Agent Native

runway-dev-recipes

This skill helps agents integrate Runway recipe APIs into applications by selecting the right recipe for a use case, implementing SDK client.recipes calls…

by RunwayOfficial publisher

Identity proven by GitHub's verified organisation badge (runwayml)

Agents
Claude Code
License
MIT (permissive)
Pin
e3dffc1pinned Oct 9, 2026
Context cost
about 400 tokenswhen the skill loads
GitHub stars
72on runwayml/skills
Scripts
None found

What it does

“Choose, build, modify, debug, or verify Runway recipe integrations: match a recipe to the user's use case, follow its current contract, implement SDK client.recipes calls, and wire results into the application. Use with +runway-dev. Not for direct model endpoints or Model Routers.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill helps agents integrate Runway recipe APIs into applications by selecting the right recipe for a use case, implementing SDK client.recipes calls with proper versioning, and wiring results into application UI. It includes MCP tools for checking credit balance and inspecting tasks, and guides the agent through schema validation, SDK implementation, and verification workflows.

When to use it

  • Building application integrations with Runway recipes for specific tasks
  • Debugging or updating existing recipe integrations in user code
  • Verifying recipe SDK calls work correctly before deployment
  • Choosing between multiple Runway recipes for a use case

When not to

  • Calling Runway model endpoints or Model Routers directly
  • Working without the +runway-dev companion skill available
  • Updating application code without server-side API boundaries

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add runwayml/skills --skill runway-dev-recipes

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install runwayml/skills runway-dev-recipes@e3dffc15498e9588e7815f37b9ecf10e8bc2c902

Installs the commit we checked (e3dffc1).

Copy by hand

Download the folder at e3dffc1 and put it in .claude/skills/runway-dev-recipes for Claude Code and in .agents/skills/runway-dev-recipes for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at e3dffc1

Claude Code plugin

/plugin install runway-api@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "runway-dev-recipes" by Runway.

Source, pinned to commit e3dffc15498e9588e7815f37b9ecf10e8bc2c902:
https://github.com/runwayml/skills/tree/e3dffc15498e9588e7815f37b9ecf10e8bc2c902/skills/runway-dev-recipes

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/runway-dev-recipes/ for Claude Code and .agents/skills/runway-dev-recipes/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/runway/runway-dev-recipes

SKILL.md at the pin

---
name: runway-dev-recipes
description: "Choose, build, modify, debug, or verify Runway recipe integrations: match a recipe to the user's use case, follow its current contract, implement SDK client.recipes calls, and wire results into the application. Use with +runway-dev. Not for direct model endpoints or Model Routers."
user-invocable: true
---

# Runway Dev — Recipes

> **Companion:** Use `+runway-dev` for shared guidance when available. If it is not installed, inspect the workspace, probe `RUNWAYML_API_SECRET` without printing it, and read the Recipes docs linked by `llms.txt`. Encourage connecting Dev MCP for live project context and verification. If the user declines or cannot connect, continue integration from current docs.

## Goal

Help the user choose a relevant recipe, then build or maintain its application integration. Verify changes with one working SDK call when safe.

## MCP tools

- `get_credit_balance` — check budget before billable verification.
- `get_task` — inspect or debug an existing task, not replace SDK wait helpers in application code.

## Workflow

1. Understand the user's desired result. If no recipe is pinned or already integrated, follow `llms.txt` to compare available recipes and recommend the closest fit.
2. Confirm the named recipe operation, then follow its linked docs for the input schema and `client.recipes.{method}` mapping.
3. Pin a documented dated `version` for stable behavior. Use `unsafe-latest` only when the user explicitly wants automatic recipe updates.
4. Check `RUNWAYML_API_SECRET` when implementing the SDK call.
5. Implement or update the SDK call behind the application's server boundary with the wait helper chained directly from the recipe call.
6. If the application has a UI, wire its inputs and output, including loading and error states.
7. When verification is appropriate, submit once and present the result.

## Docs

- https://docs.dev.runwayml.com/llms.txt

From runwayml/skills at e3dffc1, shown as plain text under its license: MIT (permissive). The license text is in LICENSE.

View SKILL.md on GitHub at e3dffc1

Files

1 file, 2.0 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at e3dffc1
All 17 skills from Runway

More from Runway

  • runway-dev

    Provides foundation for building and integrating Runway Dev Platform into applications using the MCP connection for live account context and SDK for…

    Claude Code · about 1.4K tokens · pinned 7 days ago

  • runway-dev-characters

    This skill helps build and debug Runway Characters integrations by managing avatar creation, live sessions, and SDK implementation.

    Claude Code · about 850 tokens · pinned 7 days ago

  • runway-dev-model-routers

    This skill enables agents to build, modify, and debug Runway Model Routers for managing API calls across multiple models with credit caps and fallback policies.

    Claude Code · about 670 tokens · pinned 7 days ago

  • runway-dev-models

    This skill helps agents integrate Runway's generative models (text-to-video, text-to-image, etc.) into applications by selecting appropriate model endpoints…

    Claude Code · about 670 tokens · pinned 7 days ago

  • runway-dev-workflows

    This skill builds, modifies, and debugs integrations that expose Runway app workflows as API endpoints.

    Claude Code · about 340 tokens · pinned 7 days ago

  • rw-check-org-details

    This skill queries the Runway ML API to retrieve organization account details including credit balance, usage tier, rate limits, and daily generation counts…

    Claude Code · about 1.2K tokens · pinned 7 days ago

All AI and agents skills
  • -21risk-automation

    This skill automates 21risk operations by connecting to the 21risk toolkit through Composio's Rube MCP server.

    by ComposioOfficial publisher

    Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 7 days ago

  • -2chat-automation

    This skill automates 2chat tasks by integrating with Composio's 2chat toolkit through Rube MCP.

    by ComposioOfficial publisher

    Agents not labelled yet · about 680 tokens · pinned 7 days ago

  • ably-automation

    This skill automates Ably messaging platform tasks by connecting to Composio's Ably toolkit through Rube MCP.

    by ComposioOfficial publisher

    Agents not labelled yet · about 680 tokens · pinned 7 days ago

  • abstract-automation

    This skill enables agents to automate Abstract design platform operations through Composio's Abstract toolkit via Rube MCP.

    by ComposioOfficial publisher

    Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 7 days ago

  • abuselpdb-automation

    This skill automates Abuselpdb operations through Composio's toolkit via Rube MCP, enabling the agent to search for IP/domain abuse reports and manage threat…

    by ComposioOfficial publisher

    Agents not labelled yet · about 700 tokens · pinned 7 days ago

  • abyssale-automation

    This skill enables agents to automate Abyssale tasks through Composio's toolkit via Rube MCP.

    by ComposioOfficial publisher

    Claude Code, Codex, Cursor +3 · about 690 tokens · pinned 7 days ago

Open roles at Runway

No open roles at Runway on the Agent Native jobs board right now.

Browse the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use