For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Dashboard
User GuideDeveloper GuidesAPI Reference
User GuideDeveloper GuidesAPI Reference
  • Getting Started
    • What is Runtype?
    • Creating your account
    • Platform keys vs. BYOK
    • Understanding the Runtype UI
    • Quickstart: Social Media Post Generator
    • Quickstart: From Agent to Chat Widget
  • Dashboard
    • What is the Dashboard?
    • Daily executions
  • Playground
    • What is the Playground?
  • Products & Surfaces
    • What are Products?
    • What are Surfaces?
    • Creating a product
    • Setting up a chat surface
    • Setting up an API surface
    • Setting up an MCP surface
    • Setting up an A2A surface
    • Setting up a Slack surface
    • MCP authentication
    • Authenticating with product API keys
    • Embedding the chat widget (script tag)
    • Embedding the chat widget (React)
    • Surface orchestration modes
    • Product views
    • Adding capabilities to a product
    • Connecting external agents
    • How A2A works
    • Connecting to MCP clients
    • Scoping API keys to capabilities
    • Auto-generated OpenAPI spec
    • Calling your API endpoints
    • Client tokens and domain restrictions
    • AI-powered theme generation
    • Widget theming and customization
    • Product versioning and status
  • Flows
    • What are Flows?
    • Creating and editing flows
    • Flow step types overview
    • Agent and flow templates
    • Using prompt steps
    • Using transform-data steps
    • Using conditional steps
    • Using fetch-url and api-call steps
    • Using record steps (upsert/retrieve)
    • Flow variables and templates
    • Flow versioning and publishing
    • Running flows in batch
    • Handling batch failures
    • Debugging flows
  • Agents
    • What are Agents?
    • Creating and configuring agents
    • Agent tools
  • Records
    • What are Records?
    • Creating and managing records
    • Using records in flows
    • Filtering and searching records
  • Tools
    • What are Tools?
    • Built-in tools
    • Creating custom tools
    • Creating external tools
    • Runtime tools
  • Evals
    • What are Evals?
    • Running an eval
    • Interpreting eval results
  • Schedules
    • What are Schedules?
    • Automating batch processing
  • Logs
    • What are Logs?
    • Working with logs
  • Integrations
    • Connecting AI model providers
    • Slack integration
    • Google Workspace integration
    • GitHub integration
    • Linear integration
    • Weaviate (vector search)
    • Firecrawl (web scraping)
    • Exa (web search)
  • Settings
    • What's in Settings?
    • Available AI models
    • What are Organizations?
    • Managing AI models
    • Managing API keys
    • Billing and plans
    • Usage data
    • Team members and permissions
    • Appearance and preferences
    • Integrations (PostHog, Weaviate, Daytona)
  • Troubleshooting & FAQ
    • FAQ
    • Rate limits and usage
    • Managing Runtype with Claude
    • Agent skills
    • Flow execution failures
    • Common errors and solutions
    • Authentication issues
Dashboard
LogoLogo
On this page
  • Install all Runtype skills
  • Install specific skills
  • Available skills
  • Target a specific agent
  • Connect the MCP server
  • Updating and removing
  • Next steps
Troubleshooting & FAQ

Agent skills

Was this page helpful?
Previous

Flow execution failures

Next
Built with

Runtype publishes official agent skills that teach Claude Code, Cursor, Codex, Copilot, Windsurf, and 30+ other coding agents how to build on Runtype. A skill is a packaged set of instructions, references, and helper scripts the agent loads on demand — once installed, your coding agent knows Runtype’s product schema, MCP tools, flow step types, and SDK conventions without you re-explaining them in every prompt.

Skills are installed via the open-source skills CLI, which auto-detects which coding agents you have installed and drops the right files in the right place.

Install all Runtype skills

Run this once from any project (or your home directory for global install):

$npx skills add runtypelabs/skills

The CLI detects your installed agents and installs every Runtype skill for each of them. That’s it — restart your coding agent and the skills are available.

Install specific skills

To pick a subset interactively:

$npx skills add runtypelabs/skills --list

To install one skill non-interactively:

$npx skills add runtypelabs/skills --skill runtype-build-product -y

Available skills

SkillWhen to use it
runtypeUmbrella onboarding and routing skill. Loads first when the agent recognizes “Runtype” and routes to the focused skill below.
runtype-build-productBuild and validate hosted Runtype products: agents, flows, tools, surfaces, records, schedules, secrets, evals.
runtype-adminOperate a live Runtype account: inspect resources, debug traces and logs, run evals, apply careful mutations.
runtype-personaEmbed, theme, and debug Persona chat widgets, fullscreen assistants, client tokens, and browser-side local tools.
runtype-templatesCreate, validate, and package distributable Runtype FPO templates with pending secrets and import readiness checks.
runtype-sdk-marathonUse the Runtype SDK, CLI, Marathon, playbooks, sandboxes, and code-first stored/upsert/virtual workflows.

Most users want all of them — install once, and the right skill activates based on what you’re asking.

Target a specific agent

The CLI auto-detects installed agents, but you can scope an install to one with the -a flag (repeatable):

$npx skills add runtypelabs/skills -a claude-code -a cursor

Supported agents include claude-code, cursor, codex, copilot, windsurf, cline, gemini, opencode, and many others. See the skills.sh agent directory for the full list and per-agent install paths.

Connect the MCP server

Skills are most useful alongside the Runtype MCP server, which lets the agent read your live workspace and create resources directly. Many skill workflows assume MCP is connected — see Managing Runtype with Claude for the Claude setup, or add it manually to any MCP-aware agent:

1{
2 "mcpServers": {
3 "runtype": {
4 "type": "url",
5 "url": "https://api.runtype.com/v1/mcp/protocol"
6 }
7 }
8}

OAuth runs on first use.

Updating and removing

$npx skills update runtypelabs/skills # pull latest versions
$npx skills list # show installed skills
$npx skills remove runtype-build-product

Next steps

  • Managing Runtype with Claude for the MCP connector setup
  • Runtype skills repository for skill source and contribution guide
  • skills.sh for the hosted skill catalog