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 probabl-ai · Claude Skill · ★ 124
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is skills safe to install? View the security audit →
Probabl Skills A set of skills to team up with you in your machine learning experimentation journey. It helps you at: organizing your workspace building your machine learning pipeline with the right libraries ensuring good methodologies evaluating and storing your results such that you can easily audit and get insights from them couple it with Skore Hub to get a comprehensive view of your experiments and their results iterate on your next experiments taking insights thanks to Skore diagnostics and your own feedback So we aim at allowing you to focus on the science, letting AI agents to take care about the implementation but guided by two important ingredients: great libraries for the maintainability and good methodologies to make experiments right. In practice, from a prompt such as: you can expect your agent to start experimenting with you. The skills are working pretty well with models such as Claude Opus and Sonnet and gives really good results with smaller models such as Q
| Stars | 124 |
| Forks | 8 |
| Language | Python |
| Category | Claude Skill |
| License | BSD-3-Clause |
| Quality Score | 69.2256070581236/100 |
| Open Issues | 44 |
| Last Updated | 2026-09-15 |
| Created | 2026-05-05 |
| Platforms | claude-code, python |
| Est. Tokens | ~14k |
Looking for a skills alternative? If you're comparing skills with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
更好用的 Markdown 排版助手｜专为微信公众号与多平台排版设计，支持富文本复制、图片生成与矢量 PDF 导出。
OpenClaw-inspired autonomous AI agent built entirely in n8n. Adaptive RAG-powered memory, Skills via MCP templ
A VSCode extension that lets you find and install Agent Skills and MCP Apps to use with GitHub Copilot, Claude
OpenSkills: Run Claude Skills Locally using any LLM
AI agent tooling for data engineering workflows.
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plug
Explore other popular claude skill tools:
skills is Data Science Skills for AI agents like Claude Code. It is categorized as a Claude Skill with 124 GitHub stars.
skills is primarily written in Python. It covers topics such as skills.
You can find installation instructions and usage details in the skills GitHub repository at github.com/probabl-ai/skills. The project has 124 stars and 8 forks, indicating an active community.
skills is released under the BSD-3-Clause license, making it free to use and modify according to the license terms.
The top alternatives to skills on Agent Skills Hub include bm.md, n8n-claw, copilot-mcp. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: