hot-skills
精选热门 AI Agent 技能合集,汇集社区高下载量技能于一处。
商品介绍
# Hot Skills A curated collection of 7 top-downloaded AI agent skills, bundled into a single plugin for easy installation. ## Included Skills | Skill | Description | |-------|-------------| | **find-skills** | Discover and install agent skills from the open ecosystem | | **summarize** | Summarize URLs, files, and YouTube links via the summarize CLI | | **proactive-agent** | Transform agents from task-followers into proactive partners | | **obsidian** | Work with Obsidian vaults and automate via obsidian-cli | | **humanizer** | Remove signs of AI-generated writing from text | | **self-improving** | Self-reflection, self-criticism, and self-learning memory system | | **skill-vetter** | Security-first skill vetting before installing unknown code | ## Installation Install via CodeBuddy marketplace: ``` /install hot-skills ``` ## Skill Details ### find-skills Helps users discover and install skills when they ask "how do I do X", "find a skill for X", or express interest in extending capabilities. ### summarize Fast CLI to summarize URLs, local files, and YouTube links. Requires the `summarize` CLI tool. ### proactive-agent A proactive, self-improving architecture for AI agents. Includes WAL Protocol, Working Buffer, Autonomous Crons, security hardening, and battle-tested patterns. ### obsidian Work with Obsidian vaults (plain Markdown notes) and automate via `obsidian-cli`. Requires the `obsidian-cli` tool. ### humanizer Identifies and removes signs of AI-generated text based on Wikipedia's "Signs of AI writing" guide. Covers 24 patterns including inflated symbolism, promotional language, AI vocabulary, and more. ### self-improving Agent evaluates its own work, catches mistakes, and improves permanently. Features tiered memory storage, automatic promotion/demotion, and self-reflection logging. ### skill-vetter Security-first vetting protocol for AI agent skills. Checks for red flags, permission scope, and suspicious patterns before installing any skill. ## License MIT
价格
免费
- 安装:免费
在组织开通时一次性收取;再次读取清单或下载不重复收费。
以上为公开标价。你的组织可能有协议价,以控制台显示的价格为准。
如何使用
为组织安装
开通即安装:组织固定使用开通时的版本(当前为 1.0.1),它包含的商品会一并开通。
创建凭证
客户端使用组织凭证读取;绑定到数字人后,数字人使用绑定凭证按需加载。请求中携带:
Authorization: Bearer $ZGI_MARKET_KEY读取清单与安装包
清单列出版本、文件和校验值;安装包是一个 zip 文件。
读取清单 curl "https://market-api.zgi.im/v1/market/plugins/hot-skills/manifest" \ -H "Authorization: Bearer $ZGI_MARKET_KEY"下载安装包 curl "https://market-api.zgi.im/v1/market/plugins/hot-skills/package" \ -H "Authorization: Bearer $ZGI_MARKET_KEY" \ -o hot-skills.zip读取清单和下载安装包不计入用量。下载后请用响应头中的 SHA-256 校验文件。
插件清单
- 名称
- hot-skills
- 作者
- CodeBuddy
- 说明
- 精选热门 AI Agent 技能合集,汇集社区高下载量技能于一处。
- 格式
- Claude CodeAgent Plugins(Codex 等)
- 安装包
- 附带可安装的插件包
插件包内容
- 技能
- 34
- 命令
- 0
- 智能体
- 0
- MCP 服务
- 0
- 钩子
- 0
包含的商品
安装插件时会同时为你的组织开通它包含的商品,每个商品按各自的价格和用量计费。
来源与审核
- 审核状态
- 尚未审核,内容来自上游来源
- 许可证
- MIT
审核状态是平台对上架信息的记录,不构成对上游服务质量或可用性的担保。
相关商品
- 插件插件
taskmaster
Claude Code 插件 - 基于AI的任务管理系统,提供命令、代理和 MCP 集成
- productivity
- plugin
- valuz
免费 - 插件插件
交易智能体(多角色辩论式)
基于多角色辩论方法论的系统性投资分析:技术/基本面/新闻/情绪分析 → 多空辩论 → 交易决策 → 三方风险评估,输出 BUY/SELL/HOLD 建议。数据源使用当前环境可用的金融数据 skill / 连接器。
- quant-trading
- finance
- plugin
- +1
免费 - 插件插件
algorithmic-art
使用 p5.js 创建算法艺术,支持种子随机性和交互式参数探索。适用于生成艺术、流场、粒子系统等代码艺术创作。
- design
- plugin
- valuz
免费