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 seaworld008 · MCP Server · ★ 70
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Commonly-used-high-value-skills safe to install? View the security audit →
Commonly Used High-Value Skills 面向全球 AI 开发者与 Agent 工作流构建者的高价值 Skills 仓库，覆盖开发工程、DevOps、产品设计、运营、办公自动化、金融投资、AI 平台与安全治理等高频任务场景。当前共 16 个分类 / 304 个技能。 为什么值得收藏 一次收齐高频可复用 Skills，减少到处找 prompt、脚本和工作流的时间。 同时兼容 、、、 等多种 AI 工具使用方式。 按场景分类组织，既适合日常检索，也适合二次扩展和团队沉淀。 很多技能不只是文档，还带 、、，可以直接复用。 仓库已经具备发现新 Skill、同步上游更新、候选优选、质量校验和生成视图的自动化链路，适合持续运营而不是一次性收集。 现在支持用策略文件对白名单来源、黑名单来源、优先来源和基础门槛做统一治理，优选结果更稳定、更可控。 已提供 ，可以把仓库中的最新技能一键同步到 、 等本机技能目录，减少手工拷贝和版本漂移。 除了功能覆盖，仓库也重视安全与可信度：既有来源追踪、候选筛选与安装前风险识别能力，也内置 、、、 等安全审查类技能。 现在还内置了许可证审计与月度死链巡检： 会阻止缺失 license 元数据的外源技能进入主分支， 工作流会按月生成外链巡检报告。 也被作为一等支持对象维护：可直接使用 分类目录，并且仓库已包含 、、 等 Hermes 生态专用技能。 适合谁 AI 开发者、Agent 工作流构建者和自动化工具使用者 想把常见任务沉淀为 Skills 的个人或团队 正在使用 Co
| Stars | 70 |
| Forks | 9 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 63.055058749172/100 |
| Open Issues | 2 |
| Last Updated | 2026-09-07 |
| Created | 2026-03-04 |
| Platforms | claude-code, codex, mcp, python |
| Est. Tokens | ~20k |
Looking for a Commonly-used-high-value-skills alternative? If you're comparing Commonly-used-high-value-skills with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Battle-tested skill library for AI agents. Save 98% of API costs with ready-to-use code for crypto, PDFs, sear
The skill layer for AI agents: npm for AI Agent Skills.
An introduction to the world of AI Agents
A collection of AI agent skills for Clawdbot, Claude Code, Codex
MCP server for reusable prompt templates, multi-step workflow chains, and quality gates — compose agentic work
📜 An MCP server for conversation history search and retrieval in Claude Code
Explore other popular mcp server tools:
Commonly-used-high-value-skills is High-value AI skills repository for Codex, Claude Code, OpenClaw, agents, prompts, and automation workflows. 高价值的 AI 技能库，涵盖 Codex、Claude Code、OpenClaw、代理、提示和自动化工作流程。. It is categorized as a MCP Server with 70 GitHub stars.
Commonly-used-high-value-skills is primarily written in Python. It covers topics such as agent, agentic-workflows, ai.
You can find installation instructions and usage details in the Commonly-used-high-value-skills GitHub repository at github.com/seaworld008/Commonly-used-high-value-skills. The project has 70 stars and 9 forks, indicating an active community.
Commonly-used-high-value-skills is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to Commonly-used-high-value-skills on Agent Skills Hub include open-skills, openagentskill, oreilly-ai-agents. 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: