发现最适合你需求的 AI 技能
Run analytics end-to-end from your agent without opening a dashboard. English-first workflow, with Chinese docs and content available. Create projects, ship tracking, query results, and run experiments.
Enables peer-to-peer cross-communication between isolated OpenClaw agents. Resolves the limitation of `sessions_send` which cannot cross agent boundaries. 100% Zero-Intrusive, safe, compliant, with zero console popups and robust multiline support.
Get Portland transit information including arrivals, trip planning, and alerts. Use when user asks about buses, MAX, trains, or transit in Portland.
|
快速部署新的 assistant agent。当用户需要新增 agent 时自动创建,编号递增,沿用现有 workspace 和 agentDir 结构。使用场景:「新增一个 agent」、「创建 assistant2」、「加一个日常助手」等请求。
PIV workflow orchestrator - Plan, Implement, Validate loop for systematic multi-phase software development. Use when building features phase-by-phase with PRPs, automated validation loops, or multi-agent orchestration. Supports PRD creation, PRP generation, codebase analysis, and iterative execution with validation.
在 OpenClaw 中创建新的 Agent 并绑定到新的飞书机器人/群聊。用于:(1) 添加新 Agent 管理不同飞书群聊 (2) 实现多机器人路由 (3) 为不同业务线创建独立 Agent。需修改 ~/.openclaw/openclaw.json 配置文件。
Interact with Apollo.io REST API (people/org enrichment, search, lists).
多路召回skill ,用于将意图识别skill中的指标和维度信息进行分析,通过向量知识库召回QA问答对,通过图数据库召回表的定义结构。
利用 Python 从微信公众号文章中提取元数据与正文内容。适用于用户需要解析微信文章链接(mp.weixin.qq.com)、提取文章信息(标题、作者、正文、发布时间、封面图),或将微信文章转换为结构化数据的情景。
用日常穿搭比喻解释代码,帮助小白理解。当用户要求用穿搭、穿衣、衣柜、outfit 比喻解释代码,或提到 Coding as Dressing 时使用。
将Markdown文章转换为小红书风格的封面图、插图和配图。支持阿里百炼和MiniMax API,4种风格(fresh/warm/notion/cute),4种布局(balanced/list/comparison/flow)。