runtypelabs
- 14 skills
- 0 followers
- 1 week ago last updated
- ▌ Runtype External Agents · runtypelabs bundleConnect externally executed agents (Flue, Cloudflare Agents SDK, Vercel AI SDK, LangGraph, custom loops) to Runtype traces, evals, or surfaces; not Runtype-hosted execution.
- ▌ Tool Design Composition · runtypelabs bundleCompose and expose agent toolsets: task-level operations, batching, discovery, dry runs, and versioning.
- ▌ Tool Design Security · runtypelabs bundleDesign tool identity, credential injection, authorization, tenant scope, and audit boundaries.
- ▌ Runtype Build Product · runtypelabs bundleBuild or modify Runtype-hosted AI products, agents, flows, and surfaces using current platform instructions.
- ▌ Tool Design Execution · runtypelabs bundleDesign agent tool execution: async jobs, idempotency, timeouts, transactions, and compensation.
- ▌ Tool Design Interface · runtypelabs bundleDesign agent-facing tool names, descriptions, and parameter schemas; diagnose incorrect tool selection or inputs.
- ▌ Tool Design Errors · runtypelabs bundleDesign actionable agent tool errors, ambiguity handling, retry guidance, and fallback behavior.
- ▌ Tool Design Output · runtypelabs bundleDesign agent tool results, including pagination, partial success, context size, and actionable next steps.
- ▌ Runtype Sdk Marathon · runtypelabs bundleBuild source-controlled Runtype workflows with the SDK or CLI, including Marathon tasks and playbooks.
- ▌ Runtype Admin · runtypelabs bundleInspect, debug, or manage a live Runtype account through MCP or CLI; mutate only within the requested scope.
- ▌ Runtype Persona · runtypelabs bundleEmbed, style, or debug Runtype Persona widgets and browser-side chat integrations.
- ▌ Runtype Templates · runtypelabs bundleCreate, validate, or package distributable Runtype FPO templates and their setup requirements.
- ▌ Runtype · runtypelabs bundleScope a Runtype project or set up platform access; route implementation to the relevant Runtype skill.
- ▌ Tool Design · runtypelabs bundleDesign or audit an AI agent toolset; route naming, schemas, output, errors, execution, and security to focused guides.