Claude Skills by agentskillexchange

Scrapling is an adaptive Python web scraping framework that automatically handles website structure changes. Its parser learns from page updates and relocates elements, its fetchers bypass anti-bot systems like Cloudflare Turnstile, and its spider framework scales to concurrent multi-session crawls with proxy rotation.

Orchestrates large-scale web crawling using Scrapy with scrapy-redis for distributed job queuing. Integrates Splash for JavaScript rendering, stores results in MongoDB via scrapy-mongodb pipeline, and respects robots.txt with AutoThrottle.

Builds production Scrapy spiders with custom Item Pipelines for data cleaning and storage. Uses scrapy.linkextractors.LinkExtractor for crawl scoping and ItemLoader with MapCompose processors for field normalization.

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 crawling, feed exports, and extensible pipelines for transforming or storing collected data.

Generates Scrapy spider classes with CSS/XPath selectors, item pipelines, and middleware configurations for structured web scraping. Includes Scrapy-Splash integration for JavaScript-rendered content.

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 to MongoDB or Elasticsearch.

Generates production-ready Scrapy spiders with middleware configuration and item pipeline setup. Uses the Scrapy Framework API, Selector (XPath/CSS), and Twisted reactor for concurrent crawling.

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 BigQuery.

Use SafeDep Vet as a pre-adoption gate when an agent, maintainer, or CI pipeline is about to add a new dependency or import a skill repository and needs malware and policy signals first.

Encrypt Kubernetes Secret manifests against a Sealed Secrets controller so agents can commit cluster-targeted secrets to Git without exposing plaintext.

Connect an MCP-capable assistant to arXiv search, paper download, local paper storage, and research prompts for grounded literature review workflows.

Use Zotero MCP to let research agents search papers, retrieve metadata, inspect annotations, and analyze citation context from a Zotero library.

Browse archived sessions from multiple coding agents, search across them locally, and copy exact resume commands when you need to re-enter prior work.

Use GritQL when an agent needs reviewable structural search and rewrite passes across a large codebase before a migration, policy cleanup, or API change, instead of relying on regex or hand edits.

Give supported coding agents a shared Markdown-first memory layer so they can recall prior decisions, transcripts, and notes across sessions instead of re-deriving context from scratch.

Lets an MCP-compatible agent search Help Scout inboxes, customers, organizations, and full thread history so support replies start with the right account and ticket context.

Index docs and source trees into structure-aware search so you can answer targeted questions quickly without a vector database or brittle grep sprawl.

Use Claude Context when a coding agent needs targeted semantic retrieval from a very large repository instead of repeatedly loading folders or files into prompt context. It indexes code into a vector database and exposes code-search retrieval through MCP for Claude Code and other compatible agent clients.

Use pdf-mcp to inspect a PDF, search it, and load only the pages that matter so an agent can answer questions from long documents without brute-forcing the whole file into context.

Index local notes, docs, and meeting transcripts, then return ranked files or structured JSON so an agent can pull only the context it needs.

Use notebooklm-mcp-cli when an agent needs to search NotebookLM notebooks, add sources, run notebook queries, and retrieve generated study artifacts without leaving an MCP workflow.

Uses ripgrep-all to run one full-text search across mixed document and archive formats so an agent can find evidence without separately extracting every file type first. Best when a workflow has PDFs, Office documents, ebooks, media sidecars, or compressed bundles that need fast on-demand search.

Lets an MCP-compatible agent read, search, send, thread, template, and organize Apple Mail on macOS so email work can stay inside a bounded agent workflow.

SearXNG is an open-source metasearch engine that aggregates results from multiple search providers without tracking users. It fits research and scraping workflows that need self-hosted search, configurable engines, and a documented admin surface for search aggregation and result control.

Downloads and parses SEC EDGAR filings (10-K, 10-Q, 8-K) using the EDGAR full-text search API and python-xbrl. Extracts financial statements, risk factors, and executive compensation into structured datasets.

Retrieves and parses SEC EDGAR filings (10-K, 10-Q, 8-K) using the EDGAR Full-Text Search API and company filing API. Extracts XBRL financial data via the SEC XBRL API for structured balance sheet and income statement analysis.

Java or Docker

Orchestrates Selenium Grid 4 node scaling based on test queue depth using the Grid GraphQL API. Manages Docker container lifecycle for Chrome, Firefox, and Edge nodes with health monitoring.

Distributes browser test suites across Selenium Grid 4 nodes using RemoteWebDriver and the W3C WebDriver protocol. Supports parallel execution on BrowserStack and Sauce Labs with automatic capability negotiation.

Distributes browser automation workloads across Selenium Grid 4 nodes using the Grid REST API and session queue management. Implements weighted round-robin with health-check monitoring via /status endpoint.

Orchestrates parallel cross-browser testing across Selenium Grid nodes using WebDriver RemoteConnection API. Supports Chrome, Firefox, and Edge with configurable DesiredCapabilities for each browser matrix.

Manages Selenium Grid 4 hub and node registration for cross-browser parallel testing. Configures Chrome, Firefox, and Edge nodes with resource allocation policies.

Orchestrates distributed browser testing across Selenium Grid 4 nodes using the Grid REST API. Manages session allocation, node health monitoring, and parallel TestNG suite execution.

Orchestrates parallel browser automation across Selenium Grid nodes using RemoteWebDriver, DesiredCapabilities, and WebDriverWait. Manages session distribution, retry policies, and HTML test reports via ExtentReports.

Orchestrates distributed browser tests across Selenium Grid 4 nodes with dynamic scaling. Uses selenium-webdriver RemoteWebDriver with W3C WebDriver protocol and Zalenium-style video recording.

Manages browser session allocation across Selenium Grid 4 nodes using the GraphQL status endpoint and SE_NODE_MAX_SESSIONS configuration. Implements weighted round-robin distribution with health-check-based failover for Chrome, Firefox, and Edge instances.

Manages distributed browser sessions on Selenium Grid 4 via the GraphQL API and /status endpoint. Handles node scaling, session queuing, and capability matching for parallel test execution.

Routes browser automation sessions across Selenium Grid 4 nodes using the /status and /session endpoints. Configures RemoteWebDriver with DesiredCapabilities for cross-browser parallel execution.

Orchestrates distributed browser testing across Selenium Grid 4 nodes using the Grid API. Manages session queuing, node health, and parallel test execution via the WebDriver protocol.

Selenium is the long-running open source browser automation framework behind the W3C WebDriver standard. It gives agents and developers a stable way to drive Chrome, Firefox, Safari, and Edge across multiple languages and execution environments.

SeleniumBase is a Python framework for browser automation, end-to-end testing, and stealthy web interaction. It layers pytest-friendly test structure, browser control, reporting, and anti-bot-aware CDP and UC modes on top of Selenium workflows.

Use Speaches when an agent stack expects OpenAI-style audio endpoints but you want a self-hosted speech backend for transcription, translation, and text-to-speech instead of a hosted API.

Capture failures, corrections, and repeatable lessons so important operational knowledge persists across sessions.

semantic-release automates version calculation, changelog generation, tagging, and package publishing from conventional commits and CI runs. It fits agent workflows that need repeatable release automation across npm and other release targets without manual version bumps.

Runs Semgrep against a codebase using official or custom rule registries and outputs a grouped report of security anti-patterns, deprecated API usage, and policy violations. Supports 30+ languages and produces SARIF output.

Python, pip

Builds custom Semgrep rules using the Semgrep pattern syntax and semgrep CLI. Generates YAML rule files with metavariable patterns, taint tracking, and autofix transformations.

Generates Semgrep SAST rules from vulnerability descriptions using the Semgrep CLI and semgrep-rules YAML schema. Supports metavariable patterns, taint tracking, and join rules for cross-function analysis.

Builds custom Semgrep rules using the semgrep YAML rule syntax with metavariable-pattern, pattern-either, and taint-mode analysis. Generates rule packs for OWASP Top 10 detection across Python, JavaScript, and Go codebases.