Branch Grower — Intention Creation Skill

Parse learning intentions into structured Banyan Tree branch records with root connections.

Updated Jul 5, 2025
One-click install
npx skills add https://github.com/nsuberi/ai-prototype-hub --skill branch-grower-intention-creation-skill
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Branch Grower — Intention Creation Skill
Source: https://github.com/nsuberi/ai-prototype-hub/tree/main/prototypes/research-workspace/vault-seed/.claude/skills/branch-grower
Command: npx skills add https://github.com/nsuberi/ai-prototype-hub --skill branch-grower-intention-creation-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It converts a user’s vague learning intention into a structured, connected “branch” in the Banyan Tree, so follow-up research and progression become organized and actionable.

Core Features & Use Cases

  • Intention parsing into structured branch data: Extracts topic, scope, and depth, then creates a new branch record with a refined title and detailed description.
  • Branch discovery and relationship mapping: Finds overlapping branches and offers sub-branch, sibling-connection, or expansion options to reduce fragmentation.
  • Clarifying questions to improve precision: Asks 1–2 targeted questions to refine the intention before it writes to .tree.json.
  • Root connection with semantic matching: Automatically links the new branch to semantically related roots to anchor it in the existing knowledge graph.

Quick Start

Ask the skill to create a new learning intention branch and refine it with 1–2 clarifying questions, then write it into .tree.json and connect it to the best-matching roots.

Frequently Asked Questions about Branch Grower — Intention Creation Skill

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

FAQPage Schema
How do I structure vague learning goals into a connected knowledge graph?

Structuring vague learning goals requires parsing topic scope and asking clarifying questions to create connected knowledge graph branches. This process refines user intent into structured branch records with semantic rootConnections to reduce knowledge fragmentation.

What is the best way to manage branch overlap when adding new learning intentions?

Managing branch overlap involves running discovery checks against existing branches to identify matching topics. When overlap is found, the workflow offers sub-branch creation, sibling-connection, or expansion options to integrate the new learning intention without fragmenting the graph.

How do I create structured branch records from a learning intention?

Creating structured branch records starts by extracting the topic, scope, and depth from your stated goal. The process asks up to two targeted clarifying questions to improve precision, then writes a refined title and detailed description into a `.tree.json` file.

Does active learning branch management require manual semantic linking to existing roots?

Active learning branch management does not require manual semantic linking because the workflow automatically matches and links new branches to semantically related root ids. This anchors the new branch in the existing knowledge graph without manual rootConnection mapping.

When should I use clarifying questions in learning design workflows?

Clarifying questions should be used in learning design workflows when a user states a learning goal that lacks sufficient precision. Asking up to two targeted questions refines the intention before writing to `.tree.json`, ensuring the resulting branch record is actionable.