image-generation-gateways
Select, integrate, and operate multi-model image-generation gateways with model-specific schema discovery, version policy, asynchronous jobs, webhooks, spend approval, safe inputs and artifacts, data-governance review, and billing observability. Use for comparing or building against fal.ai, Replicate, or Together AI image APIs, including controlled failover; do not use for direct model-provider APIs, local inference, training, dedicated endpoint provisioning, video generation, or general image editing.
Profile →npx skills add calesthio/generative-media-skills --skill image-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
Select, integrate, and operate multi-model image-generation gateways with model-specific schema discovery, version policy, asynchronous jobs, webhooks, spend approval, safe inputs and artifacts, data-governance review, and billing observability. Use for comparing or building against fal.ai, Replicate, or Together AI image APIs, including controlled failover; do not use for direct model-provider APIs, local inference, training, dedicated endpoint provisioning, video generation, or general image editing.
How it works
The skill treats a gateway as the access surface for multiple models, keeping gateway details, model publisher, model/version, execution path, schema, price, safety behavior, and downstream terms as separate facts in every plan and ledger row. It covers three gateways: fal.ai Model APIs (direct or queue calls with status, cancellation, and signed webhooks), Replicate predictions (prediction resources around various models), and Together AI serverless images (synchronous OpenAI-like image endpoint across models). For each approved adapter, it prescribes:
- Retrieve the current model-specific schema from the first-party page/API.
- Permit only fields in that schema with local type/range checks.
- Save a canonical schema hash and model/page URL in the release record.
- Test a dry request fixture and mocked responses for success/failure.
- Require review when key design changes occur (schema hash, endpoint ID, model/version, price unit, publisher terms, or safety defaults).
It also contains a detailed set of rules and example price observations from 2026-07-10 for fal.ai, Replicate, and Together, and a comprehensive paid-plan validation workflow using a Python script to verify approval plans before capable adapters run.
When to use it
Use when you need to compare or build against multi-model image APIs (fal.ai, Replicate, Together AI), especially when considering controlled failover, schema discovery, version policies, and governance/billing observability. Do not use for direct model-provider APIs, local inference, training, dedicated endpoint provisioning, video generation, or general image editing.
What it can touch
The skill lists tools: claude-code, codex, copilot, cursor. It emphasizes reading model schemas from first-party pages/APIs, validating inputs against discovered schema, and managing release records, dry-run tests, and billing/terms data in planning records. No explicit runtime touch of external endpoints is described here beyond recommended validation and governance steps.
Caveats
The skill includes license and governance notes (MIT license) and prescribes strict steps for schema validation, recording hashes, and approval workflows. It emphasizes three gateways (fal.ai, Replicate, Together AI) and warns against universal payloads across gateways, ensuring model/version-specific schemas are used. The guidance relies on evidence labels (FACT, PROVIDER CLAIM, HEURISTIC, UNKNOWN) for disclosures, with checks dated 2026-07-10. Exhibits a heavy emphasis on validation scripts, dry runs, and controlled spend approval, without guaranteeing generation outcomes.
# Image generation through gateways A gateway standardizes account access, not model behavior. Keep gateway, model publisher, model/version, execution path, schema, price, safety behavior, and downstream terms as separate facts in every plan and ledger row. This skill covers three current multi-model serverless gateways: - **fal.ai Model APIs**: direct or persistent queue calls to model endpoint I
What does the image-generation-gateways skill do?
Select, integrate, and operate multi-model image-generation gateways with model-specific schema discovery, version policy, asynchronous jobs, webhooks, spend approval, safe inputs and artifacts, data-governance review, and billing observability. Use for comparing or building against fal.ai, Replicate, or Together AI image APIs, including controlled failover; do not use for direct model-provider APIs, local inference, training, dedicated endpoint provisioning, video generation, or general image editing.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill image-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.