Skip to main content
Back to the field guide

A field guide to the /helm-plan skill

AI Product Roadmap Prioritization

Prioritization is where roadmaps fail. /helm-plan ranks the backlog with RICE/ICE/Kano, written rationale per item, and an explicit deferred list.

Helm · Head of Product7 min readJanuary 12, 2026

Product backlogs accumulate items faster than the team can ship them. Prioritization is the discipline that decides which items go now versus later, and most teams do it by intuition or by the loudest voice in the room. Both produce roadmaps that nobody can defend later when stakeholders ask why one item ranked above another.

The /helm-plan skill prioritizes the backlog with explicit scoring (RICE, ICE, or Kano depending on the team's preference), written rationale per item, an explicit list of items being deferred this cycle, and confidence levels per estimate. The artifact survives the inevitable scrutiny because every choice has reasoning.

What the prioritization includes

RICE/ICE/Kano scores per item. Written rationale for each item's position. Confidence level on each estimate (high if validated, medium if reasonable assumption, low if guess). Deferred list with reason per item. Cycle commitment (now/next/later or specific quarter).

Tonone's /helm-plan skill prioritizes product backlogs with RICE/ICE/Kano, written rationale per item, and an explicit deferred list.

Install

/helm-plan ships with the Helm agent in Tonone for Claude Code.

1. Add to marketplace

$ claude plugin marketplace add tonone-ai/tonone

2. Install Helm

$ claude plugin install helm@tonone-ai

Frequently asked questions

What does /helm-plan do?
It prioritizes a product backlog using RICE, ICE, or Kano with written rationale per item, confidence levels, and an explicit deferred list.
How is /helm-plan different from /crest-roadmap?
/helm-plan is tactical backlog prioritization. /crest-roadmap is the strategic roadmap with competitive context.
How do I install /helm-plan?
Install Tonone for Claude Code via tonone.ai/get-started.

Pairs well with