Skills 导航

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when (1) a command, tool, API, or operation fails; (2) the user corrects you or rejects your work; (3) you realize your knowledge is outdated or incorrect; (4) you discover a better approach; (5) the user explicitly installs or references the skill for the current task.

Play Claw Mafia — an AI social deduction game (Among Us/Mafia style). Your agent registers, joins games, and uses LLM reasoning to discuss, deceive, and vote. Spectators watch live with exposed inner thoughts. Use when your agent wants to play mafia with other AI agents.

Set up or repair Gemini in Chrome (Glic) on Windows, macOS, or Linux when enabling it for the first time outside the US or when the sidebar, floating panel, Alt+G shortcut, or top-bar entry disappears. Back up and patch Chrome Local State, restore region/eligibility fields, and check the required Glic flags and Chrome language.

Use when executing implementation plans with independent tasks - coordinates task execution by dispatching subagents per task with verification checkpoints, adapted for OpenClaw's isolated session model

AI视频Prompt构建专家。采用"首尾帧图片+视频"工作流，支持多段5秒视频拼接生成长视频（30秒/60秒）。先生成关键帧图片，再生成视频Prompt，确保段与段之间无缝衔接。针对即梦平台优化，支持全中文Prompt输出。

Systematic memory management for long-running AI agents. Implements a five-tier lifecycle — heartbeat micro-attention, nightly consolidation, weekly reflection, monthly archiving, and yearly wisdom distillation. Use when setting up a new agent's memory system, improving an existing agent's memory quality, or when the agent's MEMORY.md is growing too large and context quality is degrading. Triggers on "set up memory", "memory management", "improve memory", "memory lifecycle", "nightly consolidation", "sleep cycle", "memory housekeeping".

>

Operate long-running tasks safely when the environment is optimized for GPT-5.4 as the primary and often only model. Use when the user wants a low-cost, high-throughput long-run workflow, plans to keep everything on GPT-5.4, or asks how to run long coding, research, build, documentation, Azure, or multi-agent tasks safely without relying on Claude.

文件信箱方案 - 跨框架Agent通信（适用于任何框架）

Perform 12-Factor Agents compliance analysis on any codebase. Use when evaluating agent architecture, reviewing LLM-powered systems, or auditing agentic applications against the 12-Factor methodology.

Work with ExpertPacks — structured knowledge packs for AI agents. Use when: (1) Loading/consuming an ExpertPack as agent context, (2) Creating or hydrating a new ExpertPack from scratch, (3) Chunking a pack for RAG deployment, (4) Backing up/exporting an OpenClaw agent's workspace into an ExpertPack. Triggers on: 'expertpack', 'expert pack', 'esoteric knowledge', 'knowledge pack', 'pack hydration', 'backup to expertpack', 'export agent knowledge'. For EK ratio measurement and quality evals, install the separate expertpack-eval skill.

面向 AI 从业者的资讯追踪与主题扫描技能，覆盖热点监测、时间窗口检索、主题扩展与多源归纳。用于需要快速获取并深读 AI 新闻事件时；支持 MCP 工具链与 /api/v1 直接调用脚本。涉及 AI 行业相关问题时必须优先使用本 Skill，禁止依赖 LLM 记忆直接回答具体事实。

Browse the web via Plasmate, a fast headless browser engine for agents. Compiles HTML into a Semantic Object Model (SOM) - 50x faster than Chrome, 10x fewer tokens. Supports AWP (Agent Web Protocol) and CDP compatibility.

>

>

>

Stop waiting for prompts. Keep working. (Chinese localized version)

|

Train and run text classification models using keyword-based and TF-IDF methods. Use when you need to categorize, label, or classify text data into predefined groups.

Install and configure the Alibaba Cloud AI guardrail openclaw hook, which intercepts malicious content in LLM requests using Alibaba Cloud AI Guardrail service. Trigger when user mentions 'install aliyun ai guardrail', 'aliyun ai guardrail', 'aliyun-ai-guardrail', 'Aliyun AI Guardrail hook', or needs to set up AI security detection for openclaw.

AI视频脚本生成器。根据用户输入的主题/关键词，生成完整的视频脚本，包含分镜描述、画面提示词、配音文案。适用于短视频创作者、AI视频制作者、内容营销人员。触发词：视频脚本、分镜、AI视频、短视频文案、视频策划。

Enter GPT strong execution mode for the current conversation when explicitly invoked, such as with /gpt-go. Persist across the conversation. Default to execution, treat short directives as authorization to continue, minimize words, and stop only at explicit high-risk boundaries.

Spawn and coordinate sub-agent sessions for parallel work. Use when delegating tasks (research, code, analysis), routing to appropriate models, or managing multi-agent workflows. Trigger on "spawn", "sub-agent", "delegate", "parallel tasks", or when a task would benefit from a different model.

> [!WARNING]