发现最适合你需求的 AI 技能
Best practices for automating long-running, asynchronous tasks via cron-style polling. Use when the user wants to monitor a background CLI command or API call that does not return an immediate result — such as waiting for a report to generate, a podcast to be created, a deep research job to complete, or any task with a clear completion condition. Triggers on requests like "monitor X until done", "poll for Y", "wait for Z to complete in the background", "run X in the background and notify me when
保单数据管理 - 创建、读取、更新保单 JSON 文件。当用户选择产品后创建保单,上传材料后更新材料列表和提取数据,口述信息后更新投保数据,确认缴费计划后更新状态。
|
Render responses in a structured, modular UMG speech style with GPT-4o-inspired conversational polish for highly readable chat output.
Turns a raw podcast transcript into show notes, social captions, episode titles, SEO tags, and chapter timestamps. Supports both AI-narrated and human-hosted podcast styles.
Create a highly visual, editorial long-scroll HTML microsite from a podcast episode. Use when the user gives a podcast link (Apple Podcasts/Spotify/RSS/direct MP3/YouTube) and asks for: (1) 8–12 curated highlights (not full transcript), (2) per-highlight playable original audio clips, (3) multilingual language toggle (e.g., English/Japanese/Chinese) applied globally across UI and content, (4) premium typography-led layout inspired by an editorial deck with a sticky table-of-contents rail.
>
SSH-based PM2 service management for remote servers. List processes, restart/stop services, view logs, monitor CPU/memory usage, and perform common PM2 operations on production servers.
Use PM2 to reliably restart OpenClaw gateway on Windows. Use when the user wants to restart the OpenClaw gateway, fix port conflicts, or recover from a crashed gateway. This skill handles the Windows-specific issues with FIN_WAIT_2 TCP connections and scheduled task failures that plague the standard openclaw gateway start/stop commands.
General product-management copilot that acts as the default entry point for PM work. Use when the user has a broad PM request, mixed product materials, or wants the assistant to figure out the best immediate next step and produce the first useful artifact, instead of naming a specific PM workflow or output.
Build, review, and debug OpenClaw plugins with the official plugin SDK. Use when creating or modifying `extensions/
Systematically analyze scientific papers by mapping figures to discussions, identifying logical flow, and tracking evidence sources. Figures are the backbone of a paper's argument — this skill teaches agents to trace the logic chain from figure inventory through evidence classification to complete argument reconstruction.