{"results":[{"displayName":"self-improving-agent","score":0.05,"slug":"self-improving-agent","summary":"Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...\n记录经验教训、错误及修正以实现持续改进。适用场景：（1）命令或操作意外失败，（2）用户纠正Claude...","updatedAt":1775245916086,"version":"3.0.6"},{"displayName":"Find Skills","score":0.04874748262291712,"slug":"find-skills","summary":"Helps users discover and install agent skills when they ask questions like \"how do I do X\", \"find a skill for X\", \"is there a skill that can...\", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.\n当用户询问\"如何做某事\"、\"寻找某技能\"或希望扩展功能时，帮助发现并安装智能体技能。适用于寻找可安装功能的场景。","updatedAt":1775245957195,"version":"0.1.0"},{"displayName":"Summarize","score":0.04800866314564295,"slug":"summarize","summary":"Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).\n使用summarize CLI总结URL或文件（支持网页、PDF、图片、音频、YouTube）。","updatedAt":1775245916144,"version":"1.0.0"},{"displayName":"Agent Browser","score":0.04684838420397147,"slug":"agent-browser","summary":"A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.\n基于Rust的快速无头浏览器自动化CLI，支持Node.js回退，允许AI代理通过结构化命令执行页面导航、点击、输入和快照操作。","updatedAt":1775246072603,"version":"0.2.0"},{"displayName":"ontology","score":0.04663163754502411,"slug":"ontology","summary":"Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...\n类型化知识图谱，用于结构化智能体记忆与可组合技能。支持创建/查询实体（人员、项目、任务、事件、文档）及关联...","updatedAt":1775245616136,"version":"1.0.4"},{"displayName":"Self-Improving + Proactive Agent","score":0.04648126314727601,"slug":"self-improving","summary":"Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...\n自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。","updatedAt":1775245616110,"version":"1.2.16"},{"displayName":"Github","score":0.04641649208728985,"slug":"github","summary":"Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.\n使用 `gh` CLI 与 GitHub 交互，通过 `gh issue`、`gh pr`、`gh run` 和 `gh api` 管理议题、PR、CI 运行及高级查询。","updatedAt":1775245916077,"version":"1.0.0"},{"displayName":"Skill Vetter","score":0.046048672854587636,"slug":"skill-vetter","summary":"Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.\nAI智能体技能安全预审工具。安装ClawdHub、GitHub等来源技能前，检查风险信号、权限范围及可疑模式。","updatedAt":1775245916096,"version":"1.0.0"},{"displayName":"Gog","score":0.045822404185683174,"slug":"gog","summary":"Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.\nGoogle Workspace 命令行工具，支持 Gmail、日历、云端硬盘、通讯录、表格和文档。","updatedAt":1775244157777,"version":"1.0.0"},{"displayName":"Proactive Agent","score":0.045733078180018184,"slug":"proactive-agent","summary":"Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞\n将AI智能体从任务执行者升级为主动预判需求、持续优化的智能伙伴。集成WAL协议、工作缓冲区、自主定时任务及实战验证模式。Hal Stack核心组件 🦞","updatedAt":1775245967701,"version":"3.1.0"}]}