技能列表

针对指定表或集合做查询模式分析、可复用索引设计与 explain 迭代验证。支持两种优化模式：默认全量模式（定位该表/集合所有查询）与单查询模式（用户指定某条查询时，仅分析该查询并查询数据库现有索引）；支持两种执行确认模式：需确认模式与免确认模式。

Scheduled market intelligence briefing workflow for A-shares, HK stocks, US markets, macro policy, and geopolitical news. Activate when: (1) running as a cron/scheduled job to push hourly market updates, (2) user asks to collect or summarize market news, (3) user mentions A股, 港股, 恒指, 特朗普, 地缘政治, 军事, or related investing topics. Delivers time-aware briefings (morning/intraday incremental/closing) with deduplication. Uses Tavily Search via mcporter + web_fetch fallback, delivers via Feishu message

|

一套可复用的内容创作思维框架，用于构建具有说服力和情感层次的文章。

Virtual gene knockout simulation using foundation models to predict transcriptional

Read-only file browsing and reading in the OpenClaw workspace (/home/alfred/.openclaw/workspace). Use for listing directories or reading text files (up to 10k chars). Triggers on queries like "list files in [dir]", "read file [path]", "browse workspace [path]". Restrict to relative paths; reject absolutes or ../ escapes. NOT for writing, deleting, executing, or non-workspace access.

Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Supports multiple accounts. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.

A comprehensive AI agent skill for anyone navigating a legal case. Whether you are the plaintiff, the defendant, or somewhere in between — this skill helps you understand what you are actually facing, build the strongest possible position, work with your attorney as an equal partner, make decisions at every fork in the road with clear eyes, and reach the best available outcome from wherever you are starting.

Generate and edit images using Cloudflare Workers AI via the `imageflare` CLI. Use when: user asks to generate an image from a text prompt, edit/transform an existing image with AI, or manage Cloudflare AI image model settings. NOT for: non-image AI tasks, local image editing without AI (cropping, resizing), or video generation.

Image analysis using multimodal vision models. Use when user needs to: (1) Describe what's in an image, (2) Extract text from images (OCR), (3) Analyze visual content, (4) Compare images, (5) Answer questions about images. Supports JPG, PNG, GIF, WebP formats.

OpenClaw清理大师 - 项目目录清理与优化工具。提供快照、Diff、检查点、任务进度等能力，AI 可直接调用自动执行。

将图片（含文字、公式、标题）转换为指定代码格式。自动识别标题级别（title1/title2/title3），文字行转为 $word->body(\"正文=\".$F);，公式转为 $word->formula(\"\");，图片标记为 ![image]