Monitor website uptime - check availability, response times, and status

Web search, AI answers, content extraction, and async deep research

Verify if an email address is valid and deliverable

Get weather forecasts - temperature, precipitation, wind, and conditions

Get current weather and forecasts using free APIs (no API key required). Use when asked about weather, temperature, forecasts, or climate conditions for any location.

Take screenshots of websites and web pages

>

>

>

Daily meeting preparation system that checks your calendar each morning, deeply researches external attendees (LinkedIn, company info, GitHub, past notes), and sends you personalized briefs via email (1 per person). Use when you want automated preparation for upcoming meetings with context about each person you're meeting.

>

Repurposes long-form video (podcasts, interviews, talks) into short-form vertical clips for Instagram Reels, TikTok, and YouTube Shorts. Handles transcription, moment selection, clip extraction, speaker-tracked reframing (16:9 to 9:16), and animated captions.

>

Framer Motion patterns, page transitions, skeleton loading, scroll-linked animations, and gesture-based interactions for React.

Lambda best practices, S3 event patterns, SQS/SNS fanout, and DynamoDB access patterns for serverless AWS architectures.

AI browser automation - navigate, interact, extract, verify via browser-use MCP

GitHub Actions workflow patterns, matrix builds, caching strategies, deployment pipelines, artifact management, and rollback procedures.

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

ETL/ELT patterns, batch vs streaming, idempotency, data quality framework, and pipeline orchestration

React Hook Form + Zod integration, multi-step forms, optimistic validation, server-side error mapping, and file upload patterns.

Competitive intelligence - extract features, pricing, tech stack from competitor sites

Document modeling, aggregation pipeline, indexing strategy, change streams, and multi-document transactions.

TLDR CLI komut referansi. tree, structure, search, extract, context, cfg, dfg, slice, calls, impact, dead, arch, imports, importers, diagnostics, change-impact komutlari.

Agent basina token kullanimi takibi, maliyet optimizasyonu, butce limitleri ve ROI analizi. Session ve proje bazinda harcama raporlari. Hangi agent ne kadar token tuketiyor, hangisi verimli, hangisi israf.

**Name:** `anim`

Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers. Use when: inngest, serverless background job, event-driven workflow, step function, durable execution.

>

Guides free tools pages that drive traffic and lead generation for the main product. **Tools are free, standalone utilities** — not the primary monetization. They serve the same ICP as the paid produc

Guides download page structure and optimization for desktop and mobile app downloads. Purpose: convert visitors into installers by clearly presenting value, platform options, and trust signals.

>-

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform

Transform content into professional slide deck images.

Fetch any URL and convert to markdown using Chrome CDP. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.

Executa o pipeline de redução de ruído e normalização de volume em arquivos de áudio usando Python (bibliotecas como Silero, noisereduce, numpy e scipy) para otimizar a entrada para modelos de reconhecimento de voz como o Whisper.

Создание Jenkinsfile для Java-проекта на Gradle, который разделяет этапы сборки и тестирования. Основное требование — избежать двойного запуска тестов, используя флаг исключения в команде сборки, и поддерживать динамический выбор ветки для PR.

Навык для разработки процедур на PL/pgSQL (DO-блоков), которые выполняют итерацию по данным, полученным через dblink, делают дополнительные выборки для каждого элемента, объединяют результаты и массово вставляют их в локальную таблицу.

封装一个Python类EntityExtractor，用于从字符串中提取指标、业务线、车型、地区等实体。该类使用正则表达式匹配括号内容，并根据预定义的实体库进行过滤。

使用OpenCV和NumPy处理具有透明背景的PNG图像。功能包括：将图像画布向外扩展200像素，在非透明内容外围添加100像素宽的白色填充，并在白色填充外围添加5像素宽的平滑黑色边框。黑色边框的平滑处理需使用距离变换（Distance Transform）和高斯模糊（Gaussian Blur）技术。

编写用于加载词汇表、使用Jieba分词、构建TextDataset类以及执行LSTM模型预测的Python代码。

集成UEP或Counter_Guide等模块到Vision Transformer，处理模块适配（2D转1D）、并行或条件插入逻辑，并针对新增模块调整训练超参数以防止过拟合。

用于在Vision Transformer模型中实现特征维度转换（序列到空间、空间到序列）时，根据配置动态处理CLS Token（分类标记）的技能。确保模型在启用或禁用CLS Token时均能正确运行。

对业务查询进行深度结构化分析，支持依存关系括号表示法和广义表（LISP风格）语法树两种输出模式，精准提取时间、实体、指标及修饰词。

使用openpyxl库读取Excel文件，保留前N行（表头）不动，从第N+1行开始按指定列进行降序排序，并将结果覆写回原文件。

指导如何在CEUTrackActor类的compute_losses方法中集成基于SVD的正交高秩正规化损失。该技能包括提取注意力矩阵、计算奇异值、构建正则化项并将其加入总损失函数的步骤。

从Excel读取中文文本，支持基于句法树结构（如深度、词性）或语义向量（如TF-IDF、SentenceTransformer）的特征提取，执行聚类分析（如K-Means、DBSCAN），并将结果导出回Excel。

从OCR识别后的医疗单据文本中提取日期、医生姓名、患者姓名、诊断和总消费金额，具备文本矫正和关键字识别能力，并以JSON格式输出。

Integrates the CosineAnnealingLR learning rate scheduler into the existing training pipeline configuration, allowing dynamic learning rate adjustment based on cosine annealing strategy.

实现用于Vision Transformer的UEP模块，包含特定的卷积层顺序（低维投影、并行卷积、中间处理、高维投影）、残差连接和维度变换，并将其与ViT编码器块进行并行处理集成。

修改多模态视觉Transformer模型，构建双分支架构分别处理RGB和Event数据（分别拼接模板与搜索区域），并输出独立特征以支持双Head处理。

Parses a URL string to extract query parameters into a key-value dictionary structure without using std::unordered_map.