zenml-io

zenml-io/kitaru-skills

Instructions file CodexOpenCode

Instructions for zenml-io/kitaru-skills, covering repository guidelines, project structure, validation commands, style and accuracy requirements.

zenml-io/kitaru-skills

Instructions file

Instructions for zenml-io/kitaru-skills, covering claude.md, what this repository distributes, editing the skill, branching and releases and local claude code testing.

zenml-io/kitaru-skills

Skill Claude CodeCodex

Build a project-local Kitaru adapter for an unsupported Python or TypeScript agent framework. Use when a user wants to record or replay framework-native agent runs in Kitaru, needs a custom adapter, has no supported Kitaru integration for their framework, or needs to assess whether public framework hooks and the…

zenml-io/kitaru-skills

Skill Claude CodeCodex

Give first-time users a short, value-first Kitaru tour with the PydanticAI returns agent example in the Kitaru repository. Use when someone has no agent or traces of their own, arrives from Kitaru onboarding, asks for a demo, tutorial, quickstart, or guided example, needs the quickstart example cloned or prepared…

zenml-io/kitaru-skills

Skill Claude CodeCodex

Build and validate a custom Kitaru trace importer when a provider, observability platform, export format, or agent framework has no suitable built-in importer. Use when a user wants to map provider traces into Kitaru sessions and nodes, join per-turn traces into longer sessions, preserve incomplete or failed trace…

zenml-io/kitaru-skills

Skill Claude CodeCodex

Guide users from their own agent code or recorded traces through Kitaru setup, session import or recording, human review, an accepted behavior, a versioned cohort, and evaluator selection, then hand one bounded change to the replay-experiment skill. Use when a user wants to connect or inspect an existing agent, import…

zenml-io/kitaru-skills

Skill Claude CodeCodex

Run and interpret one safe, bounded Kitaru replay comparison against an accepted cohort and exact evaluators. Use when a user wants to replay a cohort, test or compare a model, prompt, system prompt, parameter, agent version, or tool policy, supervise an experiment run, determine whether one candidate helped, or ask…