video-gen
Skill6 starsChanged 47 days agoMITView on GitHub
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 the engine skills you have installed (for example Higgsfield, Nano Banana, Grok Imagine), then chains assembly (HyperFrames) and editing/publishing (Descript). For pricing or capability ceilings, hand off to video-engine-routing.
- Reads credentials
5 other projects use a version of this.
Adopted by
Most recently taken up by
- ksprashu/agent-skill-forgetheir own version, first seen Nov 16, 2026
- zditor/zditor-docstheir own version, first seen Oct 8, 2026
- taylorzhou16/video-gentheir own version, first seen Apr 16, 2026
- marswaveai/skillstheir own version, first seen Mar 25, 2026
- kunwl123456/zeroclaw-skills-collectiontheir own version, first seen Feb 19, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- zditor/zditor-docs★ 275same name
- marswaveai/skills★ 82same name
- kunwl123456/zeroclaw-skills-collection★ 27same name
- taylorzhou16/video-gen★ 9same name
- ksprashu/agent-skill-forge★ 3same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brand-voiceSkill
- creator-launchSkill
- short-form-hooksSkill
- youtube-packagingSkill
- acos-visual-genSkill
- arcanea-book-coverSkill
- suno-ai-masterySkill
- suno-prompt-architectSkill
- production-reviewSkill
- video-engine-routingSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 40
If the user did not specify duration, aspect ratio, or destination, infer from context.
- Very specific: line 62
If the engine for a role is missing, use the next-best one you have (an image-only engine can cover stills, not clips).
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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. It does not recommend a vendor. It uses
the engines you already have, and when a role is missing it says which kind of engine unblocks
you, then points to video-engine-routing for the cost and capability comparison.
| Engine | Role | Install |
| Higgsfield CLI + skills | All-in-one image and video engine (paid account); vendor skills: higgsfield-generate, higgsfield-soul-id, higgsfield-product-photoshoot, higgsfield-marketplace-cards | Follow the vendor's official install docs and read any install script before you run it |
| 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 |
Any other image or video engine that fits a role below (a pay-per-use API such as fal.ai, a Veo or Kling account, cloud or local ComfyUI) works the same way: assign it to the role it covers.
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
Pick the role first, then use the engine you have for it. The last column lists the shortcut when that vendor's skill is installed.
| Intent | Role | Why | Shortcut if installed |
| Product/brand still | image engine with product-shot templates | studio, lifestyle, hero, carousel prompts | higgsfield-product-photoshoot |
| Marketplace listing set | image engine with listing templates | compliant main image + secondary + A+ modules | higgsfield-marketplace-cards |
| Same face across shots | identity engine (train a reference once, reuse it) | identity persists across images and video | higgsfield-soul-id → higgsfield-generate with the Soul id; a LoRA on ComfyUI does the same job |
| Generic still, design, legible text | image engine with strong text rendering | legible text is the deciding factor | higgsfield-generate (GPT Image 2) |
| Character/reference image edit | reference-following image editor | best at keeping the reference intact | Nano Banana via Gemini API |
| Fast stylized still | fast image engine | zero marginal cost if already subscribed | Grok Imagine (included in a SuperGrok subscription) |
| Single video clip, default | budget video engine | best price/quality for social clips | higgsfield-generate (Seedance 2.0) |
| Single video clip, cinematic | cinematic video engine | motion quality, camera control | higgsfield-generate (Kling 3.0) |
| Branded ad with avatar/product | ad-format video engine | hooks, avatars, product placement in one flow | Higgsfield Marketing Studio (via higgsfield-generate) |
| Captions, title cards, audio-reactive motion, scroll video | HyperFrames composition | deterministic HTML video, no generation cost | HyperFrames |
| Cut, rearrange, remove filler, subtitle, publish | text-based editor | text-based editing beats timeline scrubbing | Descript MCP (import_media → prompt_project_agent → export) |
If the engine for a role is missing, use the next-best one you have (an image-only engine can
cover stills, not clips). If no video engine is installed, stop, say which kind of engine
unblocks the request, and hand off to video-engine-routing.
Step 3 — pipelines
Steps name the role; the engine in brackets is the shortcut when installed.
30-second product ad
- Image engine, product-shot templates → 3 stills (hero, lifestyle, closeup) [higgsfield-product-photoshoot]
- Video engine, image-to-video on the hero, 5s [higgsfield-generate with Seedance 2.0]
- 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
- Video engine, batch, 5s each [higgsfield-generate with Seedance 2.0]
- Voiceover: HyperFrames TTS, or ElevenLabs if the user has it
- Descript: import all, sequence to narration, auto-captions
Talking-head with a consistent face
- Identity engine: train once, store the reference id [higgsfield-soul-id]
- Video engine with that identity → presenter clips [higgsfield-generate with the Soul id]
- 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, check the finished cut for hook
strength, retention risk and distraction. If your engine has a predictor, use it (Higgsfield's is
brain_activity); otherwise review the first 2 seconds by hand against the same three points.
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 the cost structure for subscription vs pay-per-use vs cloud ComfyUI.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

