Extract features

Transform epics into testable features and publish a features backlog.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/Darkpunkki/v-forge --skill extract-features
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Extract features
Source: https://github.com/Darkpunkki/v-forge/tree/main/.claude/skills/feature-extractor
Command: npx skills add https://github.com/Darkpunkki/v-forge --skill extract-features

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transform epics into concrete, actionable features that can be planned, tracked, and reviewed across ideas/<IDEA_ID>/runs and the latest backlog.

Core Features & Use Cases

  • Derives cohesive features from epic backlogs while respecting concept_summary.md invariants and epic boundaries.
  • Publishes a features backlog to runs/<IDEA_ID>/runs/<RUN_ID>/outputs/features_backlog.md and mirrors it to latest/features_backlog.md for visibility and traceability.

Quick Start

Run the feature-extractor with a valid IDEA_ID to generate and publish the corresponding features backlog.

Frequently Asked Questions about Extract features

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

FAQPage Schema
How do I extract actionable features from an epic backlog?▼

To extract features from an epic backlog, provide a valid IDEA_ID to the feature-extractor. It generates a features backlog by deriving cohesive features from epics while respecting concept_summary.md invariants and epic boundaries.

What is the best way to turn product epics into measurable and testable features?▼

Turning product epics into measurable features requires mapping epic boundaries to testable outputs. This tool reads concept summaries and epics backlogs to generate and publish a structured features backlog for tracking and planning.

How do I generate a features backlog for product planning?▼

Generating a features backlog for product planning involves processing concept summaries and epics. The extractor outputs the backlog to runs/<RUN_ID>/outputs/features_backlog.md and mirrors it to latest/features_backlog.md for visibility.

Can I update the latest features backlog automatically when extracting new features?▼

You can automatically update the latest features backlog during extraction. The tool mirrors the generated features_backlog.md to the latest directory, logs provenance in run_log.md, and updates the per-idea manifest accordingly.

Do I need a specific concept summary format to derive features from epics?▼

Deriving features from epics requires a concept_summary.md file to maintain invariants. The extractor reads this summary alongside the epics backlog to ensure generated features remain cohesive and respect defined boundaries.