Best AI Agent Claude SkillsPage 4

Security-first behavioral guidelines for cautious agent operation. Use this skill for ALL operations involving external resources, installations, credentials, or actions with external effects. Triggers on - any URL/link interaction, package installations, API key handling, sending emails/messages, social media posts, financial transactions, or any action that could expose data or have irreversible effects.

Comprehensive research framework that combines web search, content analysis, source verification, and iterative investigation to conduct in-depth research on any topic. Use when you need to perform thorough research with multiple sources, cross-validation, and structured findings.

Multi-step deployment agent for full-stack apps. Build → Test → GitHub → Cloudflare Pages with human approval at each step.

Outcome-driven scientific publishing for AI agents. Publish research papers, hypotheses, and experiments with validated artifacts, structured claims, milestone tracking, and independent replications. Claim replication bounties, submit peer reviews, and collaborate with other AI researchers.

Automatically recover working context after session compaction or when continuation is implied but context is missing. Works across Discord, Slack, Telegram,...

Dual-mode screen sharing and analysis. Model-agnostic (Gemini/Claude/Qwen3-VL).

Native Windows mouse control (move, click, drag) via user32.dll. Use when the user asks you to move the mouse, click, drag, or automate pointer actions on Windows.

Start every day focused. Get a morning briefing with overdue tasks, today's priorities, calendar overview, and context from recent meetings. Works with ai-meeting-notes to-do list. No setup. Just say 'briefing'.

使用 agent-browser CLI 进行浏览器自动化。用于签到、填表、截图、信息抓取等需要控制浏览器的任务。触发条件：(1) 用户要求自动化浏览器操作 (2) 需要签到、填表、点击按钮 (3) 需要抓取网页内容作为研究素材

通用多Agent调度系统（中文版）：将主Agent变为纯调度员，所有任务通过 sessions_spawn 委派给5个持久化子Agent。支持轮询调度、先回复再派遣协议、 sessionKey固定复用。用户可自定义调度员角色和子Agent名称/人设。

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Connect Claude to Clawdbot instantly and keep it connected 24/7. Run after setup to link your subscription, then auto-refreshes tokens forever.

Trade Polymarket weather markets using NOAA (US) and Open-Meteo (international) forecasts via Simmer API. Inspired by gopfan2's weather trading approach. Use...

QVeris is a capability discovery and tool calling engine. Use discover to find specialized API tools — real-time data, historical sequences, structured repor...

Create and manage Docker sandboxed VM environments for safe agent execution. Use when running untrusted code, exploring packages, or isolating agent workloads. Supports Claude, Codex, Copilot, Gemini, and Kiro agents with network proxy controls.

Backup agent brain (workspace) and body (state) to local folder and optionally sync to cloud via rclone.

Manage and retrieve long-term memories with LanceDB using semantic vector search, category filtering, and detailed metadata storage.

Proactive task state management. Use on EVERY task start, progress update, completion, or failure. Tracks what was requested, what's running (background proc...

Break any problem down to fundamental truths, then rebuild solutions from atoms up. Use when user says "firstp", "first principles", "from scratch", "what are we assuming", "break this down", "atomic", "fundamental truth", "physics thinking", "Elon method", "bedrock", "ground up", "core problem", "strip away", or challenges assumptions about how things are done.

Access and manage Google Calendar events with gogcli for cross-calendar agendas, keyword search, and filtered outputs avoiding unwanted calendars like holidays.

Edit and validate OpenClaw Gateway config (openclaw.json / JSON5). Use when adding/changing config keys (gateway.*, agents.*, models.*, channels.*, tools.*, skills.*, plugins.*, $include) or diagnosing openclaw doctor/config validation errors, to avoid schema mismatches that prevent the Gateway from starting or weaken security policies.

A marketplace connecting AI agents with humans who need tasks completed. Agents earn cryptocurrency (ETH or SOL) for accepted work. Supports swarm jobs where...

Agent-first AEO operating platform.

快速配置 OpenClaw 与企业微信 AI Bot 对接，实现无需公网和证书的智能助理接入和消息回复功能。

Runtime core for NEXO Desktop. Provides local memory, Deep Sleep, Evolution support-ticket mode, skills, watchdog, and MCP tools for the desktop product.

Microsoft To Do API integration with managed OAuth. Manage task lists, tasks, checklist items, and linked resources. Use this skill when users want to create...

AI-powered context management for OpenClaw sessions

Self-driving agent workflow with heartbeat-driven task execution, day/night progress reports, and long-term memory consolidation. Integrates with todo-manage...

Runs autonomous iterative AI loops for requirements, planning, or building phases using structured prompts and fresh context per iteration.

Proactive goal and task management system. Use when managing goals, breaking down projects into tasks, tracking progress, or working autonomously on objectives. Enables agents to work proactively during heartbeats, message humans with updates, and make progress without waiting for prompts.

Production-grade autonomous self-improvement system with research-backed meta-learning, safe self-modification, and continuous optimization. Based on AI safe...

Multi-agent content production system. One piece of source content becomes many formats — social posts, email, scripts, headlines, and more. Five specialized...

Send messages, reply to messages, and search message history in Discord channels using the message tool. Use when the user wants to communicate with Discord (send/reply/search messages), check Discord activity, or interact with Discord channels.

Security scanner and runtime guard for OpenClaw skills, MCP servers, and AI agent workflows. Detects prompt injection, identity hijacking, memory poisoning,...

Format and deliver rich Telegram messages with HTML formatting via direct Telegram API. Auto-invoked by the main session for substantive Telegram output — no other skills need to call it. Decision rule: If your Telegram reply is >3 lines or contains structured data (lists, stats, sections, reports), spawn this as a Haiku sub-agent to format and send. Short replies (<3 lines) go directly via OpenClaw message tool. Handles: research summaries, alerts, status updates, reports, briefings, notifications — anything with visual hierarchy.

Persistent memory toolkit for AI agents. Save context, recall with relevance scoring, consolidate insights, track decisions across sessions. Features importa...

Use Model Context Protocol servers to access external tools and data sources. Enable AI agents to discover and execute tools from configured MCP servers (legal databases, APIs, database connectors, weather services, etc.).

Local Python orchestration skill: multi-agent workflows via shared blackboard file, permission gating, token budget scripts, and persistent project context....

半自动回复微信联系人消息（置信度>85%自动发送，否则确认），或主动发送指定内容。使用方式：wechat-auto-reply "联系人名称" 或 wechat-auto-reply "联系人名称" "消息内容

Generate contextual follow-up suggestions after AI responses. Shows 3 clickable buttons (Quick, Deep Dive, Related) when user types "/followups".

AI-powered diary generation for agents - creates rich, reflective journal entries (400-600 words) with Quote Hall of Fame, Curiosity Backlog, Decision Archae...

Self-orchestrating multi-agent development workflows. You say WHAT, the AI decides HOW.

ClawdTalk — Voice calls, SMS, and AI Missions for Clawdbot

Persistent cloud task planning and execution for OpenClaw. Create hierarchical task plans that survive session resets, span multiple agents, and let users re...

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.

Audit a user's current AI tool stack. Score each tool by ROI, identify redundancies, gaps, and upgrade opportunities. Produces a structured report with score...

Program recurring or one-time tasks. User defines what to do, skill handles when.

Step-by-step guide for integrating Moonshot AI (Kimi) and Kimi Code models into Clawdbot. Use when someone asks how to add Kimi models, configure Moonshot AI, or set up Kimi for Coding in Clawdbot.

微信消息自动发送。使用 peekaboo 工具操作窗口，结合 Agent-Eye 获取实时屏幕截图进行视觉理解。触发条件：用户提到"发微信"、"给xxx发消息"、"微信自动发送"等。

The agent's wallet for EVM chain transactions and raw signing. Use this skill when users want to create a wallet, transfer tokens, swap on DEXs, interact wit...