AIエージェントのおすすめClaudeスキル7ページ目

自动保存、备份和恢复OpenClaw会话记忆，防止任务中断和信息丢失，支持语义搜索与项目时间线管理。

Opinionated constraints for building better interfaces with agents.

CornerStone MCP x402 skill for agents. Tools for stock predictions, backtests, bank linking, and agent/borrower scores. Payment-protected MCP tools (run_prediction, run_backtest, link_bank_account, get_agent_reputation_score, get_borrower_score, by-email variants) with x402 flow (Aptos + Base). Skill handles 402 → pay → retry. Wallet attestation for onboarding. For marketplaces where agents download and use skills autonomously.

Persistent task ledger for agent coordination. Plan multi-step work, checkpoint progress across session boundaries, and coordinate across multiple agents wit...

Create and send interactive cards to Feishu (Lark) with buttons, forms, polls, and rich UI elements. Use when replying to Feishu messages and there is ANY uncertainty - send an interactive card instead of plain text to let users choose via buttons. Automatically handles callbacks via long-polling connection. Use for confirmations, choices, forms, todos, polls, or any scenario requiring user interaction in Feishu.

Automate Canva tasks via Rube MCP (Composio): designs, exports, folders, brand templates, autofill. Always search tools first for current schemas.

Best practices for AI agents - Cursor, Claude, ChatGPT, Copilot. Avoid common mistakes. Confirms before executing, drafts before publishing. Vibe-coding essential.

Manage and optimize OpenClaw context window usage via partitioning, pre-compression checkpointing, and information lifecycle management. Use when the session context is near its limit (>80%), when the agent experiences "memory loss" after compaction, or when aiming to reduce token costs and latency for long-running tasks.

使用百度地图Web服务API进行地点搜索、天气查询、路线规划和地理编码。

Make AI-powered phone calls with custom personas and goals. Uses OpenAI Realtime API + Twilio for ultra-low latency voice conversations. Supports DTMF/IVR na...

Nano (XNO) cryptocurrency wallet operations, transaction analysis, and explorer lookups. Use for send/receive, balances, pending funds, address validation, unit conversion, tx/hash/account lookup, explorer links, and Nano block-lattice questions. Prefer xno-mcp first; use xno-skills CLI as fallback. Configured OWS wallets ARE the assistant's own wallets — never claim you cannot receive or hold Nano.

General-purpose orchestration for Codex. Uses update_plan plus background PTY terminals to run parallel codex exec workers.

Top-level Windows computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules,...

Universal web access skill: search, fetch, browser automation via CDP Proxy. Handles login-required sites, anti-scraping bypasses, and complex web interactions.

Run the Model Context Protocol (MCP) Atlassian server in Docker, enabling integration with Jira, Confluence, and other Atlassian products. Use when you need to query Jira issues, search Confluence, or interact with Atlassian services programmatically. Requires Docker and valid Jira API credentials.

USDC wallet capabilities for OpenClaw agents via Circle Developer-Controlled Wallets

A curated collection of 2409+ best OpenClaw skills — AI tools, productivity, marketing, frontend, mobile, backend, DevOps and more. Weekly updated by MyClaw....

Agent-to-agent messaging with cryptographic signing and encryption. Send structured messages through the ClawHub relay.

Agent Community认知治理协议公开受信声明v3.3.1。行业贡献定位(规范驱动:action-ref.md源自A2A草案/标准贡献:CTEF §3.8第9个验证实现/生态共建:三方交叉验证核心参与方)+PFG临界积蓄状态(商业维度最强驱动力)+微软AGT合并+UUMit叙事。

通过已登录的Edge或Chrome浏览器，利用Chrome DevTools Protocol执行JS渲染页面的导航、点击、截图及数据提取等自动化操作。

Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee...

Capture durable lessons from debugging, user corrections, missing capabilities, and repeated workflow friction so future sessions avoid the same mistakes. Us...

Operate your 37Soul account programmatically — chat with the AI characters (hosts) you created and direct them to post, all through your agent. Use when the...

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Manage Clawdbot agents: discover, profile, track capabilities, define routing hierarchy, and assign tasks. Use when: (1) Listing available agents, (2) Profiling agent capabilities and communication methods, (3) Defining agent routing (can_assign_to, reports_to, escalation_path), (4) Assigning tasks to appropriate agents, (5) Tracking agent performance and completed work, (6) Updating agent registry after changes.

Get a FREE email address "[email protected]" - Email for AI agents.

Transform any AI into a professional executive assistant with battle-tested personas and workflows. Complete templates for Google Workspace integration (Gmail, Calendar, Drive), milestone delivery system, and security guidelines.

Build automated AI workflows combining multiple models and services. Patterns: batch processing, scheduled tasks, event-driven pipelines, agent loops. Tools:...

每天获取并转发 ai345 AI 简报；用于 AI 日报订阅、AI 资讯订阅、每日 AI 简报，以及立即获取今日简报。

Windows 电脑端微信消息监控与发送 MCP，实现在微信上给指定联系人发送消息

Read, search, export, create, update, monitor, query, inspect, batch-edit, and explicitly archive Notion pages and databases. Use when the user requests Notion content or database operations and a host secret manager can supply NOTION_API_KEY.

Zero-LLM one-shot reminders (<48h) via nohup sleep + openclaw message send, operated via {baseDir}/scripts/nohup-reminder.sh.

Find work, earn money, and collaborate with other AI agents on ClawdWork - the job marketplace for AI agents

Helps craft context-aware, empathetic messages by synthesizing conversation history, emotional cues, and relationship dynamics for clear, effective communica...

通过企业微信Webhook发送文本或Markdown消息，支持@指定用户，实现消息提醒与定时通知管理。

Comprehensive deep reasoning framework that guides systematic, thorough thinking for complex tasks. Automatically applies for multi-step problems, ambiguous...

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

解决AI记忆混乱问题——"今天讲明天忘"。通过文件系统和规则流程实现持久记忆，确保新任务开始时自动回顾上下文，而不是靠"想"。核心机制：任务开始判断→读取记忆→执行→保存。适用于频繁切换话题或任务的AI协作场景。

Secure computer-to-computer networking for AI agents — gossip broadcast, direct messaging, CRDTs, group encryption. Post-quantum encrypted, NAT-traversing. Everything you need to build any decentralized application.

Setup your own "[email protected]" email here without your human -Autonomous email for AI agents.

Google Calendar: Manage calendars and events.

PROACTIVELY use whenever the user needs data outside your training set or requires a live network call — web search, URL scraping, news, social media (any platform), market prices (crypto/stocks/FX), on-chain data, e-commerce product data, business/company data, weather, travel (flights/hotels). The provider catalog is dynamic and grows over time; if unsure whether a provider exists, call find_tools first to discover it. Not needed for conceptual, code, or local-file work.

Control OpenCode directly via the Agent Client Protocol (ACP). Start sessions, send prompts, resume conversations, and manage OpenCode updates.

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured co...

Create, list, and cancel reminders and cron jobs scoped to the channel they were requested from. Use when: user says 'remind me', 'set an alarm', 'schedule a...

浏览哲学 像人一样思考，兼顾高效与适应性的完成任务。 执行任务时不会过度依赖固有印象所规划的步骤，而是带着目标进入，边看边判断，遇到阻碍就解决，发现内容不够就深入——全程围绕「我要达成什么」做决策。这个 skill 的所有行为都应遵循这个逻辑。 ① 拿到请求 — 先明确用户要做什么，定义成功标准：什么算完成了？需要获取什么信息、执行什么操作、达到什么结果？这是后续所有判断的锚点。 ② 选择起点 — 根据任务性质、平台特征、达成条件，选一个最可能直达的方式作为第一步去验证。一次成功当然最好；不成功则在③中调整。比如，需要操作页面、需要登录态、已知静态方式不可达的平台（小红书、微信公众号等）→ 直接 CDP ③ 过程校验 — 每一步的结果都是证据，不只是成功或失败的二元信号。用结果对照①的成功标准，更新你对目标的判断：路径在推进吗？结果的整体面貌（质量、相关度、量级）是否指向目标可达？发现方向错了立即调整，不在同一个方式上反复重试——搜索没命中不等于"还没找对方法"，也可能是"目标不存在"；API 报错、页面缺少预期元素、重试无改善，都是在告诉你该重新评估方向。遇到弹窗、登录墙等障碍，判断它是否真的挡住了目标：挡住了就处理，没挡住就绕过——内容可能已在页面 DOM 中，交互只是展示手段。 ④ 完成判断 — 对照定义的任务成功标准，确认任务完成后才停止，但也不要过度操作，不为了"完整"而浪费代价。

AI agent skill scaffolding CLI. Create skills for OpenClaw, Moltbot, Claude, Cursor, ChatGPT, Copilot instantly. Vibe-coding ready. MCP compatible.

Builds automation workflows from repetitive tasks. Use when user mentions "automate", "save time", "reduce manual work", or has repeated tasks.

Use when the user asks to "remember project context", review saved findings, initialize runtime memory, archive stale work, reconcile notes, or erase a subje...

Backup and restore ClawdBot configuration, skills, commands, and settings. Sync across devices, version control with git, automate backups, and migrate to new machines.