「AI 智能体」Claude 技能排行榜第 7 页

Automate George online banking (Erste Bank / Sparkasse Austria): login/logout, list accounts, and fetch transactions via Playwright.

OpenCode多智能体编排插件。当用户需要安装、配置或操作oh-my-opencode时使用，包括智能体委派、超工作模式、Prometheus规划、后台任务、分类路由、模型解析、tmux集成等功能。涵盖安装配置、所有智能体（Sisyphus、Oracle、Librarian、Explore、Atlas、Prometheus、Metis、Momus）、分类、斜杠命令、钩子、技能、MCP及故障排除。

Audit workspace structure and memory files against OpenClaw conventions. Use when asked to "review workspace", "audit files", "check structure", or during periodic self-maintenance. Helps catch drift from standard patterns.

Convert memory, conversation history, or completed tasks into publishable OpenClaw skills. Use when (1) A task or workflow should be reusable, (2) Extracting...

Send push notifications to your phone via Pushover (pushover.net). Use when you want reliable out-of-band alerts from OpenClaw: reminders, monitoring alerts, cron/heartbeat summaries, or 'notify me when X happens' workflows.

完整的智能体记忆与性能系统。提取结构化事实，构建知识图谱，生成简报。通过赛前流程、工具策略、结果压缩和行动后复盘强化执行纪律。支持外部知识摄入（ChatGPT导出等）至可搜索记忆。适用于：记忆管理、简报生成、知识整合、外部数据摄取、智能体一致性维护或跨会话执行质量提升。

面向AI智能体的集体智慧——搜索其他智能体已解决的方案，分享你的学习成果。

NousResearch Hermes Agent CLI integration. Core capabilities: - Self-improving skill system - Persistent memory (FTS5 + LLM summaries) - Sub-agent delegation...

Master the art of spawning and managing sub-agents. Write prompts that actually work, track running agents, and learn from every outcome. Part of the Hal Stack 🦞

Improve reusable agent workflows with reflective experiments, value checks, and local pattern memory.

OpenClaw 自动化配方 - 10 个实用自动化场景。适合：效率工具爱好者、自动化新手。

AI智能体的记忆与防护：语义召回、知识图谱及其衰减，以及记忆防火墙，扫描并阻止提示注入、凭证泄露和投毒。

Local retrieval-augmented generation system for AI agents using ChromaDB and sentence-transformers, supporting multi-agent shared memory and privacy controls.

PIV workflow orchestrator - Plan, Implement, Validate loop for systematic multi-phase software development. Use when building features phase-by-phase with PRPs, automated validation loops, or multi-agent orchestration. Supports PRD creation, PRP generation, codebase analysis, and iterative execution with validation.

Become an AI radio host. Register as a radio personality, create shows, book schedule slots, and publish episodes. Use when you want to host a radio show, record episodes, have multi-agent roundtable conversations, or broadcast content to listeners. Supports solo shows and collaborative sessions with other AI agents.

AI Presentation Maker — the interview-driven pitch deck generator for your OpenClaw agent. Tell it what you built, who you're presenting to, and pick an angl...

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

Conflict detection and error monitoring for AI agents. The 'something's off' detector. Part of the AI Brain series.

Autonomous Polymarket prediction market trading agent. Scans markets, evaluates probabilities with LLM, sizes positions with Kelly criterion, and executes trades via CLOB API. Use when user wants to trade on Polymarket, set up automated prediction market trading, or build a trading bot. Supports cron-based autonomous operation, P&L tracking, and budget management.

NL emotion tracking + prompt injection via OpenClaw hook

Manage installed skills lifecycle: suggest by context, track installations, check updates, and cleanup unused.

Visual AI workflow builder - ComfyUI meets n8n for LLM agents, RAG pipelines, and multimodal data flows. Local-first, open source (AGPL-3.0).

Audit codebases, infrastructure, AND agentic AI systems for security issues. Covers traditional security (dependencies, secrets, OWASP web top 10, SSL/TLS, f...

Play Texas Hold'em poker as an autonomous agent, making timely decisions and maintaining session activity via a two-worker architecture with API polling.

自动把用户粗糙的输入改写成优化、结构化的提示词，显著提升AI响应质量。发送时在前面加“p:”即可启用。

LanceDB long-term memory plugin with BM25 + vector hybrid search (RRF or linear reranking).

Explore or optionally join Crustafarianism, an AI-agent belief system centered on memory, purpose, partnership, artifacts, and growth through shedding. Use w...

代理间任务市场（发布 → 认领 → 提交 → 付费解锁结果，通过 x402）

Memory-as-a-Service for AI agents. Store and recall memories with semantic vector search. 100 free calls per wallet, then x402 micropayments. Your wallet add...

在 Skillz Market 搜索并调用付费 AI 技能，自动使用 Base 上的 USDC 支付。适用于用户寻找付费 AI 服务、使用加密货币支付调用外部技能，或集成 Skillz Market 生态系统。

利用 Mem0 为 Clawdbot 提供智能记忆层。支持语义搜索，并在对话中自动存储用户偏好、模式及上下文。

AI 自动化咨询服务 - 帮你用 AI 省时省钱。适合：中小企业、自由职业者、想提效的人。

Semantic memory system using Baidu Embedding-V1 for secure, local vector storage and retrieval in Clawdbot with SQLite persistence.

通用上下文协议（CXP）为AI智能体。v2.3.7包含最新高性能CXP引擎（编译于2026‑02‑13），修复内存遗忘、macOS二进制支持以及pfeilschnell索引功能。由@Blackknight1dev创建。

Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.

Skill that restores conversation context when users want to "continue where we left off". Reads compressed context files, extracts key information (recent operations, projects, tasks), and provides structured output to help users quickly resume their work.

使用 Nia AI 对代码仓库、文档、研究论文、HuggingFace 数据集、本地文件夹和软件包进行索引和搜索，包含Oracle 自主研究、依赖分析、上下文共享和代码顾问功能。

加密的 Clawbot 间消息，发送端到端加密信息给朋友的 Clawbot。

Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.

帮助用户发现和安装智能体技能，当用户询问如「如何做X」、「找X的技能」、「有能做...的吗」等问题时

Advanced thinking model that improves decision-making speed and accuracy. Integrates with memory system to compare and integrate previous thinking models for continuous enhancement.

参考github上的andrej-karpathy-skills修改为openclaw的可用版本 同时支持Qclaw安装使用 "模型会替你做出错误的假设，然后盲目地跟着执行，而不进行检查。它们不管理自己的困惑，不寻求澄清，不暴露不一致性，不提出权衡，在应该反对的时候也不反对。" "它们真的喜欢过度复杂化代码和 API，膨胀抽象，不清除死代码……用超过 1000 行的臃肿结构，而 100 行就足够了。" "它们有时仍然会改变/删除它们不完全理解的注释和代码，作为副作用，即使这与任务无关。" 四条核心原则解决AI幻觉问题 Think Before Coding — 别默认假设，先澄清再动手 Simplicity First — 最少代码解决问题，不搞过度抽象 Surgical Changes — 只改该改的，顺手重构是大忌 Goal-Driven Execution — 定义可验证的成功标准，循环直到达标

Persistent memory for OpenClaw agents. Store decisions, preferences, and context that survive across sessions. Build knowledge graphs that compound over time...

Use Redis effectively for caching, queues, and data structures with proper expiration and persistence.

Signed Protobuf packets over TCP for AI agent-to-agent communication. Now with MCP tools for sub-second latency! Lightweight ed25519-authenticated protocol with discovery, routing, and memory sharing.

Monitor iMessage/SMS conversations and auto-respond based on configurable rules, AI prompts, and rate-limiting conditions. Use when you need to automatically reply to specific contacts with AI-generated responses based on conversation context. Also use when the user asks to manage auto-responder settings, contacts, prompts, or view status/history.

OpenClaw代理控制记忆插件，具备置信度评分、衰减和语义搜索；代理自行决定何时存取记忆，不自动。

AI智能体的自主实验循环。在用户需要运行系统性实验（如超参数优化、寻找更好配置等）时使用。

AI智能体云端记忆。跨会话存储、搜索与召回上下文。

Linear.app CLI 用于问题追踪。可用于列出、创建、更新和搜索 Linear 问题、评论、文档、周期和项目。为 LLM 代理优化，支持 JSON 输出。