Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality re — from…
Best practices for scikit-learn machine learning, model development, evaluation, and deployment in Python
Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering, dimensionality re — from…
Classical ML in Python: classification, regression, clustering, dim reduction, evaluation, tuning, preprocessing pipelines.
Machine learning in Python with scikit-learn. Use for classification, regression, clustering, model evaluation, and ML pipelines. — from majiayu000/claude-skill-registry
A comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival; use it when you need to model censored time-to-event outcomes, fit…
Declarative YAML-based AI agent lifecycle management with tmux/screen, SSH remote deployment, modular auto-accept, and live state inspection.
App developer SDK — scaffold, validate, dev-install, standalone shell, file operations, and cloud SDK for building SciTeX workspace apps.
Unified container management for Apptainer/Singularity + Docker — 14 MCP tools for the reproducible-science lifecycle.
Execution-context detection — `is_notebook()`, `is_ipython()`, `is_script()`, `detect_environment()`.
Dictionary utilities for scientific Python — attribute-access dicts, conflict-aware merging, nested flattening, and pretty rendering.
General-purpose async event bus. Emit typed events (`scitex_events.emit("test_complete", project="...", status="success", payload={...})`) from any CLI/HPC/Python process; events…
IPython-style introspection for any Python package. `q(obj)` mirrors IPython's `obj?` (signature + type hints + docstring summary). `qq(obj)` mirrors `obj??` (full source).
Jupyter notebook reproducibility — verify execution via Clew sessions, scan for untracked I/O (`scitex.io` calls outside `@scitex.session`), reconstruct the true cell-dependency…
One-call alerting across 9 backends — audio TTS (spoken notification), desktop popup, emacs minibuffer, matplotlib banner, playwright browser toast, email (SMTP), webhook (HTTP…
Agent Communication Hub — real-time WebSocket messaging between AI agents across machines with channel routing, @mentions, presence, and persistence.
Project-aware path utilities for scientific Python — finding files/dirs/git roots, SciTeX `script_out/` session-path conventions, versioned directories, and symlink hygiene.
System resource introspection + monitoring. `get_specs()` returns full hardware/OS/Python snapshot (CPU, memory, disk, network, GPU, OS, Python version) as a nested dict.
Type aliases and runtime type guards for scientific Python — unions across NumPy/pandas/torch arrays, matplotlib color inputs, and list-of-T predicates.
Project-specific UI refactor workflow for the Scoop news platform in /home/bender/classwork/Thesis. Use when updating Scoop frontend layouts, globe UX, research workspace, and…
Exploratory workflow for understanding problem spaces and drafting feature proposals, refactorings, or complex bug-fixes.
Analyze a problem, plan the fix, execute with verification. Use when tackling a non-trivial bug, feature, or refactor that needs structured approach.
Analyze project structure, architecture, tech stack, and existing Claude Code configuration. Use when starting the dream-team workflow to understand the codebase context.
Use when after implementing or modifying the scoring module that computes average InChIKey scores and neighbourhood scores for candidate matches, or when integrating new scoring…
A write-capable assistant that guides small, focused code changes end-to-end. Use when you need to make a targeted edit — add a function, fix a typo, update a config, refactor a…
A read-only assistant for exploring, explaining, and discussing code. Use when you want to understand how something works, trace a flow, review architecture, or ask questions…
Map a codebase's structure, tech stack, architecture patterns, and conventions into a reusable Project Context document.
Final-pass QA review — cross-task integration testing, UI validation via browser MCP (Playwright), and overall quality assessment.
Analyze test coverage gaps, recommend test strategies by module, and generate test task files. Use when you want to proactively improve test health, assess coverage, or plan a…
Use when building or reviewing Scout web UI, dashboard UX, demo flows, visual polish, accessibility, responsive layout, and product screens for the Codex Hackathon project.
Scrape sites protected by Akamai/Cloudflare bot detection by launching real Chrome with remote debugging (CDP).
使用 Python + Scrapling 获取网页内容，支持简单选择器\n\n核心能力:\n\n- 研究工具领域的专业化AI辅助工具\n\。Use when 需要AI模型调用、智能对话、Agent编排、LLM应用时使用。不适用于需要100%确定性的关键决策。适用于独立开发者、企业团队和自动化工作流场景。
Веб-скрапинг через Scrape.do. Обходит блокировки и CAPTCHA. АВТОМАТИЧЕСКИ используй при ошибках WebFetch: 403, 401, 429, timeout, access denied, Cloudflare block.
ScrapeGraphAI is a Python web scraping library that uses LLMs and directed graph logic to create intelligent scraping pipelines.
Cloud browser automation CLI for AI agents powered by Scrapeless. Use when the user needs to interact with websites using cloud browsers, including navigating pages, filling…
Automate Scrapfly tasks via Rube MCP (Composio). Always search tools first for current schemas. — from engineering/cloud-platforms
Automate cloud browsers với Playwright qua Scrapfly Cloud Browser API. Proxy rotation, anti-bot fingerprinting, geo-targeting built-in.
Crawl toàn bộ website với tự động phát hiện link, depth control, trích xuất dữ liệu có cấu trúc. Dùng khi cần crawl nhiều trang cùng lúc.
Web scraping API với proxy rotation, anti-bot bypass, JavaScript rendering. Dùng khi cần scrape trang web bị chống bot (Cloudflare, DataDome, PerimeterX).
Receive and verify Scrapfly webhooks. Use when setting up Scrapfly webhook handlers for async scrape, extraction, screenshot, or crawler jobs, debugging…
Interfaces with the ScrapingBee REST API for JavaScript rendering and Google SERP extraction. Uses custom_google parameter for search result parsing and screenshot endpoint for…
Web scraping with Scrapling - HTTP fetching, stealth browser automation, Cloudflare bypass, and spider crawling via CLI and Python.
Scrapling is an adaptive Python web scraping framework that automatically handles website structure changes.
Scrapling CLI(명령줄) 도구로 터미널에서 웹 스크래핑하는 방법. 코드 작성 없이 scrapling extract 명령으로 웹페이지를 HTML/Markdown/텍스트로 추출하고, scrapling shell로 인터랙티브 스크래핑 REPL을 실행하며, scrapling install로 브라우저 의존성을 설치한다.
Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering.
使用 Scrapling 抓取、清洗、分析网页并生成结构化数据或中文报告。适用于 scrape / crawl / fetch / extract / summarize 网站内容、profile/activity feed、回答/文章/帖子列表、近 1 年动态、批量网页调研，以及用户明确提到…
Orchestrates large-scale web crawling using Scrapy with scrapy-redis for distributed job queuing. Integrates Splash for JavaScript rendering, stores results in MongoDB via…
Manages Scrapy spider deployments via Scrapyd API with custom item pipelines for MongoDB ingestion, deduplication via MinHash LSH, and rotating proxy middleware configuration.
Scrapy is a high-level Python framework for web crawling and structured data extraction. It is a strong fit for agent workflows that need repeatable scraping, asynchronous…
Generates Scrapy spider classes with CSS/XPath selectors, item pipelines, and middleware configurations for structured web scraping.
Builds and manages Scrapy web scraping spiders with custom item pipelines. Supports Splash rendering for JavaScript pages, rotating proxies via scrapy-rotating-proxies, and export…
Expert guidance for building web scrapers and crawlers using the Scrapy Python framework with best practices for spider development, data extraction, and pipeline management.
Manages Scrapy spider deployments and job scheduling on ScrapyCloud via the Scrapinghub API. Handles spider argument injection, job prioritization, and item export to S3 or…
Why all temporary debug scripts, one-off AST refactorers, and test payloads must be quarantined inside a dedicated scratch/ directory, eliminating git status noise and test runner…
Domain-first folder structure reflecting business capabilities. Trigger: When structuring projects or refactoring toward use-case-driven boundaries.
Interactive screen reader simulation for education and debugging. Parses HTML/JSX and produces step-by-step narration of what a screen reader would announce.
Practical guide to testing web applications with screen readers for comprehensive accessibility validation.
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring…
VBShop mobil (mobile/) projesine yeni bir feature veya ekran iskeleti ekler — Clean Architecture katmanları (domain/data/presentation), Riverpod provider'ları, go_router rotası ve…
Retrieve and analyze Screenpipe CLI backend logs and desktop app logs for debugging