Explorar skills

Activates FinancialModelBuilder for building complete financial models from scratch. Use when you need a 3-statement model (P&L, balance sheet, cash flow) built with assumptions, a revenue model with multiple drivers, a unit economics model, a startup runway model, or a scenario analysis with sensitivity tables — all with clear assumptions and audit trail.

飞书妙记：妙记相关基本功能。1.查询妙记列表（按关键词/所有者/参与者/时间范围）；2.获取妙记基础信息（标题、封面、时长 等）；3.下载妙记音视频文件；4.获取妙记相关 AI 产物（总结、待办、章节）；5.上传音视频生成妙记，也支持将本地音视频文件转成纪要、逐字稿、文字稿、撰写文字等产物；6.更新妙记标题（重命名妙记）；7.替换妙记逐字稿中的说话人。遇到这类请求时，应优先使用本 skill。飞书妙记 URL 格式: http(s)://<host>/minutes/<minute-token>

飞书视频会议：让机器人代当前用户加入/离开正在进行的会议，并读取会议期间的实时事件（参会人加入与离开、发言、聊天、屏幕共享等）。1. 用户提供 9 位会议号、要求代为入会或离会时使用 +meeting-join / +meeting-leave——会真实产生入会/离会记录。2. 会议进行中用户想知道“谁加入了”“谁离开了”“谁在发言”“有人共享屏幕吗”等会中动态时，机器人入会后用 +meeting-events 读取事件时间线。3. 典型场景：参会机器人、会中助手、代为旁听、代为参会。前提：机器人只能读到它自己参会过且仍在进行中的会议的事件；查询已结束会议的参会名单、纪要或逐字稿请使用 lark-vc 技能。

Analyze energy load forecasting systems including demand prediction models (ARIMA, Prophet, LSTM), weather API integration, peak shaving strategies, demand response program optimization, renewable intermittency handling, net load duck curve management, model validation with MAPE/RMSE accuracy metrics, and time-series data pipeline quality for utility and ISO/RTO operations.

Ajuda profissionais de marketing a auditar e melhorar o desempenho técnico de websites, incluindo velocidade de carregamento da página e Core Web Vitals, para reduzir a taxa de rejeição e melhorar a conversão.

Complete customer interview intelligence — discovery interviews, win/loss interviews, churn interviews, NPS follow-up calls, and synthesizing insights that change what gets built

This skill checks prerequisites for building Dapr Workflow apps with .NET Aspire. Use this skill when the user asks to "check prerequisites for Aspire", "verify Aspire environment", or "check Aspire setup".

Lark/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via `lark-cli event consume <EventKey>` (covers IM messages/reactions/chat changes, VC meeting ended, Minutes generated, etc.). Use for Lark bots, real-time message processing, long-running subscribers, streaming webhook/push handlers. Supports `--max-events` / `--timeout` bounded runs and a stderr ready-marke

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Activates ArxivResearcher — a deep academic paper analysis and synthesis agent. Use when you need to understand cutting-edge research, compare approaches across multiple papers, extract key contributions and limitations, translate ML/CS/physics papers into actionable insights, build literature reviews, or track the state-of-the-art on a specific topic.

Use when reproducing, isolating, and fixing a bug with the smallest safe change.

Analyze vendor management systems for performance scorecards, third-party risk assessment, SLA enforcement, vendor rationalization, and relationship governance. Evaluates vendor tiering strategies, risk taxonomy (financial, cyber, compliance, geopolitical), continuous monitoring with BitSight/SecurityScorecard, ITIL supplier management alignment, diversity program tracking, and lifecycle managemen