kitaru-insights SKILL.md skillA

kitaru-insights from zenml-io/kitaru-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add zenml-io/kitaru-skills/kitaru-insights@git:20261030.d38c791

Pins git:20261030.d38c791 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
zenml-io/kitaru-skills
Path
skills/kitaru-insights/SKILL.md
Versions recorded
1
Latest version
git:20261030.d38c791, committed Oct 30, 2026
Size
6,231 bytes
Repository stars
6
License
Apache-2.0

Read many recorded Kitaru sessions with the user's own coding agent and subagents, find recurring failure and success patterns that fixed counters miss, and save them as insight cards that hand off to investigation. Use when a user asks what is going wrong (or right) across an agent's sessions, wants deeper or better insights than the built-in analyzer, wants to analyze a tag, cohort, import, time window, or list of sessions, wants a deep dive with subagents, or wants to rerun or refresh…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Find insights across many sessions

Turn a set of recorded sessions into a few well-evidenced insight cards. The server's analyzer counts known signals cheaply. This skill reads whole sessions with models, so it can find behavior nobody wrote a counter for, and it can read the agent's code to suggest why.

Cards are leads, not verdicts. Every card says what was read, how sessions were picked, and how sure the finding is. A human confirms a behavior later through `kitaru-investigation`.

## Read the relevant reference

- Read [insight-method.md](references/insight-method.md) before choosing a level, sampling, grouping notes, measuring a pattern, or wording a card.
- Read [subagent-briefs.md](references/subagent-briefs.md) before fanning out to subagents or choosing their model. It holds the exact briefs and the note formats they write.
- Read [kitaru-operations.md](references/kitaru-operations.md) before any Kitaru CLI or MCP call. It lists exact commands, limits, and known gaps.
- Read [insight-contract.md](references/insight-contract.md) before drafting, checking, writing, or replacing cards.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add zenml-io/kitaru-skills/kitaru-insights@sha256:b98e064024b6ce2e

The line at the top of this page pins the label git:20261030.d38c791, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_qze6haohs7na34gk.svg)](https://markdownregistry.com/a/art_qze6haohs7na34gk)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 30, 2026.

versioncommittedcommitsizeaudit
git:20261030.d38c791 latest2026-10-30 d38c791 6,231 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (6231 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 · 6 stars · license Apache-2.0 · pushed 2026-11-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_qze6haohs7na34gk
GET https://markdownregistry.com/api/v1/resolve?ref=zenml-io/kitaru-skills/kitaru-insights
GET https://markdownregistry.com/api/v1/blob/b98e064024b6ce2e020fdd4d338bc7fd7093a78fba9a70c79e9486126f2646a6

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from zenml-io/kitaru-skills

skills-release SKILL.md 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 · 6 stars
AGENTS.md AGENTS.md file
zenml-io/kitaru-skills · AGENTS.md
git:20261030.d38c791 · audit A · 6 stars
CLAUDE.md CLAUDE.md file
zenml-io/kitaru-skills · CLAUDE.md
git:20261030.d38c791 · audit A · 6 stars
kitaru-adapter-builder SKILL.md 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 · 6 stars
kitaru-guided-tour SKILL.md 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 · 6 stars
kitaru-hosted-onboarding-tour SKILL.md 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:20261023.8030665 · audit B · 6 stars
kitaru-importer-builder SKILL.md 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:20261023.8030665 · audit A · 6 stars
kitaru-investigation SKILL.md 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:20261030.d38c791 · audit A · 6 stars
kitaru-replay-experiment SKILL.md skill
zenml-io/kitaru-skills · skills/kitaru-replay-experiment/SKILL.md · Run and interpret one safe, bounded Kitaru replay comparison against an accepted cohort and exact evaluators. Use when…
git:20260903.598f4b2 · audit A · 6 stars
kitaru-validate-evaluator SKILL.md 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 · 6 stars

Every file in zenml-io/kitaru-skills

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