Video gen
Creator-lane agent skills from Agentic Creator OS. Install: npx skills add frankxai/creator-skills
npx -y skills add frankxai/creator-skills --skill video-genAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Route any image or video generation request to the right engine and pipeline. Use when asked to "make a video", "generate an image", "create b-roll", "make a video ad", "animate this photo", "clip for socials", "product shot", "talking head", "faceless video", "YouTube short", "UGC video", or any multi-step visual content request. Classifies intent by deliverable, identity consistency, and destination, dispatches to installed engine skills (Higgsfield, Nano Banana, Grok Imagine), then chains assembly (HyperFrames) and editing/publishing (Descript). For pricing or capability ceilings, hand off to video-engine-routing.
SKILL.md
5.4 KB, as published. Nobody here has run it
video-gen — the routing brain for visual content
One dispatcher, many engines. Intents stay stable; engines are swappable. When an engine changes, this file changes — the prompts and pipelines that call it do not.
Stack prerequisites
This skill routes to engines you install separately. Missing engines degrade gracefully — the router picks the next-best available and says so.
| Engine | Role | Install |
|---|---|---|
| Higgsfield CLI + skills | Default image and video engine (paid account) | curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh, then sync the vendor skills (higgsfield-generate, higgsfield-soul-id, higgsfield-product-photoshoot, higgsfield-marketplace-cards) |
| Gemini API key | Nano Banana image gen and edits (character/reference work) | GEMINI_API_KEY env var |
| Grok Imagine | Fast stylized images if you have a SuperGrok subscription | vendor CLI/app |
| HyperFrames | HTML video compositions, captions, TTS, audio-reactive motion | npx hyperframes + its skills |
| Descript MCP | Edit by editing text: cuts, filler removal, captions, publish | connect the Descript MCP server |
Step 1 — classify the request
Three axes decide everything downstream:
| Axis | Values |
|---|---|
| Deliverable | still image · single clip (≤15s) · assembled video (edited, multi-scene) |
| Identity consistency | none · product (same object every shot) · face (same person every shot) |
| Destination | social feed · marketplace listing · YouTube · website/hero · ad campaign |
If the user did not specify duration, aspect ratio, or destination, infer from context; ask only when the answer changes the engine choice.
Step 2 — dispatch
| Intent | Route | Why |
|---|---|---|
| Product/brand still | higgsfield-product-photoshoot | prompt templates for studio, lifestyle, hero, carousel |
| Marketplace listing set | higgsfield-marketplace-cards | compliant main image + secondary + A+ modules |
| Same face across shots | higgsfield-soul-id (train once) → higgsfield-generate with the Soul id | identity persists across images and video |
| Generic still, design, legible text | higgsfield-generate (GPT Image 2) | strongest text rendering |
| Character/reference image edit | Nano Banana via Gemini API | best reference-following for edits |
| Fast stylized still | Grok Imagine | included in a SuperGrok subscription, zero marginal cost |
| Single video clip, default | higgsfield-generate (Seedance 2.0) | best price/quality for social clips |
| Single video clip, cinematic | higgsfield-generate (Kling 3.0) | motion quality, camera control |
| Branded ad with avatar/product | Higgsfield Marketing Studio (via higgsfield-generate) | hooks, avatars, product placement in one flow |
| Captions, title cards, audio-reactive motion, scroll video | HyperFrames composition | deterministic HTML video, no generation cost |
| Cut, rearrange, remove filler, subtitle, publish | Descript MCP (import_media → prompt_project_agent → export) | text-based editing beats timeline scrubbing |
Fallback order when an engine is missing: Higgsfield → Nano Banana (images only) → Grok Imagine (images only). If no video engine is installed, stop and say which install unblocks.
Step 3 — pipelines
30-second product ad
- higgsfield-product-photoshoot → 3 stills (hero, lifestyle, closeup)
- higgsfield-generate image-to-video on the hero (Seedance 2.0, 5s)
- HyperFrames: title card + price overlay + end card around the clip
- Descript: assemble, caption, export per destination aspect ratio
Faceless YouTube b-roll batch
- Script beats → one prompt per beat
- higgsfield-generate batch (Seedance 2.0, 5s each)
- Voiceover: HyperFrames TTS, or ElevenLabs if the user has it
- Descript: import all, sequence to narration, auto-captions
Talking-head with a consistent face
- higgsfield-soul-id: train once, store the reference id
- higgsfield-generate with the Soul id → presenter clips
- Descript: filler-word removal, captions, publish
Caption-heavy short (quote/hook format)
- Still from the dispatch table (or user-supplied)
- HyperFrames: audio-reactive captions, marker highlights, beat-synced motion
- Render via HyperFrames; no Descript needed
Quality gate before publishing
For anything going to a paid placement or a growth channel, run the Higgsfield virality
predictor (brain_activity) on the finished cut: hook strength, retention risk, distraction.
Score low → fix the first 2 seconds before touching anything else.
When you hit a ceiling
Credits exhausted, need a custom pipeline (LoRA, ControlNet, motion transfer), or per-clip
cost matters at volume → hand off to the video-engine-routing skill. It holds the decision
tree and current pricing for subscription vs pay-per-use vs cloud ComfyUI.