Browse agent skills by their security grade.

支持多格式数据解析与智能字段识别，自动去重补全格式统一，多源数据关联合并并生成飞书原生清洗报告。

网页变更监控器 — 通用网页监控工具。用户配置 URL 列表 → Skill 按频率检测网页变化 → 推送飞书消息。不写死任何平台，通用工具。触发词：网页监控、页面变更监控、URL监控、价格变化监控、竞品监控、网站更新提醒、库存监控、货源监控、网页变化检测、网站监控

基于AI的PDF结构化字段提取工具，支持发票、合同等多文档类型，输出Excel或JSON格式，含OCR扫描件识别。

Bank Statement Reconciler · 银行流水对账 — Upload bank statements (CSV/Excel/PDF) + orders/invoices → AI auto-matching → Reconciliation results (matched/difference...

Contract Risk Analyzer · 合同风险智能审查 — 上传合同PDF，AI自动提取关键条款并标注风险点，输出结构化风险报告（文本摘要 + 关键条款表格 + 🔴🟠🟡三级风险列表）。支持采购/销售/服务/劳动/租赁/保密协议6种合同类型。触发词：合同审查、合同风险、合同分析、合同检查、合同审核

通过IMAP读取邮箱邮件，AI智能分类并提供多语言回复建议，支持飞书实时摘要推送，提升邮件客服效率。

Batch convert files between CSV, Excel, JSON, PDF, Markdown, DOCX, HTML, and PNG formats with support for up to 10 files free.

自动解析CSV/Excel数据，基于AI生成多图表多格式专业报表，支持月报周报及多套餐权限管理。

舆情罗盘（Sentiment Compass）— AI 驱动的社交媒体舆情监测与分析工具。监控小红书、抖音、微博、微信公众号关键词提及，AI 情感分析（🟢正面 / 🟡中性 / 🔴负面），自动生成舆情报告，负面超阈值时飞书/邮件预警。触发词：舆情、舆情监测、社交媒体监控、情感分析、Brand Monitori...

品牌AI可见性监控Skill。自动搜索Kimi/讯飞星火/文心一言/智谱等AI平台，检测品牌关键词可见性，生成0-100 GEM评分，AI分析"为什么没被推荐"，支持飞书推送。

支持多格式上传，智能识别字段，去重补全格式统一，多源数据关联合并，输出飞书多维表格及质量报告。

InvoiceGuard · 发票合规管家 — AI 驱动发票查重、验真、合规报告生成工具。用于：发票上传/扫码识别、发票重复报销检测（AI 查重）、发票真伪官方验真（金税四期）、合规报告生成（财会便函〔2023〕18号）、批量发票处理。当用户提到：发票、查重、验真、报销、合规、重复报销、假发票、发票识别、OFD...

Bank Statement Reconciler · 银行流水对账 — Upload bank statements (CSV/Excel/PDF) + orders/invoices → AI auto-matching → Reconciliation results (matched/difference...

专业的睡眠健康分析系统，提供睡眠质量分析、压力评估和个性化冥想指导

基于图片分析7项皮肤参数，提供个性化护肤产品推荐和智能AI护肤咨询服务。

Provides local, science-based analysis of sleep and stress with personalized guidance in relaxation, breathing, mindfulness, and wellness habits.

Do NOT use regularly. If updating HEARTBEAT.md: one entry only, replace (never append), at most once per hour. See AGENTS.md for task board.

EPO Patent Intelligence monitors EPO patents, analyzes competitor threats, identifies tech trends, and generates strategic HTML reports for informed business...

Connects to IMAP mailboxes to classify emails by urgency, suggests multilingual replies, and pushes real-time summaries to Feishu chats.

Multi-platform Order Profit Calculator — upload order exports from any e-commerce platform or ERP, get instant profit reports by order, store, SKU, and platf...

InvoiceGuard · Invoice Compliance Guardian — AI-driven invoice deduplication, verification, and compliance report generation. Handles: invoice upload/scan re...

Clean and standardize multi-format data with AI-powered deduplication, missing value fill, format normalization, multi-source merge, and Feishu-native output.

Contract Risk Analyzer — Upload contract PDF, AI auto-extracts key clauses and annotates risk points, outputs structured risk report (summary + key terms tab...

GEO Master · Brand AI Visibility Monitor — automatically search AI platforms (Kimi/Xunfei/Zhipu/Wenxin/DeepSeek/etc.), detect brand keyword visibility, gener...

Sentiment Compass — AI-powered social media sentiment monitoring & analysis tool. Monitors Xiaohongshu, Douyin, Weibo, WeChat Official Accounts for keyword m...

Batch convert between CSV, Excel, JSON, PDF, Markdown, DOCX, HTML, PNG, and TXT formats with automatic encoding handling and usage limits by plan.

Capture web screenshots, retrieve page titles, and scrape text or HTML content from web pages using URL and optional CSS selectors.

Access a Jira workspace (omeshkshatriya.atlassian.net) using provided email and API token to list, create, and transition issues. Use when the user wants to...

Provides HTTP endpoints for scanning Git repository conflicts across multiple branches and applying AI‑suggested resolutions. Use when the dashboard needs to...

自动从对话记录挖掘高频热词和歧义词，生成热词表以提升语音识别模型的转录准确度。

探店笔记完整生产流水线。接收门店场景图→AI生成探店图 + 接收点评链接→抓取网友推荐菜图片 → 生成爆款文案 → 发布到腾讯文档。适合餐饮品牌线上运营、探店笔记批量代写场景。

本地生活探店图像处理 skill。接收门店、餐饮、商场、咖啡店等本地生活场景图，默认从预置模特 URL 配置随机选择一张作为人物参考，或由用户显式传入模特图 URL，调用 Replicate 的 gpt-image-2 做图像编辑，再调用 SeedVR2 做高清放大。用户提到探店图、门店场景合成、模特放入店铺场景...

Headless Ghost publishing. Write, audit, and automate your entire Ghost operation from your AI workflow — 17 workflows covering article publishing, batch imp...

Visualize how attention moves across your agent's projects. Every session leaves a trace. Over time, those traces form a map — not of what your agent was tol...

Reads your raw idea stream — voice notes, fragments, half-sentences — and surfaces the patterns you keep circling without realizing it. Drop anything. Find t...

Bidirectional mathematical engine for Borges' Library of Babel. Finds the permanent hexagon address of any text, reads any page at any coordinate, and scores...

Estimate LLM task token usage, cost, and duration using rule-based classification and optional local profile data without external dependencies.

Web access privileges for your agent. So your agent stops hitting walls.

Your OpenClaw is the brain. Codex or Claude Code are the hands. The clipboard is the protocol.

出题工具。根据文档内容（docx、pdf、txt 等）生成选择题测试卷，并返回二维码供答题者扫码作答。触发词：出题、生成题目、创建测验、云端出题。

Security scanner that audits OpenClaw skills for malicious code, prompt injection, supply chain attacks, data exfiltration, and more

Scan OpenClaw skills for malware, prompt injection, reverse shells, wallet theft, supply chain attacks, and data exfiltration. Protect your agent from the 38...

SkillShield v4 — Ultimate security scanner for OpenClaw skills. 65 security checks, SARIF v2.1.0 output, CI/CD ready, campaign detection, C2 IP blocklist, kn...

Full browser automation skill for the OpenClaw platform. Use this skill whenever the user wants to log in to OpenClaw, navigate its portal, submit forms, ret...

Register AI agents with permanent identities, create and share soul templates and dreams, contribute to community souls, and browse favorite personalities wi...

Monitor Twitter to identify key opinion leaders, track emerging trends, analyze sentiment, detect bots, and deliver verified real-time intelligence reports.

Provides accurate, context-aware translations that preserve meaning, tone, and cultural nuances while ensuring terminology consistency across documents.

Constructs and executes precise, multi-query Google searches using advanced operators to retrieve, filter, and rank credible, up-to-date sources.

Conducts systematic academic searches across arXiv, Google Scholar, and Semantic Scholar to deliver verified top 5 relevant peer-reviewed papers with summari...

Aggregate and deduplicate multiple RSS/Atom feeds, score and cluster articles by importance, and generate concise, source-attributed daily digests.

Autonomously inspects a live OpenClaw instance across 5 health domains (hardware, config, security, skills, autonomy) and delivers a quantified traffic-light...

Continuously identifies and prioritizes unsolved tasks, searches and installs BotLearn skills, and engages the community to improve agent capabilities autono...

Conducts standardized exams assessing multi-dimensional OpenClaw Agent capabilities, scores with rubrics, generates radar-chart reports, and offers improveme...

botlearn-selfoptimize — BotLearn continuous improvement engine that captures errors, corrections, and learnings; triggers on command failure, user correction...

Download videos from Jable.tv. Triggered when the user mentions "download Jable video", "jable download", or uses /skill jable.

Simple video downloader for Jable.tv. Download videos by ID or search by actress name.

Propose, confirm, and execute Safe multisig transactions using the Safe{Core} SDK (protocol-kit v6 / api-kit v4). TypeScript strict. Use when an agent needs to operate a Safe smart account — (1) create/predict a new Safe, (2) fetch Safe owners/threshold/nonce, (3) list pending multisig txs, (4) build + propose a tx, (5) add confirmations, (6) execute a tx onchain, or (7) troubleshoot Safe nonce/signature issues across chains (Base/Ethereum/Optimism/Arbitrum/Polygon/etc.).

DEPRECATED — archived Pulse skill. Use x402janus for wallet security and monitoring.

Propose, confirm, and execute Safe multisig transactions using the Safe{Core} SDK (protocol-kit v6 / api-kit v4). TypeScript strict. Use when an agent needs to operate a Safe smart account — (1) create/predict a new Safe, (2) fetch Safe owners/threshold/nonce, (3) list pending multisig txs, (4) build + propose a tx, (5) add confirmations, (6) execute a tx onchain, or (7) troubleshoot Safe nonce/signature issues across chains (Base/Ethereum/Optimism/Arbitrum/Polygon/etc.).

x402janus — autonomous on-chain wallet security for EVMs: scan approvals, trace fund flow, detect drainers, and build revoke transactions. Pay via x402 USDC...