runway-video
Build and operate production-safe Runway API video generation, video editing, and character-performance workflows with native Runway models, explicit paid-call approval, duplicate-create protection, asynchronous task handling, secure media transfer, and evidence-aware governance.
Profile →npx skills add calesthio/generative-media-skills --skill runway-video --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
Describes a server-side integration for Runway video generation, editing, and character-performance workflows using the Runway Developer API. It supports Runway-native models, explicit paid-call approval, duplicate-create protection, asynchronous task handling, secure media transfer, and evidence-aware governance. It covers scope exclusions such as consumer web app endpoints, real-time characters, and non-video routes. It defines an upfront setup of consent, data rights, and execution modes, and provides concrete endpoints, inputs, and pricing guidance for native Runway models.
How it works
- Start with scope, consent, and an execution mode: determine mode (Plan/dry-run, Approved create, Resume, Cancel/delete) and collect rights, permissions, and provenance details.
- Route the request to the current Runway-native surface and document endpoints like /v1/text_to_video, /v1/image_to_video, /v1/video_to_video, /v1/character_performance, including required anchors and durations from the API model catalog.
- Enforce explicit paid-approval workflow: require a canonical request envelope, human approval, and specific environment flags (SEND_RUNWAY_REQUEST=1, APPROVE_RUNWAY_PAID_CALL=YES, RUNWAY_APPROVAL_SHA256 matching).
- Implement duplicate-create protection by creating a local job record before POST and treating task IDs as asynchronous results.
- Handle input media as per Runway API: support HTTPS URLs, data URIs, and runway:// ephemeral uploads with appropriate size limits; validate and bind SHA-256 to approvals.
- Manage output media as signed, time-limited URLs; download to private storage, compute SHA-256, and log metadata including task ID, prompts, source hashes, and rights disclosures.
- Apply pricing rules for native modes (gen4.5, gen4_turbo, aleph2, act_two) and adhere to approval and billing constraints; use conservative upper bounds for approvals when fractional durations are involved.
- Respect out-of-scope boundaries for partner models and still-image routes; re-research if a partner model is chosen.
When to use it
Use when building backend services that integrate Runway video generation/editing capabilities, require explicit paid-call governance, asynchronous task handling, and secure media transfer. Applicable when you need to orchestrate generation across gen4.5, gen4_turbo, aleph2, and act_two models and enforce governance policies.
What it can touch
- Base URL: https://api.dev.runwayml.com
- Authorization header: Bearer $RUNWAYML_API_SECRET
- X-Runway-Version: 2024-11-06
- Content-Type: application/json
- Input media via HTTPS URLs, data URIs, or runway:// ephemeral uploads
- Output media: signed URLs with strict handling instructions
- Pricing calculations based on requested_output_seconds and model type
Caveats
- Explicit consent, rights, and provenance planning required before design and execution.
- The policy requires a paid-approval workflow with exact envelope digests; any change invalidates approval.
- Documentation notes that some ratios and inputs may be model-version dependent; treat ambiguous values as unresolved and recheck live references.
- Partner models exist with different schemas and terms; switching to a partner model requires re-research and new approvals.
- Outputs are time-limited and should be stored in durable storage; do not expose as product URLs.
- There is no general requests-per-minute cap documented; implement your own queue and budgets.
# Runway Video Use this skill for server-side integrations with the documented Runway Developer API at `https://api.dev.runwayml.com`. It covers Runway-native video models and makes partner models, still-image generation, the consumer web app, Recipes, Workflows, Characters, and third-party gateways explicit out-of-scope branches. Research cutoff: **2026-07-10**. ## Evidence language Interpret sta
What does the runway-video skill do?
Build and operate production-safe Runway API video generation, video editing, and character-performance workflows with native Runway models, explicit paid-call approval, duplicate-create protection, asynchronous task handling, secure media transfer, and evidence-aware governance.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill runway-video --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.