AI Video Generation skills for Claude Code and Codex
Skills that create footage from text or images with models such as Kling, Seedance, Veo, Cosmos and Venice, plus prompt guides for video models.
Highest-scoring AI video generation skills in the October 22, 2026 snapshot: video-router from Orkas-AI/Orkas-VideoStudio (83/100), vibe-creating-prompt from Alisa0808/vibe-creating-skill (80/100) and prompt-videos from replicate/skills (70/100). Scores come from the Suede Skill Check.
- 18 listed skills
- 6 repositories
- 3 with full pages
5 from official publishers. 11 bundle scripts. 0 connect to an outside service. Listed in Video, Image, Audio and Creative (18).
All 18 AI video generation skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| prompt-videos 70/100 · C | replicate/skills | Teaches prompting techniques for AI video generation models on Replicate, for writing prompts or building video generation features. |
| vibe-creating-prompt 80/100 · B | Alisa0808/vibe-creating-skill | Rewrites ideas or rough prompts into clearer text-to-video prompts in the Vibe Creating style, preserving user-specified dialogue, voiceover, music, and sound effects. |
| video-router 83/100 · B | Orkas-AI/Orkas-VideoStudio | Classifies a video-production brief and locks the primary path, either generating AI footage, composing designed HTML, editing real footage, or AUTO end-to-end. |
| animate-image 73/100 · C | gooseworks-ai/goose-skills | Animate an existing product image or static ad into a short branded video using the GooseWorks Animate Images workflow, with source-image continuity… |
| create-video-fal 83/100 · B | gooseworks-ai/goose-skills | Image-to-video (or text-to-video) via any FAL video model (Kling, Seedance, Veo), ROUTED THROUGH THE GooseWorks fal-proxy so the call bills the Ads… |
| create-video-seedance-2-fal 72/100 · C | gooseworks-ai/goose-skills | Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai, for shots with no realistic face (a product… |
| paidf-augmentation 81/100 · B | NVIDIA/skills | Use when authoring or validating PAIDF augmentation YAML configs, or running remote Cosmos Transfer (including Cosmos3 WSM controls), Cosmos… |
| paidf-cosmos-predict 72/100 · C | NVIDIA/skills | Prepare and run PAIDF Cosmos Predict video generation for DEFT media samples. |
| physical-ai-event-video-generation 77/100 · C | NVIDIA/skills | Run the PAIDF Orchestration Event Video Generation DAG on Kubernetes - image-to-video anomaly generation, auto-labeling, and anomaly dataset… |
| render-absurdist-explainer 81/100 · B | gooseworks-ai/goose-skills | Assemble an absurdist animated-explainer video ad (~38s, 9:16) from per-scene i2v clips + their measured VO windows — retime each clip to its VO… |
| render-cartoon-music-video 79/100 · C | gooseworks-ai/goose-skills | Assemble a cartoon / animated / hand-crafted music-video ad from a config — a sung song carries the whole narrative while N per-bar i2v clips (one… |
| render-cgi-sizzle 81/100 · B | gooseworks-ai/goose-skills | Assemble a 3D-CGI app sizzle — nano-banana CGI plates (blank-glow floating phone + a CGI studio with rim-light + placeholder burst shapes; studio… |
| render-cinematic-music-video 81/100 · B | gooseworks-ai/goose-skills | Assemble a cinematic live-action-style music-video ad from a config — an original sung anthem carries the whole narrative while N 35mm-film-look i2v… |
| render-editorial-motion-podcast 81/100 · B | gooseworks-ai/goose-skills | Assemble an editorial-motion podcast-clip ad from a config — a real clipped podcast MP3 carries the narrative while N flat limited-palette… |
| render-narrated-ugc-wardrobe-stitch 73/100 · C | gooseworks-ai/goose-skills | Assemble a narrated-UGC "stitch reply" ad from a config — a single spoken VO carries a verbatim testimonial while ~30 per-cut i2v clips (one creator… |
| render-song-mv 81/100 · B | gooseworks-ai/goose-skills | Assemble a song-driven music-video ad from a config — a generated sung track carries the whole narration across N tableaux (one keyframe -> one i2v… |
| stage-generate 72/100 · C | Orkas-AI/Orkas-VideoStudio | AI-generated footage plus execution of bounded semantic video-edit segments already approved by EDIT/AUTO. Generate per shot with `ovs video`… |
| venice-video 67/100 · D | veniceai/skills | Generate videos via Venice. Covers the async /video/quote + /video/queue + /video/retrieve + /video/complete loop, text-to-video, image-to-video… |
How to choose AI video generation skills
Most skills call one hosted service (fal.ai, Venice, Replicate or NVIDIA), and video generation costs more per call than images. Confirm keys and budgets first.
Prompt skills help any model; endpoint skills run the job. Pair one of each.
For a full production flow with review gates, the Orkas VideoStudio router sends a brief to generation, composition or editing.
Ranked AI video generation shortlists
Related topics
Video Ads 45Animation and Motion Graphics 23Prompt Engineering 28Prompt Generators 19Video Avatars and AI Presenters 11Video Editing 10Video Enhancement 3Video Scripts and Storyboards 7
Find your next useful skill
Explore Rising Skills with quality scores and source reports, or search from inside your agent.
Get Rising Skills by email · Read Rising Skills · Install the finder · State of Agent Skills