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 cafe3310 · Agent Tool · ★ 248
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is public-agent-skills safe to install? View the security audit →
cafe3310's Public Agent Skills 个人常用的 Agent Skill（公开部分）。通过合适的上下文工程，可以将 Agent Skill 用在几乎任何地方。 提醒 Agent Skill 可能非常个性化，很多都是用户个人最佳实践的提炼，不一定对其他人有用。 这玩意儿说穿了是提示词和代码的集合。在当下，提示词也是代码。审核你放进本地 agent 的每一个 skill 的所有文档和代码，不要被人搞啦。 任何 LLM 相关的问题基本都是公开知识，学习如何使用 LLM 或让它协同你工作的方法里，最好的就是问 LLM 自己，最智障的是花钱买课。可以先问问 Gemini / GPT「这是我看到的文档，我希望学习关于 x 的知识。交互式地教教我」。 安装 可以 clone 项目仓库并运行以下脚本： 该脚本会将 目录下的所有子目录符号链接到 。 一、创作与知识管理 这类 Skill 解决信息结构化、表达优化与知识复用问题。 适用于内容生产、研究分析及长期知识资产管理。 语音转写长文处理 / long-audio-transcript-processor 解决超长语音转写稿（如全天会议、深度访谈）无法一次性塞入上下文的难题。通过文件系统记录处理状态，支持分段校对、清洗与结构化，同时动态维护全局勘误和术语表，以确保前后文一致。最重要的是支持「断点续传」，随时中断工作而不丢失进度，是整理录音稿的重型武器。也能随语音处理满足额外的内容提炼、问答获取、角色识别等需求。 方便你蒸馏自己。 语音整理入库 / long-audio-to-obsidian 专门用于将语音转写项目的复杂文件结构（原始录音、分段脚本、说明文档）整理并合并。它采用「Agent 规划排序 + 脚本机械执行」的模式，产出适合在 Obsidian 归档的 Markdown。 聊天记录项目化 / long-chat-task-processor 把以 Markdown 标题组织的超长聊天记录转为待办、决策和里程碑文档。它严格基于文档目录结构（TOC）分段处理，确保对话上下文不丢，能自动积累人名和黑话术语。 IM 知识库整理 / im-local-kb 重型 IM 知识整理和分析技能，专注于从聊天记录中提取高价值的知识。它维护一个基于 Markdown 的本地文件系统，支持数据摄入、断档诊断和知识生成。可以处理上万行的大量群聊信息。 方便你蒸馏别人。 项目交互式学习 / project-learner 让 Agent 充当导师，在讲解项目代码或底层技术时，自动将过程记录到持久化的学习日志中。支持断点续学，让学习过程像项目开发一样有据可查。 研究报告编写 / [content-research-writer](skills/content-research-writer
| Stars | 248 |
| Forks | 30 |
| Language | JavaScript |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 61.5623898744908/100 |
| Last Updated | 2026-06-26 |
| Created | 2026-02-18 |
| Platforms | cli, gemini, node |
| Est. Tokens | ~14k |
Looking for a public-agent-skills alternative? If you're comparing public-agent-skills 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.
OpenSkills: Run Claude Skills Locally using any LLM
Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication
Nuwax Agent OS - An enterprise-grade AI Agent Development and Operation Platform - Providing a complete soluti
A local sandbox for your AI agents
Explore other popular agent tool tools:
public-agent-skills is personal agent skills for better QoL. It is categorized as a Agent Tool with 248 GitHub stars.
public-agent-skills is primarily written in JavaScript. It covers topics such as agent-skill-repository, gemini-cli, skills.
You can find installation instructions and usage details in the public-agent-skills GitHub repository at github.com/cafe3310/public-agent-skills. The project has 248 stars and 30 forks, indicating an active community.
public-agent-skills is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to public-agent-skills on Agent Skills Hub include open-skills, claude-codex-settings, agent-deck. 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: