Scans and categorizes files in a directory, detects duplicates, and reorganizes them into a clear folder structure with safety features and rollback options.
Combine multiple image screenshots into a paginated A4 PDF. Intelligently handles page breaks to avoid cutting through text. Use when the user wants to combi...
LinkedIn inbox manager and conversation assistant powered by Linxa. Use this skill whenever the user mentions LinkedIn messages, LinkedIn inbox, LinkedIn con...
Token-efficient agent behavior — response sizing, context pruning, tool efficiency, and delegation
Multilingual Text-to-Speech (TTS) with intelligent Pinyin-to-Hanzi conversion. Use when the user asks to generate audio for text that contains a mix of Vietn...
Intelligent multi-model router — automatically selects the best AI model based on task type (vision, image generation, video generation, audio, reasoning, co...
获取 Amber Electric 的实时电价、预测电价及站点信息。支持获取当前价格、预测价格和站点列表。
Monitor log files in real-time. Filter noise, surface errors, summarize patterns, alert on anomalies. Makes logs readable.
Chuyển đổi văn bản đa ngôn ngữ (Việt - Hoa - Anh) thành giọng nói chuẩn xác. Tự động xử lý Pinyin và ghép nối âm thanh chất lượng cao. Yêu cầu cài đặt edge-t...
Extract text from images and scanned documents using PaddleOCR - supports 100+ languages
Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, s
Generate contextual follow-up suggestions after AI responses. Shows 3 clickable buttons (Quick, Deep Dive, Related) when user types "/followups".
基于检索增强技术，实现语义搜索、记忆优化与对话增强，显著降低 token 消耗并提升检索准确率。
多模型提供商智能体分配系统 | Multi-Provider Agent Model Assignment System
跨平台 Agent 长期记忆系统。分层上下文供给 + 温度模型 + Skill经验记忆 + 结构化存储 + 自动归档。三层存储：Markdown（人可读，QMD 可搜索）+ JSON（结构化）+ SQLite/FTS5（高性能全文搜索）。纯 Node.js 原生模块，零外部依赖。
智能收支追踪器 — 通过自然语言快速记账，自动分类，生成日/周/月报告和趋势分析。 支持中文自然语言输入("今天午饭花了35元")，数据本地JSON存储保护隐私。 适用于个人财务管理、预算追踪和消费分析场景。
Automates the backup of the OpenClaw workspace to a remote Git repository. Handles large file exclusions, validates git configuration, and performs intelligent sync with conflict resolution.
Auto-route tasks to the cheapest z.ai (GLM) model that works correctly. Three-tier progression: Flash → Standard → Plus/32B. Classify before responding. FLASH (default): factual Q&A, greetings, remind
Automatically selects the optimal AI model based on file type and task complexity, with context monitoring and RESTful API support.
--- name: clawdaddy description: The world's #1 AI-friendly domain registrar. Check availability, purchase domains with USDC or cards, configure DNS, and manage nameservers - all without CAPTCHAs or s
Personal X (Twitter) analytics — timeline engagement, mentions, follower tracking, read any tweet/thread, bookmarks, and combined briefings via X API v2. Cos...
Advanced prompt injection defense with multi-layer protection, memory integrity, and tool security wrapper. OWASP LLM Top 10 2026 compliant.
When user asks to set reminders, save quick notes, get morning briefing, draft messages, use quick reply templates, translate text, plan day, schedule tasks,...
5-layer memory architecture for OpenClaw agents. Solves context bloat, the 48h fogging problem, and rule amnesia. Works for single-agent and multi-agent setu...