Home / zenml-io / kitaru-skills · skills/kitaru-replay-experiment/SKILL.md · GitHub

kitaru-replay-experiment skillA

kitaru-replay-experiment is agent-read markdown (skill) from zenml-io/kitaru-skills: 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 for one bounded change worth testing..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Kitaru replay experiment

Test one candidate condition against known cases and explain whether the available evidence improved, regressed, traded off, or stayed inconclusive. Do not make the deployment decision.

## Core contract

- Start from an accepted behavior, exact cohort version, exact evaluator versions and parameters, and one candidate change. Suggest one bounded candidate only when asked.
- Replay starts a fresh agent task from each historical session's stored top-level inputs after applying the override. It does not restore an arbitrary checkpoint, conversation, process memory, adapter instance state, filesystem, or external world state.
- Resolve adapter support and its construction path before asking to run the experiment. A shared replay schema does not prove that an adapter supports a requested override or tool source.
- Require an explicit tool policy for every tool-using run. Omission resolves to live passthrough on the current server and is unsafe as an implicit default.
- Carry exact IDs, versions, evaluator parameters, run-spec evidence, tool policy, failures, and missing results forward.
…

Read the whole file at its exact version.

How to install

Latest version
mdr add zenml-io/kitaru-skills/kitaru-replay-experiment@git:20260903.598f4b2
Exact content
mdr add zenml-io/kitaru-skills/kitaru-replay-experiment@sha256:bb4f2c6bc6eeeaef

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_vt65qkjp5svgrhak.svg)](https://markdownregistry.com/a/art_vt65qkjp5svgrhak)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260903.598f4b2 latest2026-09-03 598f4b2 14,702 BA view · diff
git:20260902.d9aba702026-09-02 d9aba70 14,304 BA view · diff
git:20260902.1e2a1a92026-09-02 1e2a1a9 14,135 BA view · diff
git:20260825.ed9c6c32026-08-25 ed9c6c3 13,737 BA view · diff
git:20260825.9c0e2f12026-08-25 9c0e2f1 13,379 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (14702 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

zenml-io/kitaru-skills · 5 stars · license Apache-2.0 · pushed 2026-09-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vt65qkjp5svgrhak
GET https://markdownregistry.com/api/v1/resolve?ref=zenml-io/kitaru-skills/kitaru-replay-experiment
GET https://markdownregistry.com/api/v1/blob/bb4f2c6bc6eeeaef820cc9405ad9e4bdb09933c081cbf9ecd8af1217de1abd79

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from zenml-io/kitaru-skills

skills-release skill
zenml-io/kitaru-skills · .claude/skills/skills-release/SKILL.md · Use when cutting a release of the kitaru-skills repository — pushing develop to main, bumping the kitaru plugin…
git:20260821.5fabdd1 · audit A · 5 stars
AGENTS.md agents
zenml-io/kitaru-skills · AGENTS.md
git:20260921.499e730 · audit A · 5 stars
CLAUDE.md claude
zenml-io/kitaru-skills · CLAUDE.md
git:20260921.499e730 · audit A · 5 stars
kitaru-adapter-builder skill
zenml-io/kitaru-skills · skills/kitaru-adapter-builder/SKILL.md · Select a supported Kitaru adapter or build a project-local one for an unsupported Python or TypeScript agent framework…
git:20260902.d9aba70 · audit A · 5 stars
kitaru-guided-tour skill
zenml-io/kitaru-skills · skills/kitaru-guided-tour/SKILL.md · Give first-time users a short, value-first Kitaru tour with the PydanticAI returns agent example in the Kitaru…
git:20260825.cf46ae3 · audit A · 5 stars
kitaru-hosted-onboarding-tour skill
zenml-io/kitaru-skills · skills/kitaru-hosted-onboarding-tour/SKILL.md · Guide the ZenML Pro hosted Kitaru onboarding tour from preloaded traces through human review, one reusable evaluator…
git:20260901.180473c · audit B · 5 stars
kitaru-importer-builder skill
zenml-io/kitaru-skills · skills/kitaru-importer-builder/SKILL.md · Build and validate a custom Kitaru trace importer when a provider, observability platform, export format, or agent…
git:20260910.8a51df1 · audit A · 5 stars
kitaru-investigation skill
zenml-io/kitaru-skills · skills/kitaru-investigation/SKILL.md · Guide users from their own agent code or recorded traces through Kitaru setup, session import or recording, human…
git:20260921.499e730 · audit A · 5 stars
kitaru-validate-evaluator skill
zenml-io/kitaru-skills · skills/kitaru-validate-evaluator/SKILL.md · Guide a human through checking one evaluator against criterion-specific Kitaru investigation verdicts, inspecting…
git:20260921.499e730 · audit A · 5 stars

Every file in zenml-io/kitaru-skills

Browse by kind, by grade A, or by owner.