Skip to main content
Back to the field guide

A field guide to the /crest-okr skill

AI OKR Design with North Star Metric

Most OKRs describe activities. /crest-okr produces OKRs framed as outcomes with measurable KRs, an input metrics tree, and review cadence.

Crest · Product Strategy6 min readJanuary 7, 2026

OKRs that describe work to do are not OKRs. They are project lists with three letters in front. Real OKRs describe outcomes the team intends to produce: a metric moves, a behavior changes, a capability comes online. The KRs are measurable and ambitious. The input metrics tree shows how each KR connects to the North Star. Without this rigor, OKRs become a status meeting in disguise.

The /crest-okr skill designs the OKR framework. Objectives framed as outcomes. Key Results that are measurable, time-bound, and ambitious. Input metrics tree showing how each KR connects to the North Star. Review cadence (weekly check-in, monthly reset, quarterly retrospective).

What the framework includes

North Star metric and rationale. 3-5 Objectives framed as outcomes. 3-4 Key Results per objective, measurable and time-bound. Input metrics tree connecting KRs to the North Star. Review cadence with the questions to ask at each.

Tonone's /crest-okr skill designs OKR frameworks with outcome-framed objectives, measurable KRs, an input metrics tree, and review cadence.

Install

/crest-okr ships with the Crest agent in Tonone for Claude Code.

1. Add to marketplace

$ claude plugin marketplace add tonone-ai/tonone

2. Install Crest

$ claude plugin install crest@tonone-ai

Frequently asked questions

What does /crest-okr do?
It designs OKRs with outcome-framed objectives, measurable KRs, an input metrics tree, and review cadence.
How do I install /crest-okr?
Install Tonone for Claude Code via tonone.ai/get-started.

Pairs well with