# Skill Tree Generator
**Your agent doesn't need every skill in context — just the ones it needs.**
Turn a flat pile of agent skills into a hierarchical **routing tree** your AI agent
walks on demand, loading only the leaves it actually needs — one for a focused task,
several in parallel when the prompt spans intents.
[](LICENSE)
[](#-status)
[](CONTRIBUTING.md)
[-success.svg)](#-how-it-works)
[](https://github.com/maipianworni/SkillTree)
**English** · [中文](README.zh.md)
Works with **Claude Code** · **Codex CLI** · **OpenCode** · **OpenClaw** · **Bitfun** · **Hermes** · and any agent that reads `AGENTS.md` (Cursor, Aider, Jules…)
---
## 😩 The problem
Skills are great — until you have a lot of them. Every `SKILL.md` your agent can see has to
be **loaded or scanned on every turn**. The more capabilities you add, the worse it gets:
- 🧠 **Context bloat** — dozens of full skill files compete for the window
- 🎯 **Worse routing** — the agent must read everything before deciding what to use
- 💸 **Higher cost & latency** — you pay for tokens you never needed this turn
```text
BEFORE — flat skills, all loaded every turn
.claude/skills/
├── web-dev/SKILL.md ┐
├── data-pipeline/SKILL.md │
├── pdf-tools/SKILL.md ├──▶ everything in context ──▶ 🧠💥 bloat
├── seo-audit/SKILL.md │
└── …20 more/SKILL.md ┘
```
## ✨ The solution
**Skill Tree Generator** restructures your skills into a tree of tiny routing files
(`ROOT.md → ROUTER.md → leaf SKILL.md`). The agent reads a small routing table first,
narrows down branch by branch, and **loads only the leaves it needs** — never the whole catalog.
```text
AFTER — a routing tree, leaves loaded on demand
.claude/skills/my-tree/
├── ROOT.md ◀── agent reads this first (a tiny routing table)
│ └─ narrows to one branch…
├── web-dev/ROUTER.md ◀── …then one sub-branch…
│ └─ frontend/SKILL.md ◀── ✅ this leaf is loaded on demand
└── data-pipeline/ROUTER.md
```
---
## 🌳 How it works
The agent follows a routing protocol before answering: read `ROOT.md`, match the intent,
descend through `ROUTER.md` files, stop at the `[LEAF NODE]`(s) it needs, and execute those —
and only those. A focused prompt lands on a single leaf; a multi-intent or cross-domain prompt
**fans out to every matched leaf** and reads them in parallel — you're never locked to one branch.
```mermaid
flowchart TD
P["💬 User prompt