OpenClaw AI 技能

Universal multi-代理 工作流 orchestration using Claude Code 多代理团队s. Use when user asks to 运行 a team 工作流, 创建 an 多代理团队, or coordinate parallel work across mu

Provides Q&A, casual chat, and simple tasks using HAIku 4.5; spawns Sonnet 4.5 or Opus 4.6 for analysis, reasoning, and complex tasks as needed.

Delegate coding tasks to Claude Code 命令行工具 via background process. Use when: building features, reviewing PRs, refactoring codebases, or iterative cod

Trigger Claude Code development tasks in observable tmux 会话s with stable 启动up, 进度 visibility, and completion callback to OpenClaw. Use when user asks

检查 how much Claude Max / Claude Pro subscription quota you have LEFT — not how much you spent. Most usage 工具s 追踪 API billing or 令牌 costs. This one ans

The complete autonomous 代理 stack for Claude Code — APEX cognitive 框架, MEMORIA persistent memory, and ARCHITECT goal execution engine — bundled into a

设置up production-grade .claude/ AI collaboration layer for projects. Use when an 代理 启动s using Claude Code for development, enters a new project directo

Delegate implementation, review, and official BMad 代理-driven 工作流s to local Claude Code. Use for: (1) substantial coding/refactoring/review work, (2) r

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rul

Launch non-blocking interactive Claude Code tasks for slash-only 插件s like ralph-loop. Use when a task needs interactive slash commands and completion

检查 Claude Max plan usage limits by launching Claude Code and 运行ning /usage. Use when the user asks about Claude plan usage, remAIning quota, rate limi

Trigger Claude Code development tasks in observable tmux 会话s with stable 启动up, 进度 visibility, and completion callback to OpenClaw. Use when user asks

Manage Claude Code 会话s with naming, 检查pointing, and 恢复 strategies

路由s OpenClaw Anthropic API calls through oauth-coder (Claude 命令行工具 with OAuth), no API key needed.

Evaluate and 验证 Claude Code rules in .claude/rules/ directories. Use for frontmatter, glob patterns, and 质量 审计s

自动识别平台，创建并启动百炼最优模型团队，自动分配角色任务，支持项目优化、修复及自定义团队管理。

Use when onboarding a 仓库 into Claude Code by creating or improving CLAUDE.md, and optionally identifying useful 技能s, hooks, and verifier 设置up.

Structured memory 系统 with 4-type classification (user/feedback/project/reference), frontmatter metadata, and automated 迁移. Based on Claude Code memory

Structured memory 系统 for OpenClaw 代理s. Provides a 4-type classification (user/feedback/project/reference), layered architecture (MEMORY.md + topics/ +

运行 coding tasks using a persistent tmux 会话 with git worktree isolation. Supports multiple coding 代理s (Claude Code, Codex, CodeBuddy, OpenCode, etc.).