Runway Dev Characters

Organization

runwayml

runway-dev-characters

Build, modify, debug, or verify Runway Characters integrations: inspect preset or custom avatars with MCP, manage live Sessions via SDK, and connect the application UI. Use with +runway-dev. UI says Characters; MCP/API use avatars. Not for avatar video generation endpoints.

Overview

Publisher	runwayml
Repository	`skills`
Skill name	`runway-dev-characters`
Stars	68
Forks	17
Bundled files	Instructions only
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by runwayml on GitHub. Read the source before you install it.

Installation

Install the Runway Dev Characters AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/runwayml/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/runway-dev-characters .claude/skills/runway-dev-characters

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Runway Dev Characters in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Runway Dev Characters on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Runway Dev Characters is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Runway Dev — Characters

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 Characters docs linked by llms.txt. Encourage connecting Dev MCP to inspect or manage characters and knowledge documents. If the user declines or cannot connect, continue integration from current docs and an existing character ID.

Goal

Keep a Characters integration and its live Session lifecycle correct across the application's backend and UI. Verify changes end-to-end when safe.

Terminology

Dev Portal Characters = API avatars (list_avatars, get_avatar).
Character ID = avatar UUID.
live Session = realtime conversation via POST /v1/realtime_sessions.
Fallback preset when the user wants a default: influencer ({ type: 'runway-preset', presetId: 'influencer' }).

No character specified

Ask whether the user wants an existing character, a preset, or a custom character from an image. Do not branch into avatar-video generation unless requested.
For a custom character, ask the user to supply the image and use create_avatar according to its live MCP tool schema. If the user wants a default instead, use preset influencer.
Implement the Session lifecycle behind the server boundary: create once, poll NOT_READY until READY, consume connection credentials once, and return only the connection fields the client needs.
Connect the application's call UI with the current Avatar SDK, then end or cancel the Session during teardown so it does not keep running.
For end-to-end verification, connect one Session successfully and cleanly end it.

Character specified

get_avatar for status and attached knowledge document ids.
Use that character id; do not substitute another avatar.
If status is PROCESSING, poll until READY or stop on FAILED.

MCP tools

list_avatars / get_avatar — inspect custom avatars in project.
create_avatar / update_avatar / delete_avatar — manage custom characters; confirm destructive changes before applying them.
list_avatar_knowledge_documents / get_avatar_knowledge_document — inspect attached knowledge.
create_avatar_knowledge_document / update_avatar_knowledge_document / delete_avatar_knowledge_document — manage domain knowledge when requested; confirm deletion first.

Application UI

Follow the current Avatar SDK README rather than copying component APIs from memory.
In React, use @runwayml/avatars-react with its stylesheet. Keep session creation and credential consumption on the server; browser code receives only one-time connection fields.
Use the packaged call component for standard UI or the SDK hooks for a custom experience. Handle microphone permission, connecting, active, error, and ended states.
A failed connection needs a new Session because consumed credentials cannot be reused.

Knowledge

Use the MCP knowledge-document tools above for live state and CRUD. Inspect attached documents before updating them, keep content focused and structured, and do not delete knowledge without confirmation.

Docs

https://docs.dev.runwayml.com/llms.txt
Characters: https://docs.dev.runwayml.com/_llms-txt/characters.txt
Avatar SDK: https://github.com/runwayml/avatar-sdk-react

Frequently asked questions

What does the Runway Dev Characters AI skill do?

Why use Runway Dev Characters on TypingMind?

Because you install it once and use it with any model. Runway Dev Characters is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Runway Dev Characters in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/runwayml/skills/tree/main/skills/runway-dev-characters. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Runway Dev Characters?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Runway Dev Characters?

As many as you like. As long as a model supports skills, you can use Runway Dev Characters with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Runway Dev Characters AI skill free?

Yes. It is published on GitHub by runwayml under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Writing Plans

obra

CommunityPopular

Use when you have a spec or requirements for a multi-step task, before touching code

Ask Matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

Code Review

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what…

Codebase Design

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Runway Dev — Characters

Goal

Terminology

No character specified

Character specified

MCP tools

Application UI

Knowledge

Docs

Frequently asked questions

Related AI Skills

Set up your own AI workspace now