upskill — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

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 huggingface · Codex Skill · ★ 750

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

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

About upskill

UPskill Generate and evaluate agent skills based on traces with agents. Create skills with teacher models (expensive/slow) that student models (cheap/fast) can use to perform harder tasks reliably. [!TIP] UPskill v2 - recommended default config file now runs evaluations on Hugging Face Jobs. Make sure to set your and use for job creation and result capture Quick Start Install upskill: Create a new skill Generate a skill with a teaching model and evaluate it on a student model. Benchmark a set of models against a skill. View the results later. Development checks This repo uses a CI flow inspired by with separate format, lint, typecheck, and test stages. Install dev dependencies: Run t

Quick Facts

Stars750
Forks92
LanguagePython
CategoryCodex Skill
LicenseApache-2.0
Quality Score68.0219057551843/100
Open Issues9
Last Updated2026-09-23
Created2026-01-21
Platformsclaude-code, codex, python
Est. Tokens~17k

upskill alternative? Top 6 similar tools

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

  • Claude-to-IM-skill by op7418 · ⭐ 2.9k

    Bridge Claude Code / Codex to IM platforms — chat with AI coding agents from Telegram, Discord, or Feishu/Lark

  • skillshare by runkids · ⭐ 2.7k

    📚 Sync skills across all AI CLI tools with one command and simplify team sharing. Supporting Codex, Claude Co

  • pi-skills by badlogic · ⭐ 2.5k

    Skills for pi coding agent (compatible with Claude Code and Codex CLI)

  • agent-skill-creator by FrancyJGLisboa · ⭐ 2.4k

    Build tested agent skills and govern their lifecycle through a user-defined marketplace: evidence, discovery,

  • learning-opportunities by DrCatHicks · ⭐ 2.4k

    A Claude or Codex skill for deliberate skill development during AI-assisted coding

  • nano-banana-pro-prompts-recommend-skill by YouMind-OpenLab · ⭐ 1.9k

    AI skill for OpenClaw & Claude Code — recommend from 10000+ Nano Banana Pro (Gemini) image prompts. Smart sear

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is upskill?

upskill is Generate and evaluate agent skills for code agents like Claude Code, Open Code, OpenAI Codex. It is categorized as a Codex Skill with 750 GitHub stars.

What programming language is upskill written in?

upskill is primarily written in Python.

How do I install or use upskill?

You can find installation instructions and usage details in the upskill GitHub repository at github.com/huggingface/upskill. The project has 750 stars and 92 forks, indicating an active community.

What license does upskill use?

upskill is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to upskill?

The top alternatives to upskill on Agent Skills Hub include Claude-to-IM-skill, skillshare, pi-skills. 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 Codex Skill tools