀 Protocol: Using the Cinema Director
+
+### Step 1: Define the Creative Brief
+Provide the agent with a subject and a "Director's Intent."
+
+### Step 2: Invoke the Script
+The `generate-film.sh` script accepts a `--brief` which it expands using its internal knowledge of cinematography.
+
+```bash
+# Directing a scene
+bash scripts/generate-film.sh 
+  --subject "A lone samurai in a blizzard" 
+  --intent "epic reveal" 
+  --model "kling-master"
+```
+
+### Step 3: Handle the Async Response
+Video generation is asynchronous. Use the returned `request_id` to poll for completion via `core/platform/check-result.sh`.
+
+---
+
+## ⚠️ Constraints & Guardrails
+
+- **Temporal Consistency**: Avoid complex subject transformations in a single shot (e.g., "man turns into a bird").
+- **Movement Collisions**: Do not combine contradictory movements (e.g., "Dolly In" and "Dolly Out" simultaneously).
+- **Physical Realism**: Prefer movements possible with real-world equipment for a more professional "film" look.
+- **Model Bias**: 
+  - `Veo3`: Best for slow, high-quality aesthetic shots.
+  - `Kling`: Best for complex character motion and physics.
+  - `Luma`: Best for fast-paced, high-action cinematic sequences.
+
+---
+
+## ⚙️ Implementation Details
+This skill acts as an "Expert Translator" for the `core/media/generate-video.sh` primitive. It maintains a dictionary of cinematic styles and injects technical directives into the prompt before execution.

package/resources/skills/skills/media/cinema-director/scripts/generate-film.sh

@@ -0,0 +1,78 @@
+#!/bin/bash
+# Expert Skill: AI Cinema Director
+# Translates high-level intent into technical cinematographic directives.
+
+SUBJECT=""
+INTENT="cinematic"
+MODEL="veo3"
+ASPECT="16:9"
+DURATION=5
+AUDIO_FLAG=""
+VIEW_FLAG=""
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --subject) SUBJECT="$2"; shift 2 ;;
+        --intent) INTENT="$2"; shift 2 ;;
+        --model) MODEL="$2"; shift 2 ;;
+        --aspect) ASPECT="$2"; shift 2 ;;
+        --duration) DURATION="$2"; shift 2 ;;
+        --no-audio) AUDIO_FLAG="--no-audio"; shift ;;
+        --view) VIEW_FLAG="--view"; shift ;;
+        *) shift ;;
+    esac
+done
+
+if [ -z "$SUBJECT" ]; then
+    echo "Usage: bash generate-film.sh --subject 'description' [--intent reveal|tense|epic] [--model veo3|kling] [--duration 5|10] [--no-audio] [--view]"
+    exit 1
+fi
+
+# Director's Logic Table (Internal Knowledge)
+case $INTENT in
+    "reveal")
+        FRAMING="Extreme wide shot"
+        MOVEMENT="Slow crane up and tilt down"
+        LIGHTING="Golden hour, volumetric god rays"
+        LENS="Deep focus, high clarity"
+        ;;
+    "tense")
+        FRAMING="Dutch angle, close-up"
+        MOVEMENT="Handheld jittery movement"
+        LIGHTING="Low key, harsh shadows, flickering neon"
+        LENS="Shallow depth of field, anamorphic lens flare"
+        ;;
+    "epic")
+        FRAMING="Low angle wide shot"
+        MOVEMENT="Dolly in with circular orbit"
+        LIGHTING="Dramatic rim lighting, high contrast"
+        LENS="Anamorphic, 35mm film grain"
+        ;;
+    "melancholy")
+        FRAMING="Medium shot, profile"
+        MOVEMENT="Slow dolly out"
+        LIGHTING="Blue hour, soft desaturated tones"
+        LENS="Shallow bokeh, soft focus"
+        ;;
+    *)
+        FRAMING="Cinematic medium shot"
+        MOVEMENT="Smooth pan"
+        LIGHTING="Natural studio lighting"
+        LENS="Standard 50mm"
+        ;;
+esac
+
+# Construct the technical Director's Prompt
+DIRECTOR_PROMPT="[DIRECTOR_BRIEF]
+SCENE: $SUBJECT
+FRAMING: $FRAMING
+CAMERA_MOTION: $MOVEMENT
+LIGHTING_DESIGN: $LIGHTING
+OPTICS: $LENS
+[EXECUTE] High-fidelity cinematic footage. Professional color grade, 4k, hyper-realistic physics."
+
+# Call the Core primitive
+SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
+CORE_SCRIPT="$SCRIPT_DIR/../../core-media/generate-video.sh"
+
+bash "$CORE_SCRIPT" --prompt "$DIRECTOR_PROMPT" --model "$MODEL" --aspect-ratio "$ASPECT" --duration "$DURATION" $AUDIO_FLAG $VIEW_FLAG --async --json

package/resources/skills/skills/media/color-analysis-board/SKILL.md

@@ -0,0 +1,71 @@
+---
+slug: muapi-color-analysis-board
+name: muapi-color-analysis-board
+version: "1.0.0"
+description: Turn a portrait photo into a high-end editorial "Color Analysis Board" in a luxury fashion-magazine style (Dior / Ralph Lauren aesthetic) — best colors, undertone, makeup guide, capsule wardrobe, hair & jewelry recommendations, all laid out on a clean beige/ivory grid.
+acceptLicenseTerms: true
+---
+
+
+# Color Analysis Board
+
+**Turn a portrait photo into a high-end editorial "Color Analysis Board" in a luxury fashion-magazine style (Dior / Ralph Lauren aesthetic) — best colors, undertone, makeup guide, capsule wardrobe, hair & jewelry recommendations, all laid out on a clean beige/ivory grid.**
+
+## Inputs
+
+| Name | Type | Required | Default | Description |
+|:---|:---|:---|:---|:---|
+| `person_image` | image_url | yes | — | A clear, well-lit portrait of the person. Front-facing, neutral background, and natural lighting give the strongest color reads (undertone, hair, eyes). Avoid heavy filters or makeup that masks the natural complexion. |
+
+
+## Steps
+
+### Phase A — Color Analysis Board Generation
+
+If `{{person_image}}` is not provided, ask the user to upload a clear front-facing portrait. Make sure the face is well-lit with natural color (no heavy filters, color-cast lighting, or sunglasses) — the model needs accurate skin, hair, and eye color to pick the right palette.
+
+Once the photo is available, submit ONE step to generate the color analysis board:
+
+1. **Color Analysis Board Generation** — `muapi image edit` (model=`gpt-image-2-image-to-image`):
+   - Reference Image: `{{person_image}}`
+   - Image size: `3840x2160` (16:9 landscape) — magazine-spread aspect ratio
+   - Background: `auto`
+   - Output format: `png`
+   - Quality: `auto`
+   - Moderation: `low`
+   - Prompt:
+     ```
+     Create a high-end editorial "Color Analysis Board" from this portrait in a luxury fashion magazine style (Dior / Ralph Lauren aesthetic). Clean beige/ivory background, warm tones, soft diffused lighting, ultra-detailed photorealistic quality, consistent lighting, minimal elegant typography, grid-based layout.
+
+     Main portrait: enhanced natural beauty (same identity, smooth skin, soft glow, realistic texture)
+     Top section: "Your Best Colors" with fabric swatches with the best algorithm choices
+     Undertone panel: warm / neutral / cool with marked result.
+     Colors to avoid
+     Neutrals that work
+     Prints that flatter
+     Makeup guide: eyeshadows, blush, lips, highlighter
+     "You in your colors": multiple outfit best variations
+     Hair colors: best.
+     Jewelry
+     Style notes
+
+     Capsule wardrobe: coordinated outfits, shoes, bags, accessories
+     Style: best style for me
+     ```
+
+Present the generated board to the user. Suggest variations they can try: a different source portrait (different lighting / hairstyle for comparison), or asking to bias the palette toward a season (e.g. "spring warm" vs "winter cool") or a specific brand aesthetic (e.g. minimalist Scandinavian, Old Money, streetwear).
+
+## Trigger Keywords
+
+`color analysis`, `color analysis board`, `personal color palette`, `seasonal color analysis`, `undertone analysis`, `style guide board`, `fashion color board`, `capsule wardrobe board`
+
+
+---
+
+## 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.
+- Source schema reference: `gpt-image-v2-edit` (from the source workflow JSON) maps to `gpt-image-2-image-to-image` in the muapi catalog.
+- The output is intentionally 16:9 (3840×2160) so it reads as a magazine spread / desktop wallpaper / Pinterest landscape board. For IG-feed square or 9:16 vertical, request a re-crop or re-run with a different `image_size`.

package/resources/skills/skills/media/core-edit/SKILL.md

@@ -0,0 +1,48 @@
+---
+name: muapi-media-editing
+version: 0.1.0
+description: Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more
+---
+
+# ✏️ MuAPI Media Editing & Enhancement
+
+**Advanced editing and enhancement operations for images and videos.**
+
+Apply AI-powered edits, enhancements, and effects to existing media. Supports prompt-based editing with Flux Kontext, GPT-4o, and Midjourney, plus one-click operations like upscaling and background removal.
+
+## Available Scripts
+
+| Script | Description |
+| :--- | :--- |
+| `edit-image.sh` | Prompt-based image editing (Flux Kontext, GPT-4o, Midjourney, Qwen, and more) |
+| `enhance-image.sh` | One-click operations: upscale, background removal, face swap, colorize, Ghibli style, product shots |
+| `lipsync.sh` | Sync video lip movement to audio (Sync Labs, LatentSync, Creatify, Veed) |
+| `video-effects.sh` | Video/image effects: Wan AI, face swap, dance, dress change, Luma modify/reframe |
+
+## Quick Start
+
+```bash
+# Edit an image with a prompt
+bash edit-image.sh --image-url "https://..." --prompt "add sunglasses" --model flux-kontext-pro
+
+# Upscale an image
+bash enhance-image.sh --op upscale --image-url "https://..."
+
+# Remove background
+bash enhance-image.sh --op background-remove --image-url "https://..."
+
+# Lipsync a video
+bash lipsync.sh --video-url "https://..." --audio-url "https://..." --model sync
+
+# Apply dance effect
+bash video-effects.sh --op dance --image-url "https://..." --audio-url "https://..."
+```
+
+## Common Flags
+
+All scripts support: `--async`, `--json`, `--timeout N`, `--help`
+
+## Requirements
+
+- `MUAPI_KEY` environment variable (set via `core/platform/setup.sh`)
+- `curl`, `jq`, `python3`