using-git-worktrees
Use git worktrees to run parallel agent sessions on separate branches
Use git worktrees to run parallel agent sessions on separate branches
npx skills add https://github.com/obra/superpowers/tree/main/skills/using-git-worktreesUse git worktrees to run parallel agent sessions on separate branches
This repo contains 13 individual skills — each has its own dedicated page.
Structured ideation and problem decomposition frameworks
Split work across parallel subagents and coordinate their outputs
Execute a plan step-by-step with checkpoints and verification at each stage
Branch close checklist: tests, commit message, pull request, and review request
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Prepare code for review: self-review, test coverage, and pull request description
Orchestrate specialized subagents for different parts of a task
Hypothesis-driven debugging loop: observe, hypothesize, test, verify
TDD loop: write the failing test first, implement the minimal change, verify, then refactor
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Force a verification pass before any task is marked done
Write structured implementation plans before starting complex tasks
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Self-evolving AI agent framework — wraps Claude Code CLI with persistent memory, multi-profile isolation, and messaging platform integration
Reference template for structuring Claude Code projects to maximize performance. 5-layer memory architecture, self-improvement loop, skills, agents, hooks, and multi-platform workflow.
Lightweight workflow skills for agentic development
Independent second opinions for AI agent workflows.
AI-driven incident response copilot for Kubernetes. AlertManager webhook → agent pipeline (analyzer/hypothesis/critic/fix/risk) → human approval. FastAPI + Celery + LLM, k8s namespace guardrails.
这是一个面向二次复用的企业级 Agent 前后端基础脚手架。仓库采用浅层 monorepo 结构，内置： FastAPI + LangGraph + SQLAlchemy async 后端 React + TypeScript + Vite 前端控制台 Docker + Compose + Nginx 基础部署入口 面向所有 AI 助手和人类协作者的 skills/ 项目级知识目录