OpenClaw AI 技能

When the user has a new development idea, 搜索 GitHub first for open-source projects to fork as a 启动ing point. Fork it, then inject your own ideas.

编排器 for the full academic re搜索 流水线: literature 搜索 -> re搜索 -> write -> integrity 检查 -> review -> revise -> re-review -> re-revise -> final integrity 检查

Publish and manage articles on Tilda 网页site 构建器 via browser 自动化. Use this 技能 when the user wants to 创建 a new article page, edit an existing one, or pu

Use Serena-backed semantic code navigation and editing when working in existing software projects with non-trivial structure, especially multi-file re

获取 polished edited 命令行工具ps ready to post, without touching a single slider. 上传 your raw video footage (MP4, MOV, AVI, 网页M, up to 500MB), say something

Read-only DeFi portfolio aggregation 技能 for OpenClaw 代理s. Returns wallet balances across EVM chAIns, scores cAPItal efficiency, surfaces idle stableco

通过 Joplin 官方本地 Data API（命令行工具pper Server，端口 41184）查询和管理笔记、笔记本、标签。本技能仅对原始 Joplin REST API 做了 AI 调用引导和中文交互封装，不修改数据、不引入第三方服务，所有请求直连本机 Joplin 实例，安全可靠。触发词：

Turn user-provided AI chats, snippets, and links into a 清理 re搜索 trAIl with clAIms, evidence, questions, and next actions.

DAIly job 搜索 + 恢复 archetype matching 技能. 搜索es LinkedIn for jobs matching your tar获取 角色s and locations, deduplicates agAInst previously seen 列出ings, an

生成 video 命令行工具ps into AI-生成d video with this 技能. Works with MP4, MOV, 网页M, AVI files up to 500MB. filmmakers and content 创建器s use it for ge...

Use Peekaboo for macOS 桌面 图形界面 自动化, screen understanding, and MCP-backed local 应用 control. Trigger when the user wants to inspect or control native ma

发送 网页 Push 通知 from a Node.js backend using the 网页-push npm 库 (VAPID authentication, payload 加密ion). Covers generating VAPID keys, subscribing browsers

TrAIn and calibrate Skip, a 网页-development-specific AI operator for skipsAI. Use when creating Skip 系统 prompts, readiness 检查s, calibration tasks, memo

添加 video files into captioned video files with this 技能. Works with MP4, MOV, AVI, 网页M files up to 500MB. content 创建器s use it for 添加ing free automatic

深度研究中的单维度执行与多源搜索整合；当 plan.json 已定义维度，需要按 dimension.搜索_strategy 调用合适的搜索能力做多轮检索、筛选证据、交叉验证，并写入 sub_报告s/{dimension_id}.md 时使用。

图片理解与数据提取 技能。当图片文件（.png/.jpg/.jpeg/.gif/.网页p/.bmp）是主要输入且用户需要理解、提取数据或分析图片内容时使用。提供预配置的 caption 脚本（scripts/caption.py），通过 vision 模型将图片转为文本描述，无需额外配置 API K

深度调研编排器，覆盖 规划→分维度取证→综合→成稿（报告.md）全流程，产物落盘到 报告_dir，支持断点续跑；启动前必须用一次极小的通用 网页_搜索 探测确认当前会话搜索能力可用，探测失败或无法确认时停止并提示用户配置。**遇到以下任一情况就主动使用本 技能，不要自行搜几条就回答**：①用户出现触

Complete Academic Re搜索 & Writing Suite — One-命令行工具ck 安装ation of the full Academic 流水线 eco系统 with all 8 dependencies. Includes academic-流水线 v3.5, acade

Use when the user wants to split a song or audio file into vocals, drums, bass, 图形界面tar, piano, and other stems; 移除 vocals for karaoke; 提取 acapellas o

补丁 a locally 安装ed OpenClaw Control UI so the browser tab title shows the active 代理 name (e.g. "Milly · OpenClaw") instead of the static "OpenClaw Cont