Data & AI skills

Search the web with LLM-optimized results via the Tavily CLI. Use this skill when the user wants to search the web, find articles, look up information, get recent news, discover sources, or says "search for", "find me", "look up", "what's the latest on", "find articles about", or needs current information from the internet. Returns relevant results with content snippets, relevance scores, and metadata — optimized for LLM consumption. Supports domain filtering, time ranges, and multiple search depths.

The English summary is being prepared. Showing the original description.

Time-based cohort analysis with retention and behaviour tracking. Activate when you need to measure how groups of users/customers behave over time — retention rates, revenue by cohort, or feature adoption curves.

The English summary is being prepared. Showing the original description.

SQL query review for correctness, performance, and best practices. Activate when a query needs review before production use, shows unexpected results, or runs too slowly.

The English summary is being prepared. Showing the original description.

Systematic exploratory data analysis. Activate when a dataset needs profiling — structure check, nulls, outliers, distributions, correlations — before deeper analysis begins.

The English summary is being prepared. Showing the original description.

Customer/user segmentation with actionable insights. Use when identifying distinct customer groups, analyzing segment-specific behavior, profiling high-value segments, or testing segmentation hypotheses.

The English summary is being prepared. Showing the original description.

Create standardized metadata for data assets. Use when documenting new datasets, building data catalogs, improving data discoverability, or creating data dictionaries for teams.

The English summary is being prepared. Showing the original description.

Temporal pattern detection and forecasting. Use when analyzing trends over time, detecting seasonality, identifying anomalies in time series, or building simple forecasting models for planning.

The English summary is being prepared. Showing the original description.

Conversion funnel analysis with drop-off investigation. Use when analyzing multi-step processes, identifying conversion bottlenecks, comparing segments through a funnel, or optimizing user journeys.

The English summary is being prepared. Showing the original description.

Translate SQL queries into plain language business logic. Use when documenting queries, explaining analysis to non-technical stakeholders, code reviewing for correctness, or building a query catalog.

The English summary is being prepared. Showing the original description.

Systematic investigation of metric changes and anomalies. Use when a metric unexpectedly changes, investigating business metric drops, explaining performance variations, or drilling into aggregated metric drivers.

The English summary is being prepared. Showing the original description.

Standard business metric calculation with industry benchmarks. Use when calculating SaaS metrics (MRR, churn, LTV, CAC), e-commerce KPIs, or product analytics metrics with proper definitions.

The English summary is being prepared. Showing the original description.

Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger. Trigger when the user wants transformation sequences, multi-shot narrative shorts, weapon-charge/combat segments, emotional family/pet/farewell narratives (催泪/亲情/萌宠/离别), or any cinematic video prompt.

The English summary is being prepared. Showing the original description.

使用火山引擎 RDS MySQL MCP Server，帮助用户完成 RDS MySQL 相关的实例管理、数据库操作、账号管理和运维任务，可直接调用 uv run ./scripts/call_rds_mysql.py 脚本获取实时结果。

The English summary is being prepared. Showing the original description.

火山引擎 VEDBM（云数据库 VeDB MySQL 版）管理技能。当用户需要创建 VEDBM 实例、查询 VEDBM 实例列表、查看实例详情、管理数据库账号、获取实例连接地址（Endpoints）、或对实例规格进行升级/降级时使用此技能。包含特定关键词：火山引擎云数据库、VEDBM、VeDB MySQL。

The English summary is being prepared. Showing the original description.

Volcengine VOD audio and video processing tools skill. Use when users need VOD-based media processing or editing: upload local/URL media, stitch videos, trim clips, flip frames, change playback speed, create image-to-video, compose audio/video, extract audio, mix audio, separate vocals/accompaniment, denoise audio, enhance quality, AI super-resolution, frame interpolation, ASR speech-to-text, OCR text extraction, subtitle removal, subtitle embedding, scene slicing, portrait/green-screen matting, highlight extraction, comic style transfer, video translation, drama recap narration, drama script restoration, media info lookup, or playback URL retrieval. The skill submits async VOD jobs, polls task status, and returns generated output links. Not for pure text generation, real-time streaming, or source-free generative video creation.

The English summary is being prepared. Showing the original description.

火山引擎 Supabase . 管理 AIDAP Supabase 项目、工作区、数据库、分支、Auth、Realtime、Edge Functions、Storage、API Keys、SQL、Schema 变更、TypeScript 类型生成和 MCP 集成。

The English summary is being prepared. Showing the original description.

火山引擎 AI MediaKit 音视频处理工具集，提供视频理解、音频提取、视频剪辑、音视频拼接、画质增强、文生视频、音视频合成，以及本地翻转、调速、字幕、水印、转码等能力。当用户提及音频剪辑、视频剪辑、音视频拼接、文生视频、音频提取、画质增强、视频理解、音视频合成、媒体裁剪、视频翻转、调速、加字幕、加水印、转码等需求时必须调用本Skill。当用户需要视频理解时，宿主agent必须自动解析用户的具体要求作为prompt参数传入，同时传入视频URL和fps参数；max_frames 为可选参数。

The English summary is being prepared. Showing the original description.

Compresses and uncompresses file objects stored in Volcengine TOS through TOS data-process async jobs. Use this skill when the user needs to zip files, unzip archives, create tar or zstd archives, extract compressed files, pack multiple TOS objects into a single archive, bundle files together, or distribute files as a package — even if they don't explicitly mention 'compression', 'archive', '打包', or '压缩'.

The English summary is being prepared. Showing the original description.

This skill should be used when the user asks to "generate video prompts", "create Seedance prompts", "write video descriptions", mentions "Seedance", "seedance", "火山引擎", "火山引擎平台", "视频提示词", "视频生成", "AI视频", "短剧", "广告视频", "视频延长", or discusses video prompt engineering, AI video generation, or Seedance 2.0 workflows.

The English summary is being prepared. Showing the original description.

使用火山引擎 RDS PostgreSQL，帮助用户完成 RDS PostgreSQL 相关的实例管理、数据库操作、账号管理和运维任务，可直接调用 uv run ./scripts/call_rds_postgresql.py 脚本获取实时结果。

The English summary is being prepared. Showing the original description.

使用火山引擎 RDS SQL Server，当用户需要执行 RDS SQL Server 相关的实例管理、数据库操作、账号管理和运维任务时使用该skills，可直接调用 uv run ./scripts/call_rds_mssql.py 脚本获取实时结果。

The English summary is being prepared. Showing the original description.

招聘数据分析与优化建议技能。用于定时生成招聘进展日报、周报、月报，分析招聘效果，提供优化建议和下一步招聘策略。

The English summary is being prepared. Showing the original description.

For any completed deliverable, enforce a strict multi-round subAgent review-and-revise loop via sessions_spawn. Invoke before final output or whenever high-standard quality gating is required.

The English summary is being prepared. Showing the original description.

使用 Seedance 2.0 根据提示词与参考素材生成视频。用户要把文本/参考图/参考视频变成视频时使用。

The English summary is being prepared. Showing the original description.