SkillsBase Agent Skill Exchange
返回目录

信任与风险

基于安装命令、仓库元数据、标签和社区互动自动推断，安装前仍建议查看仓库 README。

平台兼容

  • Claude Code Claude Code 安装命令可用
  • Codex Codex 安装命令可用
  • 通用 通用 安装命令可用

注意事项

  • 需要命令行安装 安装命令包含 CLI 操作
  • 会写入本地 skill/plugin 目录 安装路径或命令会改动本地配置目录
  • 联网请求 仓库、API、MCP 或网页数据线索存在
  • 依赖外部服务 说明中出现外部服务或 API 线索

信任信号

  • 来源已识别 https://github.com/invincible04/awesome-loop-engineering
  • Skill 结构线索 标题、标签或说明中出现 skill 结构线索
  • 最近维护 1 天前有推送

已审核来源：GitHub import reviewed by SkillsBase

详细信息

Build the system that prompts your agents. A teaching repo for loop engineering: chapters, an annotated reading list, copy-paste prompts, a runnable example, and a portable agent skill

安装

/plugin marketplace add invincible04/awesome-loop-engineering
/plugin install awesome-loop-engineering@awesome-loop-engineering

If Claude Code reports no plugin, this repo has no Claude Code plugin manifest. Use:

npx skills add invincible04/awesome-loop-engineering
来源：自动推导 根据 GitHub 仓库地址生成，安装前请确认仓库结构。

安装后重启 / 重新加载 Claude Code，技能才会生效。

相似 Skill

按任务场景、标签、兼容平台和风险线索匹配。

upskill The recursive self-improvement loop for your skills (including itself) — runs a retro after every session and turns corrections into permanent skill improvements, so skills compound instead of plateauing. 设计与前端 · Claude Code 可用 · 风险提示 SafeAgentDB Isolated databases for every AI agent branch. Build, test, and migrate in parallel. Production stays untouched. 设计与前端 · Claude Code 可用 · 风险提示 agents best practices Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design. 设计与前端 · Claude Code 可用 · 风险提示 idea to ship skills Composable Agent Skills (Claude + OpenAI Codex) for taking an idea from fuzzy → validated → sequenced build → shipped — a manual tier (ideate, deep-dive, prompt-pack) and an autonomous tier (autopilot, build-loop). 设计与前端 · Claude Code 可用 · 风险提示 skills Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms when stuck. Parallel multi-task execution, independent multi-session operation, isolated multi-account browsing. 设计与前端 · Claude Code 可用 · 风险提示 deepfork Don't fork the code. Fork the design. An agent skill that reverse-engineers any open-source repo into a clean explanation + a rebuildable clean-room blueprint — then builds YOUR version. Powered by knowledge graphs. 设计与前端 · Claude Code 可用 · 风险提示

最近动态

暂无动态记录。

讨论 · 0

暂无讨论，来做第一个分享想法的人。