技能列表

Generate conversion-focused TikTok comment replies that turn questions and objections into safe next-step actions without sounding spammy. Use when the user needs sales replies for TikTok comments, wants structured reply scripts by intent, or needs comment-to-DM/cart conversion sequences for TikTok Shop.

Package, publish, and distribute OpenClaw skills to GitHub and ClawHub. Activate when user wants to: (1) package a skill folder for distribution, (2) push a skill to a GitHub repo, (3) publish a skill to ClawHub registry, (4) sync a skill across GitHub and ClawHub. NOT for: creating skill content, writing SKILL.md, or installing skills.

镜像网站到本地的完整工作流。当用户说镜像网站、下载网站、抓取网站、本地化网站，或者提供一个网址和保存路径时，必须使用此 skill。输入格式为：镜像网站 www.example.com 保存地址 /a/b/c。自动处理代理、递归下载、文件名清理等全流程。即使用户只是提到想把某个网站保存到本地、离线浏览、克隆站点，也应触发此 skill。

Triage tenant maintenance requests by severity, assign priority, identify the right contractor type, estimate costs, and generate work orders. Use when a tenant reports a maintenance issue, when reviewing open work orders, or when assessing property condition. Follows Massachusetts habitability requirements (105 CMR 410).

中文长篇小说多智能体创作体系（12Agent）。适用于新建长篇小说项目、搭建世界观与大纲、逐章写作、自动推进与读者反馈等长流程创作任务；不适用于短篇、诗歌、散文、翻译或非小说写作。

Research platform for AI agents. Agent-to-agent knowledge collaboration with persistent memory, peer review, and identity-based discovery. Use when connecting to Exuvia for research, publishing findings, peer-reviewing others' work, or setting up a new Exuvia account. Covers registration, basin keys, repos, notebooks, whiteboards, discussions, epistemic decay, and the engagement-based identity protocol.

Use MiniMax API for image generation and text-to-speech (TTS). Supports image-01 model for images and speech-2.8-hd for voice synthesis. Install when needed.

Query China Railway 12306 for train schedules, remaining tickets, and station info. Use when user asks about train/高铁/火车 tickets, schedules, or availability within China.

Detect and rewrite AI-generated writing patterns, em dashes, rule-of-three lists, sycophantic openers, hollow buzzwords like "delve" and "landscape", and replace them with direct, human-sounding prose.

Reviews BubbleTea TUI code for proper Elm architecture, model/update/view patterns, and Lipgloss styling. Use when reviewing terminal UI code using charmbracelet/bubbletea.

Use when the user wants an actual math result, simplification, expansion, exact value, high-precision value, analytic solution, or numerical solution for algebra, calculus, linear algebra, series, asymptotics, or ODE/PDE problems.

Audit OpenClaw scheduler token usage for cron jobs, scheduled tasks, and heartbeat sessions. Use when the user wants to know which scheduled job is expensive, which cron is burning the most tokens, whether a cron or heartbeat run exceeds a token threshold or budget, why scheduler token usage is high, or to investigate unexpected token burn. Trigger explicitly on slash-style phrases like "/token_auditor" and "/schedule_auditor". Also match requests such as "audit scheduler tokens", "which cron us