Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
| Date | Stars |
|---|---|
| 2026-07-31 | 269 |
| 2026-08-06 | 269 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<h1 align="center"> 👉 SkillX 👈 </h1>
<b>SkillX: Automatically Constructing Skill Knowledge Bases for Agents</b>
[](https://github.com/zjunlp/SKillX)
[](https://opensource.org/licenses/MIT)
<!-- <p align="center">
<a href="https://arxiv.org/abs/2502.15589">📄arXiv</a> •
<a href="https://x.com/zxlzr/status/1894729164609208338">𝕏 Blog</a> •
<a href="https://huggingface.co/collections/zjunlp/SKillX-67f9faaaa518f2e00b17386b">🤗 Huggingface</a>
</p> -->
</div>
## Table of Contents
- 👀[Overview](#overview)
- 🔧[Installation](#installation)
- 🏃[Quick Start](#quick-start)
- 🎁[Acknowledgement](#acknowledgement)
- 🚩[Citation](#citation)
## 📖 Overview
**SkillX** is a fully automated framework that constructs a **reusable, plug-and-play skill knowledge base** for LLM agents from experience.
Instead of storing raw trajectories, workflows, or loosely structured reflections, SkillX distills agent experience into a **three-level skill hierarchy**:
- **Planning Skills** for high-level task organization
- **Functional Skills** for reusable tool-based subroutines
- **Atomic Skills** for execution-oriented tool usage patterns
Built with a strong backbone agent, SkillX produces a transferable skill library that can be directly plugged into weaker base agents and new environments. Across challenging long-horizon, user-interactive benchmarks such as **AppWorld**, **BFCL-v3**, and **τ2-Bench**, SkillX consistently improves both **task success** and **execution efficiency**.
<div align="center" style="width: 100%;">
<img src="assets/overview.png" alt="Case GIF" style="width: 100%; max-width: 100%; height: auto;">
</div>
---
## Data Formats
### Trajectory Input (JSONL)
SkillX expects trajectories in the following schema:
```json
{
"trajectory_id": "traj_001",
"task_id": "task_001",
"user_task": "How many songs are in my Spotify library?",
"task_history": [
{"role": "system", "content": "You are a helpful assistant..."},
{"role": "assistant", "content": "I'll help you count..."},
{"role": "user", "content": "Output:\n```\n{\"songs\": 150}\n```"}
],
"reward": 1.0,
"metadata": {}
}
```
## 🤖 Key Features
### Hierarchical Multi-Level Skill Design
SkillX transforms raw trajectories into a structured three-tier skill space:
- **Planning Skills** capture high-level decomposition and ordering
- **Functional Skills** represent reusable multi-step tool subroutines
- **Atomic Skills** encode practical tool usage constraints and patterns
### Fully Automated Skill KB Construction
SkillX provides an end-to-end automated pipeline that:
- rolls out agents on training tasks,
- extracts reusable skills from successful trajectories,
- consolidates and filters low-quality skills,
- and builds a reusable **plug-and-play skill knowledge base**.
### Iterative Skill Refinement
SkillX continuously improves the skill library through:
- **skill merging** for consolidating redundant behaviors,
- **quality filtering** for removing brittle or hallucinated skills,
- and **iterative updates** that add, modify, or keep skills based on execution feedback.
### Exploratory Skill Expansion
Beyond seed demonstrations, SkillX proactively discovers new skills by:
- identifying under-used and failure-prone tools,
- guiding environment exploration,
- synthesizing new tasks from exploratory trajectories,
- and expanding skill coverage beyond the original training distribution.
### Plug-and-Play Transfer Across Agents
The resulting skill library can be directly injected into different base agents, enabling **strong-to-weak transfer** without retraining the underlying model.
### Better Performance and Efficiency
SkillX consistently improves:
- **task success rate** on challenging benchmarks,
- **execution efficiency** by reducing unneExcerpt of 9,445 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8e111eeeb4d0a146, llm:Topics: agent-skills, agentic-ai, large-language-models, natural-language-processing; description: 'SkillX: Automatically Constructing Skill Knowledge Bases for Agents' — constructs skill knowledge bases for agents using LLM/NLP.
matched fp:8e111eeeb4d0a146, llm:Topics: agent-skills, agentic-ai, large-language-models, natural-language-processing; description: 'SkillX: Automatically Constructing Skill Knowledge Bases for Agents' — constructs skill knowledge bases for agents using LLM/NLP.
matched fp:8e111eeeb4d0a146, llm:Topics: agent-skills, agentic-ai, large-language-models, natural-language-processing; description: 'SkillX: Automatically Constructing Skill Knowledge Bases for Agents' — constructs skill knowledge bases for agents using LLM/NLP.