AI Agent 分析

amElnagdy/delegate-skills

Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself — one per implementer.

Star

1.0k

语言

JavaScript

GitHub

来源与合规提示最近同步: Aug 16, 2026

Git-Stars 是独立产品，不隶属于 GitHub 或该项目。分析可能由 AI 辅助生成，依据公开仓库元数据和 README 的短摘要。我们不镜像完整 README、文档、Issue 或社媒评论。

原始 GitHub 来源方法论编辑政策

概览

delegate-skills is a collection of Claude Code skills that let an orchestrating agent delegate coding tasks to separate coding-agent CLIs (e.g., Codex, Claude Code, Cursor) via named lanes, while keeping the human in the loop for review and commit. It provides setup, direct delegation, and safety controls like read-only modes and resume support.

安装方式

npx skills add amElnagdy/delegate-skills

解决的问题

It solves the problem of using multiple AI coding agents efficiently by organizing them into a fleet of lanes, preventing context-switching and tool fragmentation. It also addresses safety and control by ensuring the human reviews and commits all changes, and by providing read-only modes and fail-closed project configs.

可以构建什么

Developers can build workflows where different coding tasks (features, tests, UI) are automatically routed to the best-suited agent CLI, with configurable models and effort. They can delegate one-off tasks directly, resume sessions, and enforce safety gates. The ceiling includes complex multi-agent pipelines with human oversight, but it's limited to tasks that CLIs can perform in a repo.

社区反馈

正向反馈

暂时没有社区反馈。

风险关注

暂时没有记录到风险关注。

结论

This is for developers who use multiple AI coding agents and want a structured, safe way to delegate tasks while retaining control. Avoid it if you prefer a single-agent workflow or need fully autonomous execution. The trade-off is added setup complexity for better agent selection and human-in-the-loop safety.

由 Git-Stars 分析 - 8/16/2026