OpenClaw AI 技能

通过 OpenClaw 的 before_tool_call 插件钩子，在执行前硬性阻止危险的 shell 命令（如 rm -rf、git push --force 等）。对安全命令完全无干扰。

使命令执行像自然语言交互一样简单，提供中文解释、安全分级和一键执行功能，提升开发效率。

[自动翻译] WHAT: Create Claude Code slash commands - reusable markdown workflows invoked with /command-name. WHEN: User wants to create, make, or add a sl

[自动翻译] Reference tool for life — covers intro, quickstart, patterns and more. Quick lookup for Tesla Commander concepts, best practices, and implement

使用机械指挥官MCP服务查询工程机械和船舶的实时数据、状态和位置信息。用于回答关于机械设备（挖掘机、装载机、自卸车、混凝土搅拌车等）、船舶（运输船、拖轮等）在施工项目中的状态、位置、工况等问题。当用户询问设备数量、位置分布、施工状态、油耗、报警等具体数据时必须使用此技能。

展示完整终端命令及其全部输出，包括正常、错误、长输出、交互和后台运行，格式清晰易读，便于理解和调试。

[自动翻译] Configure OpenClaw Feishu plugin without editing config files. Send simple commands via Feishu private chat to toggle streaming, set group repl

[自动翻译] TypeScript runtime port of Claude Code's AI agent harness for running commands, routing prompts, managing sessions, and auditing tool/command r

[自动翻译] Autonomous executor for Solo CLI — actually runs setup, calibration, teleoperation, dataset recording, policy training, and inference commands

[自动翻译] Command-line tool for macOS Sonoma that manages Apple Calendar events using EventKit with create, list, edit, and delete capabilities.

[自动翻译] Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User

论点审计 - An analytical tool that evaluates the logical structure, evidence quality, and persuasiveness of arguments. Use when user asks about 论点分析、论证评估、

[自动翻译] Evaluate and manage AI agents by scoring their loyalty and argument intensity within competitive event arenas, with config sharing and event de

[自动翻译] Multi-perspective structured debate for complex topics. Spawn parallel subagents with opposing stances, cross-inject arguments for rebuttal, th

[自动翻译] Use when evaluating grant ideas, diagnosing proposal logic, framing fundable projects, strengthening reviewer-aware arguments, or preparing to

[自动翻译] Gateway-only ACP negotiation skill with optional OpenClaw model-driven turn decisions.

[自动翻译] Professional finance research toolkit — backtesting (6 engines), factor analysis, options pricing, 68 finance skills, and 29 multi-agent swarm

[自动翻译] Scalable memory architecture with hybrid topic-based working memory and optional time-based episodic recall. Provides structured MEMORY.md rout

[自动翻译] Decision-making advisor using Tree of Thoughts for exploring options, analyzing trade-offs, and providing data-driven recommendations.

[自动翻译] Use this skill when the user wants a buyer-facing long review of a headphone, IEM, earbud, or TWS model by name. Use AskUserQuestion in option