setup-api-key
Guide users through obtaining and configuring a Runway API key
- Installs
- 47
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/runwayml/skills --skill setup-api-key- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads setup-api-key automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Setup API Key
Guide the user through obtaining a Runway API key, installing the SDK, and configuring their project for API access.
PREREQUISITE: Run
+check-compatibilityfirst to ensure the project has server-side capability.
Step 1: Create a Runway Developer Account
Direct the user to:
- Go to https://dev.runwayml.com/
- Create an organization (or use an existing one)
- Navigate to Organization Settings → API Keys
- Click Create API Key
- Copy the key immediately — it is only shown once and cannot be recovered
Important warnings to tell the user:
- Lost keys cannot be retrieved. If lost, disable the old key and create a new one.
- API keys are organization-scoped, not user-scoped.
- You must prepay for credits before the API will work. Minimum purchase is $10 (1,000 credits at $0.01/credit). Do this at https://dev.runwayml.com/ under billing.
Step 2: Install the SDK
Node.js
npm install @runwayml/sdk
Requires Node.js 18+. The SDK includes TypeScript type definitions.
Python
pip install runwayml
Requires Python 3.8+. Includes MyPy type annotations.
Step 3: Configure the Environment Variable
The SDK automatically reads the API key from the RUNWAYML_API_SECRET environment variable.
Option A: .env file (recommended for development)
Check if the project already has a .env file. If so, append to it. If not, create one.
RUNWAYML_API_SECRET=your_api_key_here
For Node.js projects: Ensure the project loads .env files:
- Next.js, Remix, Vite — built-in
.envsupport, no extra setup needed - Express/Fastify/plain Node — install
dotenv:Add to the entry point:npm install dotenvimport 'dotenv/config';
For Python projects: Ensure python-dotenv is installed if not using a framework with built-in support:
pip install python-dotenv
Add to the entry point:
from dotenv import load_dotenv
load_dotenv()
Option B: System environment variable
export RUNWAYML_API_SECRET=your_api_key_here
Option C: Pass directly to the client (not recommended)
// Node.js
const client = new RunwayML({ apiKey: 'your_api_key_here' });
# Python
client = RunwayML(api_key='your_api_key_here')
Warn the user: Never hardcode keys in source code. Use environment variables or a secrets manager.
Step 4: Update .gitignore
Ensure .env is in .gitignore to prevent accidentally committing the API key:
.env
.env.local
.env.*.local
Check the existing .gitignore and add the entry if it's missing.
Step 5: Verify the Setup
Suggest the user run a quick verification:
Node.js
import RunwayML from '@runwayml/sdk';
const client = new RunwayML();
// If no error is thrown, the API key is configured correctly
console.log('Runway SDK initialized successfully');
Python
from runwayml import RunwayML
client = RunwayML()
# If no error is thrown, the API key is configured correctly
print('Runway SDK initialized successfully')
Step 6: Confirm Credit Balance
Remind the user:
- The API requires prepaid credits to function
- Minimum purchase: $10 (1,000 credits)
- Purchase at: https://dev.runwayml.com/ → Billing
- They can check their balance via the API:
// Node.js - check organization info
const response = await fetch('https://api.dev.runwayml.com/v1/organization', {
headers: {
'Authorization': `Bearer ${process.env.RUNWAYML_API_SECRET}`,
'X-Runway-Version': '2024-11-06'
}
});
const org = await response.json();
console.log('Credits:', org.creditBalance);
Security Checklist
Before moving on, verify:
- API key is stored in an environment variable, not hardcoded
-
.envfile is in.gitignore - API calls will only happen server-side (not in browser-executed code)
- User has purchased credits
Next Steps
Once the API key is configured, the user can proceed with integration:
+integrate-video— Video generation (text-to-video, image-to-video)+integrate-image— Image generation+integrate-audio— Audio generation (TTS, sound effects, voice)+integrate-uploads— File upload for models that require image/video input
FAQ
What does the setup-api-key skill do?
Guide users through obtaining and configuring a Runway API key
How do I install setup-api-key?
Run npx skills add https://github.com/runwayml/skills --skill setup-api-key in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/setup-api-key/ (personal) or .claude/skills/setup-api-key/ (project).
Which AI agents can use setup-api-key?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is setup-api-key safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains setup-api-key?
It is published by runwayml in runwayml/skills, and it is an official skill from the maker of the technology it covers. It has 47 recorded installs.
More from runwayml/skills
runway-dev
runwayml/skills
Use whenever you build, modify, or debug an application integration with Runway Dev: inspect the app, connect Dev MCP when useful, find current API contracts, integrate through the official SDK, and keep credentials server-side. Load the matching surface skill for models, Model Routers, Characters, Recipes, or published Workflows.
runway-dev-models
runwayml/skills
Use when adding or maintaining a direct Runway Dev model endpoint in an application, including image, video, audio, or task handling. Discover current model access and constraints when needed, follow the exact endpoint contract, and integrate through the official SDK. For configured model-agnostic routing, use runway-dev-model-routers instead.
rw-generate-video
runwayml/skills
Generate videos directly using the Runway API via runnable scripts. Supports text-to-video, image-to-video, and video-to-video with seedance2, gen4.5, veo3, and more.
use-runway-api
runwayml/skills
Open the skill to read its SKILL.md instructions.
rw-generate-image
runwayml/skills
Open the skill to read its SKILL.md instructions.
rw-check-org-details
runwayml/skills
Open the skill to read its SKILL.md instructions.
Popular backend & apis skills
find-skills
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
entra-app-registration
microsoft/azure-skills
Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.
google-agents-cli-adk-code
google/agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
embedded-captions
heygen-com/hyperframes
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.
entra-agent-id
microsoft/azure-skills
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
neon
neondatabase/agent-skills
Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.