Menu
SkillsMP has collected 9 skills from zenml-io/kitaru-skills. Open a skill to review its source and details.
Showing 9 of 9 collected skills.
Interactive onboarding for new Kitaru users. Scaffolds a personalized demo flow, demonstrates crash recovery with replay, human-in-the-loop with wait(), artifact capture, and optional MCP integration. Use when a user mentions kitaru quickstart, getting…
Guide for writing Kitaru durable workflows and operational control paths. Use when creating or refactoring Kitaru flows, checkpoints, waits, logging, artifacts, tracked LLM calls, replay/resume/retry flows, KitaruClient usage, CLI commands, MCP operations,…
Replay lab for operating on existing Kitaru executions. Use when a user wants to recover a failed execution, reproduce a run, fork one replay experiment, compare replay output, debug replay divergence, replay a cohort, inspect a ReplaySubmission, or use…
Scope and validate whether an agent workflow is well-suited for Kitaru's durable execution model, then design the flow architecture — checkpoint boundaries, wait points, replay anchors, artifact strategy, operator surface, and MVP scope. Runs a structured…
Migrate existing Claude Agent SDK code to Kitaru's Claude Agent SDK adapter. Use when code mentions claude_agent_sdk, claude_agent_sdk.query, query, ClaudeAgentOptions, ClaudeSDKClient, ResultMessage, SystemMessage, session_id, resume, cwd, allowed_tools,…
Migrate existing Gemini Interactions, Google GenAI, and Antigravity managed agent code to Kitaru's Gemini Interactions adapter. Use when code mentions google.genai, genai.Client, client.interactions.create, client.interactions.get, Interaction,…
Migrate existing LangGraph and LangChain agent code to Kitaru's LangGraph adapter. Use when code mentions LangGraph, StateGraph, CompiledStateGraph, graph.invoke, graph.ainvoke, stream, astream, interrupt, Command, thread_id, checkpointer, InMemorySaver,…
Migrate existing OpenAI Agents SDK code to Kitaru's OpenAI Agents adapter. Use when code mentions agents.Agent, Runner.run, Runner.run_sync, KitaruRunner, OpenAIRunRequest, OpenAIRunResult, wait_for_approval, build_resume_request, function_tool, RunConfig,…
Migrate existing PydanticAI agent code to Kitaru's PydanticAI adapter. Use when code mentions pydantic_ai.Agent, KitaruAgent, CapturePolicy, hitl_tool, wait_for_input, kp.wrap, tools, toolsets, MCP servers, streaming, run_stream, iter, event_stream_handler,…