An easy way to force agent to think again if it's statement that the "Job is done and production ready" is actually done - usually it's not. Thanks to this command you don't have to check after the agent if they did their job.
Lyra - a master-level AI prompt optimization specialist.
Use /ultrathink <TASK_DESCRIPTION> to launch a Coordinator Agent that directs four specialist sub-agents—Architect, Research, Coder, and Tester—to analyze, design, implement, and validate your coding task. The process breaks the task into clear steps, gathers insights, and synthesizes a cohesive solution with actionable outputs. Relevant files can be referenced ad-hoc using @ filename syntax.
Execute GitHub Actions locally using act
Manage CI/CD pipeline automation: $ARGUMENTS
A comprehensive collection of 83 specialized AI subagents for [Claude Code](https://docs.anthropic.com/en/docs/claude-code), providing domain-specific expertise across software development, infrastructure, and business operations.
**TECHNICAL GUIDANCE DISCLAIMER - CRITICAL PROTECTION:**
Expert accessibility tester specializing in WCAG compliance, inclusive design, and universal access. Masters screen reader compatibility, keyboard navigation, and assistive technology integration with focus on creating barrier-free digital experiences.
**CRITICAL LEGAL DISCLAIMER - READ FIRST:**
Expert agent organizer specializing in multi-agent orchestration, team assembly, and workflow optimization. Masters task decomposition, agent selection, and coordination strategies with focus on achieving optimal team performance and resource utilization.
Advocates for inclusive design and ensures code works for everyone, regardless of abilities
Uncompromising technical reviewer focused on correctness, maintainability, and engineering truth over comfort
Paranoid about inputs, obsessed with validation, and assumes everything will go wrong
Direct and efficient communicator who provides minimal but complete responses
Obsessed with clean, consistent, and developer-friendly API design that stands the test of time
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Runs pre-commands
Contains inline bash commands via ! syntax
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub p/lifangda-workflow-suite-cli-tool-componentsBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
一条命令就能安装精心打磨的工作流、命令、代理、MCP服务器和钩子
Claude Plugins 是一个完整的AI开发工具集,包含 1600+个文件,涵盖:
总计: 948个插件组件,99个精细化插件包
Agent Skills知识库 (独立管理,32个技术领域): ⭐⭐⭐ +148% (生态大爆发)
cli-tool/skills-library/ 目录claude plugin validate验证# 从GitHub仓库添加(推荐)
/plugin marketplace add lifangda/claude-plugins
# 从本地路径添加(适合测试)
/plugin marketplace add ./claude-plugins
# 从URL添加
/plugin marketplace add https://github.com/lifangda/claude-plugins.git
# 安装完整插件包(包含748个组件)
/plugin install claude-plugins-complete@lifangda
# 安装Anthropic官方插件包(推荐所有用户)
/plugin install claude-code-official@lifangda
# 🎯 按功能分类安装Agents
/plugin install agents-data-ai@lifangda # 数据与AI开发 (18个agents)
/plugin install agents-backend@lifangda # 后端开发 (35个agents)
/plugin install agents-frontend@lifangda # 前端开发 (22个agents)
/plugin install agents-devops@lifangda # DevOps工具 (15个agents)
/plugin install agents-security@lifangda # 安全审计 (12个agents)
/plugin install agents-testing@lifangda # 测试工具 (8个agents)
# 📦 按功能分类安装Commands
/plugin install commands-git@lifangda # Git工作流命令
/plugin install commands-testing@lifangda # 测试自动化命令
/plugin install commands-deployment@lifangda # 部署工具命令
/plugin install commands-documentation@lifangda # 文档生成命令
# 🔗 按功能分类安装MCPs
/plugin install mcps-database@lifangda # 数据库集成
/plugin install mcps-devtools@lifangda # 开发工具集成
/plugin install mcps-web@lifangda # Web服务集成
# 🪝 按功能分类安装Hooks
/plugin install hooks-git-workflow@lifangda # Git工作流钩子
/plugin install hooks-testing@lifangda # 测试钩子
/plugin install hooks-security@lifangda # 安全钩子
# 核心开发工具包
/plugin install git-workflow@lifangda # Git工作流自动化
/plugin install supabase-toolkit@lifangda # 数据库开发工具
/plugin install nextjs-vercel-pro@lifangda # 前端开发工具
/plugin install testing-suite@lifangda # 测试自动化
/plugin install security-pro@lifangda # 安全审计工具
/plugin install knowledge-wikipedia@lifangda # 知识库工具
# 社区精选插件包
/plugin install marketplace-community@lifangda # 85个社区精选插件
# 编程语言专家
/plugin install python-pro@lifangda
/plugin install javascript-pro@lifangda
/plugin install typescript-pro@lifangda
/plugin install golang-pro@lifangda
/plugin install rust-pro@lifangda
# 框架专家
/plugin install react-expert@lifangda
/plugin install vue-expert@lifangda
/plugin install nodejs-pro@lifangda
/plugin install django-pro@lifangda
# 专业领域
/plugin install ai-engineer@lifangda
/plugin install security-auditor@lifangda
/plugin install devops-engineer@lifangda
/plugin install database-admin@lifangda
# 工具和命令
/plugin install git-commit@lifangda
/plugin install code-review@lifangda
/plugin install test-runner@lifangda
/plugin install deploy-helper@lifangda
# MCP服务器
/plugin install supabase-mcp@lifangda
/plugin install github-mcp@lifangda
/plugin install wikipedia-mcp@lifangda
# 查看已安装插件
/plugin list
# 测试插件功能
/python-pro # 使用Python专家
/git-workflow # 使用Git工作流
/supabase-toolkit # 使用Supabase工具
The Claude Code knowledge system — 380+ skills, 182+ agents, 100+ commands, 40 hooks, 32 rules, and workflows.
Harness-native ECC plugin for engineering teams - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
v9.50.0 - Claude Code 2026 compatibility layer: routines manifest, SubagentStop quality/cost gate, /octo:usage report, worktree bgIsolation opt-out, Claude Agent SDK seat (Opus 4.8, 1M context), starter skills pack, /plugin browse manifest. Run /octo:setup.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.