>-

Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).

**Role**: Technical Analysis Grandmaster

🚀 **AI 驱动的公众号爆款文章生成工具**

Play Agent Mafia — an AI social deduction game (Among Us/Mafia style). Register, join games, discuss, vote, and deceive other AI agents. Spectate live at the web UI. Use when your agent wants to play mafia, social deduction, or party games with other AI agents.

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.

Play casino games on Molthouse, an AI agent casino with provably fair games. Use when an agent wants to gamble, play casino games (coinflip, dice, blackjack, slots), or interact with the Molthouse platform. Handles registration, deposits (USDC on Base), gameplay, verification, and withdrawals.

Inspect, checkpoint, rollback, and branch OpenClaw sessions with the ClawReverse plugin. Use when a user wants to recover from bad tool or file changes, restore a known-good checkpoint, inspect session lineage, create a child branch from an earlier point, or avoid re-spending tokens after a long OpenClaw run. Do not use for plain git history operations or non-OpenClaw workspaces.

getnote-knowledge-master

knowledge-precipitation

科普智创审校助手。当用户提到「科普中国热点创作」「科普工作」「热点采集与科普写作」或类似意图时激活。执行以下流程：(1) 监控 kepuchina.cn 整理热门文章与关键字；(2) 根据关键字为用户拟写科普文章；(3) 执行科学性审查与引用来源核查，防止大模型幻觉。英文名：SciChina Topic Writer & Reviewer。

> **版本：** 0.2.4（进度 checkpoint + 可靠超时补救）

> **版本：** 0.3.0（主题关联图 · 快速定位知识节点）

Use Chanjing Avatar API for lip-syncing video generation

蝉镜内容创作技能包（顶层路由）

>-

Use Chanjing AI creation APIs to submit image or video generation tasks across multiple models, inspect task status, poll async results, and explicitly download generated assets when requested.

Use Chanjing Avatar API for lip-syncing and video synthesis (including cartoon avatar)

Run this skill as a lightweight pre-check for chanjing actions. When the user asks to generate or configure chanjing credentials/keys (APP_ID/SECRET_KEY), run this skill to guide them—check if already configured; if yes, ask whether to re-apply; then open login page and let the user either run the config command or paste APP_ID/SECRET_KEY for the agent to apply.

Use Chanjing TTS API to synthesize speech from text, using user-provided voice

Use Chanjing TTS API to convert text to speech

Use Chanjing video synthesis APIs to create digital human videos from text or audio, with optional background upload, task polling, and explicit download when the user asks to save the result locally.

Run this skill before any chanjing-related action. When the user asks to generate or configure chanjing credentials/keys (AK/SK), run this skill to guide them—check if already configured; if yes, ask whether to re-apply; then open login page and let the user either run the config command or paste AK/SK for the agent to apply. ALWAYS run when user asks for chanjing credentials/keys or before any chanjing API (voice list, TTS, avatar, voice-clone).

Use Chanjing customised person APIs to create, inspect, list, poll, and delete custom digital humans from uploaded source videos.

>-

Use Chanjing text-to-digital-person APIs to create AI portrait images, turn them into talking videos, optionally run LoRA training, poll async tasks, and explicitly download generated assets when requested.

Manage off-plan real estate investments, payment milestones, group buy allocations, and ROI simulations. Use when a user needs to: (1) Track property installments (Dubai 60/40, 70/30 plans), (2) Calculate proportional ownership between investors (Binkl/Dad/Friends), (3) Manage a cash buffer pool for admin payments, (4) Generate unique sharing links for investors, (5) Simulate ROI or payment gap scenarios.

当用户提到"图生图"、"AI 画图"、"生成图片"、"画一个"等时激活。

Social presence layer for AI coding agents. See who's coding right now and share ephemeral vibes.

Execute GitHub Copilot CLI via exec for code gen, file edits, shell tasks using advanced models (Claude/GPT-5). Use when needing Copilot-powered coding/automation.

引导新用户快速了解OpenClaw龙虾的能力，学会基本用法，5-10分钟即可上手。

This skill helps you discover and install skills from the open agent skills ecosystem.

Halo博客管理技能 - 使用官方@halo-dev/api-client发布文章。支持Markdown语法自动转为HTML富文本格式。Triggers: halo, 博客, 发布文章

查询 OpenRouter 上所有免费模型并调用进行智能对话。支持 Gemma、Llama、MiniMax 等 27 个免费大模型，无需付费即可使用。

根据小红书文章内容自动生成配图。使用PIL将文章标题、副标题、内容生成在图片上，适合小红书笔记配图。

Extract medical entities (symptoms, medications, lab values, diagnoses) from patient messages.

Classify medical messages (emails, iMessages) as critical, urgent, or routine based on medical urgency indicators.

将对话中解决的问题整理成方案文档，部署到 web 服务器供用户下载

luoyonghao-perspective

Use the MemOS Local memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences or history, or when you need to answer from prior context. When auto-recall returns nothing (long or unclear user query), generate your own short search query and call memory_search. Available tools: memory_search, memory_get, memory_write_public, task_summary, skill_get, skill_search, skill_install, skill_publish, skill_unpublish, memory_timeline, memory_viewer.

自动将任务经验沉淀为 skill。当任务满足沉淀条件时触发：使用了 5+ 次 tool call、遇到错误后找到正确解法、用户纠正了方法、或发现了可复用的多步骤 workflow。完成任务后自动评估是否值得沉淀，查重已有 skill，创建新 skill 或更新已有 skill。

[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]

version: 1.0.0

Cost-effective skill selector for maximizing ROI on AI operations (增收降本版 v1.0.0). Use when the user needs to accomplish a task and wants the optimal skill chosen automatically to minimize costs while maximizing quality. Evaluates skills based on quality (35%), token cost (30%), security/reliability (20%), and speed (15%). Searches both local skills and clawhub.com, presents top recommendations for user confirmation before execution.

>

AI科研团队智能协作助手。用于：(1) 管理团队知识库和项目进度追踪 (2) 协助会议纪要整理、文献综述、实验记录 (3) 代码辅助和数据分析 (4) 按团队协议执行日/周工作循环。当团队成员在Issue、PR或即时通讯中@AI，或需要知识管理、项目进度监控、文档协作时触发。

literature-daily-report

Use when a user reports Matrix @mentions not working, notifications not triggering, asks to fix/update the mentions patch, or asks to install/apply the patch. This skill should only be used when explicitly requested.

Fortress Sovereign Edition. Highest-compliance web automation toolkit with saturated security gating (Every script is locked).

Professional Web Intelligence & Automation Toolkit. Features Protocol Phantom (TLS/JA4), Local Socket Relaying, and Hardened physical gating.