Create git commits with user approval and no Claude attribution

Claude Code CLI commands, flags, headless mode, and automation patterns

Workflow orchestrator that chains existing skills for feature development

Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging

Agentica server + Claude proxy setup - architecture, startup sequence, debugging

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

Comprehensive skill evaluation and debugging framework for testing agent skills. Use when users need to (1) evaluate...

项目运行/调试手册生成:本地启动、测试、依赖服务、环境变量/配置入口、排错 FAQ,输出可执行 Runbook。支持 OUTPUT_DIR 覆盖。 (Generate an executable runbook:...

新项目快速上手/项目勘察:梳理架构、入口、怎么跑(启动/测试)、核心流程、模块地图、依赖与待澄清问题,并输出 onboarding 文档。 (Onboarding a new repo: architecture,...

领域名词表/业务概念梳理:从代码与文档提炼业务名词、核心对象/状态、核心场景(概念层,不写 API/表结构),输出 onboarding glossary。 (Extract a concept-level domain...