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=<what the person wants>" 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: A multi-shot story with consistent characters: script, storyboard, previz, shots, edit.
• How to animate a photo into a video with AI: A still photo brought to life: a subtle smile, blink, camera move or full scene motion.

Skills (44)

Prompts (5)

• fal Cinematography — fal: Direct cinematic stills and video: shot language, camera moves, lenses, lighting, grade and film texture.
• FLUX 3 Cinematic Inserts — Black Forest Labs: Write FLUX 3 prompts for standalone cinematic shots: shot craft, camera, continuity and review.
• Video Shotcraft — 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) — Serge Shima: AI film director for video prompts: dramaturgy first (Murch, blocking, montage), then exact syntax per model.
• Higgsfield Prompt Skill (O-Side Media) — 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 — fal: Put someone into a live sports broadcast: a realistic fan-cam cutaway with scoreboard and channel overlays.
• Filmed Off a Monitor — HeyGen: The UI looks filmed on a real display: slight perspective, focus falloff and glare.

Guides (6)

• fal Storytelling — fal: Plan multi-shot stories: storyboards, shot lists, first-to-last-frame chains and continuity across scenes.
• FLUX 3 Keyframes & Continuation — Black Forest Labs: Build FLUX 3 video from supplied stills or footage: keyframe image-to-video and continuation chains.
• Drama Skills (ZenStory) — ZenStory AI: Short-drama skills that beat a no-skill control in blind tests: script, assets, storyboard, keyframe and video prompts.
• Screenwriting Skills — 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 — 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 — 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 — 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 — fal: Follow proven multi-step fal pipelines for commercials, product shots, characters, lip-sync and try-on.
• Shuohao Short-Drama Skills — Wesley Wang: Seven chained skills from novel to AI short drama: characters, outline, art bible, script, staging, storyboard.
• AI Short Drama Studio — Hao0321: Greenlight score, series bible, episode compiler and production pack for serialized AI short dramas and manju.
• Procedural 3D Story — 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 — Higgsfield: Generate images, video, 3D and audio across 30+ models, plus ad videos and virality scoring, from one CLI.
• Gemini Omni Flash — Google Gemini: Generate and edit video with Gemini Omni 1.1 Flash: text-to-video, first/last frames, extensions, edits.
• Melies — Melies: Generate images, video, movie posters and thumbnails from the terminal with 148 AI actors and style flags.
• AI Video Generation — inference.sh: Generate video with 40+ models from one CLI: Veo 3.1, Seedance 2.0, HappyHorse, Wan, Grok and more.
• Google Veo — inference.sh: Generate cinematic video from text with Google Veo 3.1 and Veo 3.1 Fast.
• HappyHorse — inference.sh: Generate and edit video with Alibaba HappyHorse 1.0: text, image and reference-to-video plus video edits.
• Image to Video — inference.sh: Animate stills into video: pick the right model, then prompt motion and camera moves that hold together.
• P-Video — inference.sh: Generate fast 720p/1080p video with audio using Pruna P-Video and Wan text- and image-to-video.
• Seedance 2.0 — 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 — Runway: Generate and edit images, video, music, speech and sound effects from chat with Runway's MCP tools.
• Runway Studio Skills — Runway: Run Runway's API from Python scripts: text, image and video-to-video, character performance, images, TTS.
• FLUX 3 Video — Black Forest Labs: Route any FLUX 3 video job to the right specialist: diagnosis, direction, audio or execution.
• Kling AI — Kling AI, beta: Official Kling CLI: text/image-to-video, Omni reference and edit, images, reusable subjects, quota
• Seedance Video Gen — qiujiahong, beta: Text- and image-to-video with Doubao Seedance on Volcengine, with optional audio and first/last frame
• Tianshu Wan Video — 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 — 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 — dlazyai, beta: Animates a single first-frame image into a 5 or 10 second Jimeng (Dreamina) clip through the dLazy CLI
• dLazy Kling V3 — dlazyai, beta: Text-to-video and image-to-video with Kling v3 through the dLazy CLI, 3–15 s clips
• dLazy Seedance 2.0 — dlazyai, beta: Seedance 2.0 video from text, image/video/audio references or first and last frames, via dLazy
• dLazy PixVerse C1 — dlazyai, beta: PixVerse C1 video for action and VFX shots: text, image, reference or first/last frame, via dLazy
• dLazy Kling V3 Omni — 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 — dlazyai, beta: Jimeng (Dreamina) transition video between a first and last frame, 5 or 10 s, via dLazy
• dLazy Veo 3.1 — 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 — 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 — 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 — dlazyai, beta: Text, first/last-frame and reference-to-video with Alibaba's Wan 2.7, 2–15 s clips, through the dLazy CLI.