SkillX — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by zjunlp · Agent Tool · ★ 284

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is SkillX safe to install? View the security audit →

About SkillX

👉 SkillX 👈 SkillX: Automatically Constructing Skill Knowledge Bases for Agents 📄arXiv • 𝕏 Blog • 🤗 Huggingface -- Table of Contents 👀Overview 🔧Installation 🏃Quick Start 🎁Acknowledgement 🚩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 environm

agent-skillsagentic-aiartificial-intelligencelarge-language-modelsnatural-language-processingskillsskillx

Quick Facts

Stars284
Forks26
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score65.471586462705/100
Open Issues1
Last Updated2026-09-03
Created2026-01-09
Platformspython
Est. Tokens~15k

SkillX alternative? Top 6 similar tools

Looking for a SkillX alternative? If you're comparing SkillX with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • minecraft-mcp-server by yuniko-software · ⭐ 692

    A Minecraft MCP Server powered by Mineflayer API. It allows to control a Minecraft character in real-time, all

  • anchoring-ai by AnchoringAI · ⭐ 156

    An open-source no-code tool for teams to collaborate on building, evaluating, and hosting applications leverag

  • dialop by jlin816 · ⭐ 114

    DialOp: Decision-oriented dialogue environments for collaborative language agents

  • claude-workflow-v2 by CloudAI-X · ⭐ 1.4k

    Universal Claude Code workflow plugin with agents, skills, hooks, and commands

  • spacy-llm by explosion · ⭐ 1.4k

    🦙 Integrating LLMs into structured NLP pipelines

  • nocturne_memory by Dataojitori · ⭐ 1.3k

    A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is SkillX?

SkillX is SkillX: Automatically Constructing Skill Knowledge Bases for Agents. It is categorized as a Agent Tool with 284 GitHub stars.

What programming language is SkillX written in?

SkillX is primarily written in Python. It covers topics such as agent-skills, agentic-ai, artificial-intelligence.

How do I install or use SkillX?

You can find installation instructions and usage details in the SkillX GitHub repository at github.com/zjunlp/SkillX. The project has 284 stars and 26 forks, indicating an active community.

What license does SkillX use?

SkillX is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to SkillX?

The top alternatives to SkillX on Agent Skills Hub include minecraft-mcp-server, anchoring-ai, dialop. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools