发现最适合你需求的 AI 技能
AI's Knowledge Base CLI - Query and manage world knowledge for AI agents. Use when users want to search knowledge, add knowledge sources, or interact with the worldbook knowledge base. This is a CLI-first approach that treats AI agents as first-class citizens.
Consulta e persistência obrigatória da memória principal no PostgreSQL (Memory_openclaw + pgvector). Use quando for responder, delegar tarefas, consolidar contexto do usuário, registrar handoffs (ex.: Alfred, Prompt Improver), ou manter histórico operacional com auditoria.
调用钉钉开放平台API,支持用户搜索/详情/查询、部门管理(搜索/详情/子部门/用户列表/父部门)、机器人单聊消息发送、群聊消息发送、群内机器人列表查询、Stream模式事件推送、多会话隔离管理等核心功能。Use when needing to search DingTalk users or departments, get user/department details, send robot messages, list group bots, handle Stream mode events, or manage multi-session conversations.
Rule-based trading algorithm using Ichimoku (1H bias), Bollinger Bands, MACD, RSI(14) + 14-period smoothed MA, Fib ratios, EMA Ribbon (5,8,13,21,50), and Linear Regression. Calculates confluence score (0-7) and generates clear signals. Supports all markets. No BOS, CHOCH, SMC, ICT. Analysis only — no automatic execution.
Coach and generate Xiaohongshu (小红书/RedNote/XHS) note writing. Use when the user wants help writing XHS notes (标题/正文/标签/评论引导/封面文案), improving engagement, or turning raw points into a publish-ready note. Includes: viral 5-paragraph storytelling template, CES-style engagement optimization, title/tag formulas, and AI内容合规标注提醒. Triggers: 小红书怎么写, 小红书笔记, xhs note, rednote writing, 爆款笔记, 标题公式, 标签怎么选.
Integrate PromptDome prompt injection screening into OpenClaw. Use when setting up automatic protection against prompt injection, jailbreaks, and PII exfiltration on incoming messages. Installs two components: (1) a hook that auto-scans every incoming message before the model processes it, and (2) an agent tool (promptdome_scan) agents can call explicitly on untrusted content. Run setup.sh to configure in under 60 seconds.
Build production-ready REST APIs with contract-first design, secure auth, robust testing, and deployment runbooks.
量子科技论文追踪与速览生成。用于每日追踪量子计算、量子网络、量子纠错等领域最新论文,生成中文笔记和每日速览。触发场景:(1) 定时任务执行量子论文追踪 (2) 用户请求更新论文 (3) 补充遗漏的论文
Optimize Vercel build and deploy speed — audit checklist for new and existing projects.
>
Cross-model verification for complex tasks. Spawn a judge subagent with a different model to review plans, code, architecture, or decisions before execution. Use when working on "architecture", "system design", "complex feature", "security review", "production deployment", financial/trading systems, or when stuck after 3+ attempts. NOT for simple edits, config changes, or routine tasks.
Generate daily high-signal charisma/engagement insights with a self-improving novelty loop. Use when sending recurring tips on charisma, body language, oration, psychology, influence, persuasion, manipulation-awareness, social dynamics, or communication performance; especially for scheduled morning/night briefs with email/calendar delivery.