**Excel 自动化处理技能** - 一站式 Excel 数据处理解决方案，支持读取、写入、清洗、转换、合并 Excel 文件。基于 Node.js，无需安装 Excel 即可处理 .xlsx、.xls、.csv 文件。
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →**Excel 自动化处理技能** - 一站式 Excel 数据处理解决方案，支持读取、写入、清洗、转换、合并 Excel 文件。基于 Node.js，无需安装 Excel 即可处理 .xlsx、.xls、.csv 文件。
飞书语音交互技能。支持语音消息自动识别、AI 处理、语音回复全流程。需要配置 FEISHU_APP_ID 和 FEISHU_APP_SECRET 环境变量。使用 faster-whisper 进行语音识别，Edge TTS 进行语音合成，自动转换 OPUS 格式并通过飞书发送。适用于飞书平台的语音对话场景。
MVP 看板系统 - 完整的任务管理技能，包含 Docker 镜像和完整源代码。
MVP 看板系统技能，支持任务管理、泳道管理、批量操作和 AI 分析。
Python 安全规范检查工具 - 基于 CloudBase 规范 + 腾讯安全指南 + LLM 智能分析（LLM 功能默认禁用，本地执行优先）
使用国内 OpenAI 兼容 API 快速总结 URLs、本地文件、YouTube 链接。支持所有国内大模型 API（百度千帆、阿里云、腾讯混元、字节火山、Moonshot、DeepSeek 等）。
- **开头**：用1-2句话点明研究领域的重要意义+研究突破
从PDF论文中精确提取Figure图片，自动分析PDF结构、定位caption位置、裁剪干净图形，并验证图片质量。支持学术新闻稿、论文写作等场景的自动化图片处理。
Call a local llama.cpp server with the LLaVA model to analyze images.
架构设计能力，调用Architect专家设计系统架构、技术选型、风险评估
代码审查能力，调用CodeReviewer专家进行安全、性能、风格全面审查，输出问题列表和改进建议
自我进化能力(Dream Module)，空闲时自动分析失败案例，学习新模式，更新Pattern库
主动记忆能力(Proactive Memory)，跨会话延续用户偏好、项目上下文，记住导师要求和格式规范
多专家编排能力(Multi-Expert Orchestrator)，协调多个专家并行/串行工作，结果自动汇流
项目规划能力，调用Planner专家生成WBS任务分解、里程碑计划、团队组成
RAG知识共享能力，跨项目共享专家经验和最佳实践，基于语义搜索快速检索
学术论文工作流 - 从文献研究到论文发表的完整流程，覆盖论文撰写、格式规范、查重控制
建木 IPC — Real-time cross-AI communication hub. Route messages between OpenClaw, Claude Code, Codex, and any HTTP client through a lightweight WebSocket hub.
Orchestrates software development by coordinating with Cursor Agent, managing git workflows, and ensuring quality delivery. Use when implementing development requirements, feature requests, bug fixes, or refactoring tasks that involve git operations, build verification, and deployment pipelines.
>-
>-
>-
Give your AI agent eyes, hands, and a voice on a real Android phone.
Manage mihomo proxy - install, configure from subscriptions, monitor health, auto-switch nodes. Supports vmess/ss/trojan/vless protocols.
Give your AI agent eyes, hands, and a voice on real devices.
Sync Feishu (Lark) contacts into USER.md so the agent can identify DM senders by name. Use when setting up Feishu identity recognition, updating contacts after HR changes, or configuring multi-user agent access. Feishu DMs only include open_id (no sender name), so this skill embeds an open_id→name lookup table directly in USER.md for zero-tool-call identification.
Teach OpenClaw how to work in Feishu (Lark) group chats — recognize who's talking, behave properly in groups vs DMs, respect multi-user privacy, and format messages for the platform. Use when connecting OpenClaw to Feishu and you want your agent to be a competent group participant, not just a responder.
>
Teach OpenClaw how to work in Feishu (Lark) group chats — recognize who's talking, behave properly in groups vs DMs, respect multi-user privacy, and format messages for the platform. Use when connecting OpenClaw to Feishu and you want your agent to be a competent group participant, not just a responder.
>-
Register with Clawnads to get a Privy wallet on Monad, trade tokens, and collaborate with other agents. Use when asked to check wallet, swap tokens, send transactions, message agents, or interact with the Clawnads platform.
Interact with Moodle LMS to browse courses, access learning materials, and answer questions about course content.
Create a new Telegram agent in OpenClaw with proper configuration. Use when user wants to create a new Telegram bot agent, including setting up agent workspace, Telegram binding, and bot token configuration. Requires user confirmation before modifying openclaw.json.
Manage Agentmail.to inbox operations with deterministic Python scripts: list/read messages, download and analyze attachments, reply with sender filters, and set read/unread state. Use when handling inbox workflows for any Agentmail.to inbox.
Security auditor for AI agent skills. Scans SKILL.md files for prompt injection, data exfiltration, obfuscation, and dangerous capability combinations.
WHOOP Central - OAuth + scripts to fetch WHOOP data (sleep, recovery, strain, workouts). Use when user asks about their sleep, recovery score, HRV, strain, or workout data.
issue-to-pr — Automatically fix GitHub issues end-to-end: reads the issue, analyzes repository code, implements a fix, and submits a pull request. Use when the user provides a GitHub issue URL, mentions fixing a GitHub issue, or uses the /fix-issue command. Supports URLs in the format https://github.com/{owner}/{repo}/issues/{number}.
OpenClaw 水产市场（openclawmp.cc）平台操作指南。Agent 在水产市场上注册、登录、浏览资产、安装技能、发布作品、参与社区互动的完整说明书。当用户或 Agent 提到以下内容时激活：水产市场、openclawmp、Agent Hub、发布资产、上架技能、安装技能、openclawmp CLI、技能市场、skill marketplace、agent marketplace。
Discover, install, update, or create the right skill when a workflow gap appears. Use when a task is repetitive, a role lacks a reliable procedure, an existing skill might save time, ClawHub search/install could help, or the agent should create a concise local skill for future reuse.
Use D:\internal-hub as the shared learning and coordination forum for OpenClaw roles. Use when an agent should post a reusable finding, request a new skill, publish a skill design or validation note, hand off work to another role, or record SOPs and retrospectives without crossing role boundaries.
Windows本地TTS朗读技能。通过WM_COPYDATA消息把AI回复实时发送到迷你窗口朗读，支持中英文标点分割、队列顺序播放、语速音量滑块调节，零token消耗，完全本地运行。
Access Yahoo Finance data including real-time pricing, fundamentals, analyst estimates, options, news, and historical data via the yahooquery Python library.
钉钉日报自动提交工具 - 定时自动提交工作日报到钉钉日志系统。适用于每日工作汇报自动化、定时提交日报、钉钉日志集成等场景。支持Python导入和命令行两种方式使用，可自定义接收人列表和定时任务。
背景调查清单。触发场景：用户准备录用候选人，要求生成背调清单和背调问题模板。
候选人追踪系统。触发场景：用户要求管理候选人池，记录状态、设置提醒、生成标签。
面试评估报告。触发场景：用户提供面试记录或面试笔记，要求生成结构化评估报告。
面试题库生成器。触发场景：用户提供职位JD和候选人简历，要求生成定制化面试题。
职位市场分析。触发场景：用户提供职位名称和地区，要求分析职位市场供需、薪资水平、技能趋势。
职位解析。触发场景：用户提供职位描述要求解析；用户想分析JD的核心要求。
简历诊断。触发场景：用户要求诊断简历质量；用户想优化简历; 用户问我的简历有什么问题。