← ClaudeAtlas

runtype-sdk-marathonlisted

Use when working with the Runtype TypeScript or Python SDK, FlowBuilder, BatchBuilder, EvalBuilder, CLI commands, Marathon long-running agent tasks, playbooks, model fallback, built-in CLI tools, sandboxes, code-first stored/upsert/virtual agents or flows, local tools, hidden parameters, or source-controlled Runtype workflows.
runtypelabs/skills · ★ 1 · AI & Automation · score 68
Install: claude install-skill runtypelabs/skills
# Runtype SDK And Marathon Use this skill for code-first Runtype workflows, the CLI, and Marathon. Use `runtype-build-product` when the user is designing hosted product resources through MCP. ## SDK Guidance Fetch live docs when available: - `get_platform_documentation(topic="sdk-reference")` - `get_platform_documentation(topic="types-flow-steps")` - `get_platform_documentation(topic="types-entities")` - `get_platform_documentation(topic="flow-step-types")` Code-first modes: - Stored: create persistent agents/flows in Runtype. - Upsert on execute: code is the source of truth and overwrites the Runtype copy when run. - Virtual: definition is sent over the wire and not persisted. Default to stored or upsert for production workflows because dashboard inspection, logs, evals, and versioning are easier. Use virtual for tests, one-offs, privacy constraints, or temporary generated flows. Use local tools when execution must happen in the user's browser or server. Use hidden parameters when auth context, tenant ids, or sensitive request data must not appear in the model-visible tool schema. ## CLI Setup Install or run directly: ```bash npm install -g @runtypelabs/cli npx @runtypelabs/cli@latest <command> ``` Authenticate: ```bash runtype auth login runtype auth whoami ``` Export a key for stdio MCP or CI only when needed: ```bash export RUNTYPE_API_KEY=$(runtype auth export-key) ``` Common commands include `runtype agents list`, `runtype dispatch`, `runtype flows creat