video-generation-gateways
Select, integrate, and operate multi-model video-generation gateways — hosted inference aggregators such as fal.ai, Replicate, and WaveSpeed that expose many third-party video (and video-adjacent audio) models behind one account, one API surface, and one bill. Use when deciding whether to route video generation through a gateway versus a direct model-provider API; when comparing gateways on catalog, async/queue job design, webhooks, pricing, schema discovery, and version pinning; and when operating gateway workloads in production — spend controls, retries, cross-gateway failover, content- s
Profile →npx skills add calesthio/generative-media-skills --skill video-generation-gateways --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides the agent to select, integrate, and operate multi-model video-generation gateways (fal.ai, Replicate, WaveSpeed) that expose many third-party video models behind one account and one API surface. It covers decisions on routing through a gateway vs direct model-provider API, gateway evaluation criteria (catalog, async/queue job design, webhooks, pricing, schema discovery, version pinning, spend controls, retries, cross-gateway failover, content-safety differences, data retention, and commercial-rights passthrough), and operational production considerations for gateway workloads.
How it works
The skill defines the production contracts and operational patterns for gateway usage. It treats video generation as an asynchronous job queue rather than synchronous calls. The core workflow is Submit a job to a gateway, await completion via webhook or polling, then fetch and persist the hosted media URL before expiry. It provides concrete submission endpoints and status/result formats for fal.ai, Replicate, and WaveSpeed, including how to handle retries, deadlines, and result retrieval. It emphasizes per-model schema discovery, version pinning, and deprecation warnings, with guidance on when to prefer gateways vs direct APIs based on surface exposure, SLAs, and contractual terms. It also outlines webhook security checks, retry/backoff behaviors, and idempotent webhook handling. It details spend controls across gateways (prepaid credits, per-use billing, caps, and enterprise options) and cautions about deprecation risks and change management.
When to use it
Use when you need to route video generation through a gateway rather than direct model-provider APIs, especially to underpin multiple models behind a single integration, to unify async job handling, or to compare gateways on catalog, schema discovery, version pinning, and spend controls. It is applicable for production workloads where spend controls, retries, cross-gateway failover, content-safety differences, data retention, and commercial-rights passthrough are relevant. It is not directly for direct model-provider APIs, local/self-hosted inference, or image-only gateway use.
What it can touch
The skill enumerates concrete endpoints and actions for fal.ai, Replicate, and WaveSpeed: submitting jobs, polling/status endpoints, result URLs, webhook configurations, and signing/verification for webhooks. It references the specific API surfaces such as fal.ai queue endpoints, Replicate predictions endpoints, and WaveSpeed model endpoints, along with schema discovery mechanisms and versioning formats. It emphasizes using the provided endpoints and documented fields (e.g., request_id, status, result URLs, openapi schemas) and does not imply actions beyond those specified surfaces.
Caveats
Notes include that pricing and catalogs are volatile and should be re-verified before shipping; version pinning is recommended for reproducibility; deprecation of endpoints or models is a real operational risk; webhook security requires verification steps; and spend controls vary by gateway (prepaid credits, hard caps, and potential lack of native alerting). The skill cautions about per-model surface limitations and the need to rely on per-model docs for exact input parameters and schemas.
# Video-generation gateways A **video-generation gateway** is a hosted inference aggregator that resells many third-party video models (Veo, Kling, Seedance, Hailuo/MiniMax, Luma, Wan, LTX-Video, Pika, and others) behind a single account, a single API convention, and a single bill. You send a prompt and parameters to a gateway-owned endpoint; the gateway runs the underlying model on its own infras
What does the video-generation-gateways skill do?
Select, integrate, and operate multi-model video-generation gateways — hosted inference aggregators such as fal.ai, Replicate, and WaveSpeed that expose many third-party video (and video-adjacent audio) models behind one account, one API surface, and one bill. Use when deciding whether to route video generation through a gateway versus a direct model-provider API; when comparing gateways on catalog, async/queue job design, webhooks, pricing, schema discovery, and version pinning; and when operating gateway workloads in production — spend controls, retries, cross-gateway failover, content- s
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill video-generation-gateways --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.