Backlog Refinement

Convert raw user input into structured backlog beans with defined scope and criteria.

1|Updated Feb 7, 2026
One-click install
npx skills add https://github.com/beekeeper-lab/foundry --skill backlog-refinement
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Backlog Refinement
Source: https://github.com/beekeeper-lab/foundry/tree/main/.claude/skills/backlog-refinement
Command: npx skills add https://github.com/beekeeper-lab/foundry --skill backlog-refinement

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Turns raw ideas, feature descriptions, or broad vision text into one or more well-formed beans through an iterative dialogue. The Team Lead analyzes the input to identify distinct units of work, asks clarifying questions to understand scope and priority, then creates properly-formed beans using /new-bean. This is the primary intake mechanism for getting new work into the backlog.

Core Features & Use Cases

  • Iterative clarification to define beans from vague inputs.
  • Reads the existing backlog at ai/beans/_index.md to understand existing work, priorities, and next IDs.
  • Drafts working titles, one-line descriptions, priority estimates, and dependencies for each identified work unit.
  • Creates and links beans via the /new-bean process, updating the backlog index immediately.
  • Maintains clear scope and acceptance criteria for each bean, enabling traceable delivery.

Quick Start

Feed me raw backlog ideas and I will convert them into structured backlog beans.

Frequently Asked Questions about Backlog Refinement

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn raw feature ideas into structured backlog items?

Backlog refinement transforms raw ideas into structured backlog beans by analyzing input to identify distinct work units and drafting clear proposals with well-defined scope, priority, and acceptance criteria.

What is the best way to define scope and priority for vague product backlog items?

Defining scope and priority for vague items uses iterative clarification, asking targeted questions to understand the work, then drafting working titles, descriptions, priority estimates, and dependencies for each unit.

Can I use this to update an existing backlog index with new work units?

Yes, it reads the existing backlog index to understand current work and next IDs, then creates and links new beans via the /new-bean process, updating the backlog index immediately as each bean is created.

Does backlog refinement work for broad vision text that contains multiple work units?

Yes, it analyzes broad vision text to identify multiple distinct units of work, drafting proposals for each and iterating through clarifying questions until all beans have clear scope and acceptance criteria.

How are dependencies recorded during the backlog refinement process?

Dependencies are recorded during the proposal drafting phase, ensuring each newly created bean maintains traceable delivery links and proper prioritization within the existing backlog structure.