# Cinematic & short films: agent skills for cinematic AI video and short films > **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/api/search?q="` returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the how-to page. Cinematic AI footage, short films, trailers and multi-shot scenes made with Seedance, Kling and Veo. 44 skills for Claude Code, Codex and Grok, by type: workflows take a brief to a finished video, effects and styles change how it looks, prompts and guides teach the agent the craft, models run the generation. ## How-to tutorials - [How to make an AI short film](https://varg.ai/how-to/make-an-ai-short-film.md): A multi-shot story with consistent characters: script, storyboard, previz, shots, edit. - [How to animate a photo into a video with AI](https://varg.ai/how-to/animate-a-photo-into-a-video.md): A still photo brought to life: a subtle smile, blink, camera move or full scene motion. ## Skills (44) ### Prompts (5) - [fal Cinematography](https://varg.ai/how-to/skills/fal-cinematography.md) — fal: Direct cinematic stills and video: shot language, camera moves, lenses, lighting, grade and film texture. - [FLUX 3 Cinematic Inserts](https://varg.ai/how-to/skills/flux-3-cinematic-inserts.md) — Black Forest Labs: Write FLUX 3 prompts for standalone cinematic shots: shot craft, camera, continuity and review. - [Video Shotcraft](https://varg.ai/how-to/skills/video-shotcraft.md) — Vincent Wei: 124 shot recipe cards and a tested Remotion template for cinematic product promos built from real UI screenshots. - [AI Film Director (Visual Skills)](https://varg.ai/how-to/skills/visual-skills-video-director.md) — Serge Shima: AI film director for video prompts: dramaturgy first (Murch, blocking, montage), then exact syntax per model. - [Higgsfield Prompt Skill (O-Side Media)](https://varg.ai/how-to/skills/higgsfield-prompt-skill-oside.md) — O-Side Media: Independent 36-skill prompt pack for Higgsfield: model picks, camera presets, Soul ID, Cinema Studio, Seedance 2.5. ### Effects (2) - [fal Fan Cam](https://varg.ai/how-to/skills/fal-fan-cam.md) — fal: Put someone into a live sports broadcast: a realistic fan-cam cutaway with scoreboard and channel overlays. - [Filmed Off a Monitor](https://varg.ai/how-to/skills/filmed-off-a-monitor.md) — HeyGen: The UI looks filmed on a real display: slight perspective, focus falloff and glare. ### Guides (6) - [fal Storytelling](https://varg.ai/how-to/skills/fal-storytelling.md) — fal: Plan multi-shot stories: storyboards, shot lists, first-to-last-frame chains and continuity across scenes. - [FLUX 3 Keyframes & Continuation](https://varg.ai/how-to/skills/flux-3-keyframes-continuation.md) — Black Forest Labs: Build FLUX 3 video from supplied stills or footage: keyframe image-to-video and continuation chains. - [Drama Skills (ZenStory)](https://varg.ai/how-to/skills/zenstory-drama-skills.md) — ZenStory AI: Short-drama skills that beat a no-skill control in blind tests: script, assets, storyboard, keyframe and video prompts. - [Screenwriting Skills](https://varg.ai/how-to/skills/screenwriting-skills.md) — Terry Jia: 26 screenwriting and dramaturgy skills, from story structure to writing in the style of Ozu, Chekhov or Succession. - [Emma Short-Drama Writing Skills](https://varg.ai/how-to/skills/emma-screenwriting.md) — Emma Wang, beta: Short-drama writing kit (hooks, outlines, dialogue, trims, US localization) that beat a no-skill control in blind tests. - [Short Drama Skill Finder](https://varg.ai/how-to/skills/short-drama-skill-finder.md) — Underleveled Builder: Picks short-drama and manju skills from a hand-checked list of 90+ projects by stage, video model and agent. ### Workflows (5) - [Previz to Seedance](https://varg.ai/how-to/skills/varg-previz.md) — varg, beta: Plan multi-shot AI video before paying: story, anchor sheets, a three.js grey-box previz, then a Seedance v2v pack. - [fal Recipes](https://varg.ai/how-to/skills/fal-recipes.md) — fal: Follow proven multi-step fal pipelines for commercials, product shots, characters, lip-sync and try-on. - [Shuohao Short-Drama Skills](https://varg.ai/how-to/skills/shuohao-short-drama.md) — Wesley Wang: Seven chained skills from novel to AI short drama: characters, outline, art bible, script, staging, storyboard. - [AI Short Drama Studio](https://varg.ai/how-to/skills/ai-short-drama-studio.md) — Hao0321: Greenlight score, series bible, episode compiler and production pack for serialized AI short dramas and manju. - [Procedural 3D Story](https://varg.ai/how-to/skills/karpathy-3d-story.md) — chencheng (云谦), beta: Turn a myth or book into a seeded, multi-chapter procedural three.js film in one scene.html, audited frame by frame. ### Models & tools (26) - [Higgsfield Generate](https://varg.ai/how-to/skills/higgsfield-generate.md) — Higgsfield: Generate images, video, 3D and audio across 30+ models, plus ad videos and virality scoring, from one CLI. - [Gemini Omni Flash](https://varg.ai/how-to/skills/gemini-omni-flash-api.md) — Google Gemini: Generate and edit video with Gemini Omni 1.1 Flash: text-to-video, first/last frames, extensions, edits. - [Melies](https://varg.ai/how-to/skills/melies.md) — Melies: Generate images, video, movie posters and thumbnails from the terminal with 148 AI actors and style flags. - [AI Video Generation](https://varg.ai/how-to/skills/inference-sh-ai-video-generation.md) — inference.sh: Generate video with 40+ models from one CLI: Veo 3.1, Seedance 2.0, HappyHorse, Wan, Grok and more. - [Google Veo](https://varg.ai/how-to/skills/inference-sh-google-veo.md) — inference.sh: Generate cinematic video from text with Google Veo 3.1 and Veo 3.1 Fast. - [HappyHorse](https://varg.ai/how-to/skills/inference-sh-happyhorse.md) — inference.sh: Generate and edit video with Alibaba HappyHorse 1.0: text, image and reference-to-video plus video edits. - [Image to Video](https://varg.ai/how-to/skills/inference-sh-image-to-video.md) — inference.sh: Animate stills into video: pick the right model, then prompt motion and camera moves that hold together. - [P-Video](https://varg.ai/how-to/skills/inference-sh-p-video.md) — inference.sh: Generate fast 720p/1080p video with audio using Pruna P-Video and Wan text- and image-to-video. - [Seedance 2.0](https://varg.ai/how-to/skills/inference-sh-seedance.md) — inference.sh: Make 4–15 s videos with synced audio in Seedance 2.0: text, image or reference-to-video up to 1080p. - [Runway Media](https://varg.ai/how-to/skills/runway-media.md) — Runway: Generate and edit images, video, music, speech and sound effects from chat with Runway's MCP tools. - [Runway Studio Skills](https://varg.ai/how-to/skills/runway-studio-skills.md) — Runway: Run Runway's API from Python scripts: text, image and video-to-video, character performance, images, TTS. - [FLUX 3 Video](https://varg.ai/how-to/skills/flux-3-video.md) — Black Forest Labs: Route any FLUX 3 video job to the right specialist: diagnosis, direction, audio or execution. - [Kling AI](https://varg.ai/how-to/skills/klingai.md) — Kling AI, beta: Official Kling CLI: text/image-to-video, Omni reference and edit, images, reusable subjects, quota - [Seedance Video Gen](https://varg.ai/how-to/skills/video-gen.md) — qiujiahong, beta: Text- and image-to-video with Doubao Seedance on Volcengine, with optional audio and first/last frame - [Tianshu Wan Video](https://varg.ai/how-to/skills/tianshu-wan-video.md) — wangshengli0421, beta: Text-to-video and image-to-video with Alibaba's Wan 2.6 through DashScope, from a small Node.js script - [dLazy Video Generate](https://varg.ai/how-to/skills/dlazy-video-generate.md) — dlazyai, beta: Picks a video model for your prompt from about 20 on dLazy (Jimeng, Kling, Veo, Seedance, Wan, PixVerse) and runs it - [dLazy Jimeng First-Frame Video](https://varg.ai/how-to/skills/dlazy-jimeng-i2v-first.md) — dlazyai, beta: Animates a single first-frame image into a 5 or 10 second Jimeng (Dreamina) clip through the dLazy CLI - [dLazy Kling V3](https://varg.ai/how-to/skills/dlazy-kling-v3.md) — dlazyai, beta: Text-to-video and image-to-video with Kling v3 through the dLazy CLI, 3–15 s clips - [dLazy Seedance 2.0](https://varg.ai/how-to/skills/dlazy-seedance-2-0.md) — dlazyai, beta: Seedance 2.0 video from text, image/video/audio references or first and last frames, via dLazy - [dLazy PixVerse C1](https://varg.ai/how-to/skills/dlazy-pixverse-c1.md) — dlazyai, beta: PixVerse C1 video for action and VFX shots: text, image, reference or first/last frame, via dLazy - [dLazy Kling V3 Omni](https://varg.ai/how-to/skills/dlazy-kling-v3-omni.md) — dlazyai, beta: Kling v3 Omni video from frames, up to 7 images or a reference video, via the dLazy CLI - [dLazy Jimeng First-Last Frame](https://varg.ai/how-to/skills/dlazy-jimeng-i2v-first-tail.md) — dlazyai, beta: Jimeng (Dreamina) transition video between a first and last frame, 5 or 10 s, via dLazy - [dLazy Veo 3.1](https://varg.ai/how-to/skills/dlazy-veo-3-1.md) — dlazyai, beta: Google Veo 3.1 video from frames or reference images, plus +7 s extend, up to 4K, via dLazy - [Vidu Q2 Image-to-Video via dLazy](https://varg.ai/how-to/skills/dlazy-viduq2-i2v.md) — dlazyai, beta: Animate images into 2–10 s clips with Vidu Q2, by reference images or first/last frame, through the dLazy CLI. - [Veo 3.1 Fast via dLazy](https://varg.ai/how-to/skills/dlazy-veo-3-1-fast.md) — dlazyai, beta: Quick 4–8 s text- or image-to-video clips and +7 s extensions with Google Veo 3.1 Fast, via the dLazy CLI. - [Wan 2.7 via dLazy](https://varg.ai/how-to/skills/dlazy-wan2-7.md) — dlazyai, beta: Text, first/last-frame and reference-to-video with Alibaba's Wan 2.7, 2–15 s clips, through the dLazy CLI.