leynos

kling-3-0-deep-dive

Deep operating guidance for Kling 3.0 video generation. Use when selecting Kling 3.0 for a shot, designing multi-shot scene structure, writing Kling-native cinematic prompts, planning Elements or Motion Control references, using start/end frame anchors, handling native audio or dialogue, building product/commercial shots, choosing duration/aspect/quality settings, troubleshooting artifacts, or comparing Kling 3.0 against Seedance 2.0, Veo, Sora, DoP/Cinema, or other Higgsfield video routes. Complements shot-specifier and video-generator by turning Kling 3.0's scene-based model behaviour into practical production rules.

media-project

Package completed visual storytelling video outputs into OpenShot editor projects with the system-installed media-project command. Use when an agent needs to run or verify a playable .osp handoff, preserve production sidecar metadata, or decide whether a project is ready for OpenShot packaging.

nanobanana

Craft high-precision prompts and edit instructions for Nano Banana image workflows, especially when using the local nanobanana MCP tools for generation, editing, character consistency, or multi-image fusion. Use when the task needs structured prompts, reference-role assignment, layout-heavy image specs, typography-heavy images, iterative edit-first refinement, or reliable model/aspect/output-path choices.

phoneticize

Build pronunciation tables, generate text-to-speech (TTS) preview samples, and produce phoneticized scripts ready for narration. Use whenever a script is intended for text-to-speech rendering and the user wants to catch words the engine will mispronounce — proper nouns, Gaelic and Welsh names, brand names with idiosyncratic pronunciation (df12, Nginx), model names with embedded numerics (Atari 2600, ESP32), terms of art and acronyms (SaaS, OAuth, JWT), and document specifiers (ADR-0012, RFC 2119). Trigger on phrases like "phoneticize this script", "phonetecize this", "phonetize", "prep this for TTS", "build a pronunciation table", or any task involving text-to-speech narration where pronunciation consistency matters across takes. Drives a phased workflow: detect candidates, suggest phonetic respellings, render preview samples via the Higgsfield MCP TTS tool with Eleven v3, iterate with the user, and emit a final phoneticized script.

scene-inventory-extractor

End-to-end production-prep workflow: extracts comprehensive scene inventories from narrative writing, extracts continuity inventory and reset-critical state before prompt writing, generates all reference images (characters, locations under multiple angles/conditions, props), produces start/end/keyframe shot references with consistency verification, and then hands off to shot-specifier for per-shot direction, model routing, and prompt manifests. Use when analysing stories, scripts, or prose to create production-ready scene breakdowns with full visual asset pipelines. Also trigger when the user mentions "scene breakdown", "shot list", "character bible", "location bible", "continuity inventory", "reference images", "storyboarding", or any request to prepare narrative material for AI video generation. This skill expects access to an image-generation MCP and vision capabilities.

seedance-2-deep-dive

Deep operating guidance for Seedance 2.0 video generation. Use when selecting Seedance 2.0 for a shot, designing multimodal references, writing Seedance-native prompts, choosing duration/aspect/quality settings, planning batch generations, troubleshooting drift or artifacts, or comparing Seedance 2.0 against Kling, Veo, Sora, DoP/Cinema, or other Higgsfield video routes. Complements shot-specifier and video-generator by turning Seedance 2.0's multimodal model behaviour into practical shot-planning and generation rules.

shot-specifier

Per-shot production specification workflow: takes a completed scene inventory (from scene-inventory-extractor-v2) and decomposes every scene into numbered shots with full directorial direction — actor position and movement, camera mount and motion, lens, lighting setup, practical effects, timing, and clip boundaries. Generates storyboard keyframe images via nanobanana, assembles video generation prompts with model routing, and maintains an asset pipeline with consistent file naming and a generation manifest. Use when a scene inventory exists and the workflow must move from scene descriptions to individual, generation-ready clips. Also trigger when the user mentions "shot list", "shot breakdown", "storyboard", "video prompt", "model routing", "clip generation", or "per-shot direction".

video-generator

Execute production video generation from shot-specifier outputs through the Higgsfield Model Context Protocol (MCP). Use when prompts, storyboard frames, media roles, model routing, Higgsfield MCP uploads, generate_video calls, status polling, retakes, resume behaviour, or final assembly order are needed. Bridges structured [TAG] prompt files to model-native plain text prompts, validates model duration/aspect constraints, decomposes key-frame shots into supported start/end image clips, tracks uploaded media and job IDs, and writes generation logs.