Claude Skills by agentskillexchange

Lets an agent supervisor spawn and steer isolated terminal-based worker agents with explicit handoff, assign, and message patterns.

Use Squad to create human-directed specialist agents that persist in a repository, share decisions through files, and help coordinate implementation, testing, and review work in GitHub Copilot.

Keep a large software project moving across planning, execution, and review by handing work between structured agent roles instead of losing the thread in one giant chat.

Leverages Copy.ai's Workflows API to generate multi-step cold outreach sequences with persona-specific messaging. Each sequence step is rendered using Copy.ai's email-sequence template type and pushed to HubSpot CRM via the HubSpot Contacts and Emails API.

An agent skill built on Coqui TTS, the open-source deep learning toolkit for text-to-speech synthesis. Provides CLI and Python API access to multiple TTS model architectures including VITS, Tacotron2, and GlowTTS, with support for voice cloning, multilingual synthesis, and on-the-fly voice conversion.

Debugs and profiles Apple Audio Unit v3 (AUv3) plugins using auval validation tool, the AUAudioUnit Swift API, and Instruments AudioUnit trace template for latency measurement and buffer underrun detection.

Validates container image and artifact signatures using Sigstore Cosign with keyless verification via Fulcio and Rekor transparency logs. Enforces supply chain integrity policies with OPA/Rego.

Run web crawling and scraping workflows with Crawl4AI, an open-source crawler built to produce LLM-ready markdown and structured extraction output. It supports async crawling, browser automation hooks, deep crawls, CLI usage, and Python-based data pipelines.

Crawl4AI is an open-source web crawler that converts any website into clean, LLM-ready Markdown for RAG pipelines, AI agents, and data extraction workflows. With an async browser pool, it handles large-scale web extraction with anti-bot detection and deep crawl capabilities.

Self-hosted web crawling and content extraction exposed as MCP tools. Scrape pages, crawl sites with depth control, and extract clean markdown — all self-hosted and free.

Crawl4AI is an open source crawler and scraper built for LLM-ready web extraction, with structured markdown output, browser support, and Python package distribution. It has strong adoption, active maintenance, and a dedicated docs site for integration patterns.

Implements intelligent web crawling using the Crawlee framework with adaptive request routing between CheerioCrawler and PlaywrightCrawler. Manages request queues, handles anti-bot challenges, and exports structured data.

Crawlee is Apify’s open source crawling and scraping framework for Node.js. It unifies HTTP scraping and browser automation, adds queues, storage, retries, proxies, and lets developers switch between Playwright, Puppeteer, Cheerio, and JSDOM without rebuilding the whole pipeline.

Crawlee is Apify's open source web crawling and scraping library for Node.js. It combines request queueing, browser automation, proxy support, and storage primitives so agents can build reliable Playwright, Puppeteer, Cheerio, or HTTP crawlers from one toolkit.

Builds scalable web collection pipelines with Crawlee, Apify’s open-source crawling and browser automation library. Useful for request queue management, Playwright or Puppeteer crawling, structured dataset export, and resilient scraping across large sets of pages.

Use Dagu to define file-backed workflow jobs in YAML, run them locally or across workers, and inspect failures through a lightweight operator surface instead of a heavyweight orchestrator.

Use the Anthropic docx skill when an agent needs to produce or repair a real .docx deliverable with headings, tables, numbering, tracked changes, or layout constraints. It frames the work as a document-building workflow with validation and packaging rules, not as a generic document library listing.

Use the Anthropic xlsx skill when an agent needs to create, clean up, or modify .xlsx, .xlsm, .csv, or .tsv files as spreadsheet deliverables, not just inspect tabular data. It pushes the agent toward formula-safe edits, workbook validation, and recalculation instead of hardcoded outputs or one-off scripts.

CrewAI is a lean, lightning-fast Python framework for orchestrating role-playing autonomous AI agents. It enables developers to define agents with specific roles, goals, and backstories, then assemble them into crews that collaborate on complex tasks through sequential or parallel workflows.

Use the upstream install or setup path that matches your environment: - Let’s walk through setting up a project that depends on DynamoDB from the SDK and makes a simple service call. The following steps use yarn as an example. These steps assume you have Node.js and yarn already installed. - git clone https://github.com/aws/aws-sdk-js-v3.git - yarn && yarn test:all - yarn pack .

CronitorCLI is Cronitor's open-source command-line tool for syncing cron jobs, sending telemetry pings, and wrapping commands with execution monitoring. It fits monitoring-heavy agent runbooks where scheduled jobs, server tasks, and long-running commands need explicit visibility.

Extracts company profiles, funding rounds, and investor data using the Crunchbase Enterprise API v4 with autocomplete, search, and entity lookup endpoints. Builds competitive landscape maps with funding timeline visualizations.

Crush is a terminal-native AI coding agent built by Charmbracelet that connects your code, tools, and workflows to any LLM. It supports multi-model switching mid-session, MCP extensibility, and LSP-enhanced context across every major platform.

Parses and evaluates Content Security Policy headers using csp-parse and csp-evaluator libraries. Identifies overly permissive directives, missing protections, and generates tightened policy recommendations.

CSpell is a spell checker built for source code, configuration files, and documentation, with dictionaries and ignore mechanisms that work well in real repositories. It helps agents and teams catch noisy typos before they land in code review, docs, or CI output.

Validates CSV files against JSON Schema definitions using AJV and csv-parse. Automatically detects and repairs type mismatches, missing required columns, and encoding issues with configurable strictness levels.

csvkit is a suite of Python command-line utilities for converting to, working with, and analyzing CSV files. It includes tools for format conversion, querying CSV with SQL, data cleaning, filtering, sorting, and statistical analysis.

Generates Software Bill of Materials in CycloneDX format using cdxgen and Syft. Scans npm, pip, and Go modules for known CVEs via OSV.dev API integration.

Auto-generates Cypress component tests from React and Vue source files using AST parsing. Produces mount, interaction, and accessibility test cases.

Scaffolds Cypress component tests for React, Vue, and Angular apps using the Cypress CT mount API. Configures webpack/vite dev servers and generates snapshot-based visual assertions.

Implements component and E2E tests using Cypress with cy.mount, cy.intercept, and cy.get selectors. Configures cypress.config.ts with component devServer, custom commands, and Mochawesome reporter integration.

Creates component and integration tests using the Cypress Testing Library API and cy.intercept for network stubbing. Supports visual testing via the Cypress Image Snapshot plugin and accessibility auditing with cypress-axe.

Creates end-to-end tests with Cypress cy.intercept() for API mocking and cy.wait() for request assertion. Uses Cypress Testing Library queries with findByRole() and findByText() for accessible element selection.

Generates Cypress end-to-end test suites from user flow recordings. Uses the Cypress Real Events plugin and cy.intercept() for network stubbing with automatic fixture generation.

Cypress is an open-source browser testing framework for end-to-end, component, and accessibility testing in modern web apps. It gives agents and developers a reliable way to run local browser tests, debug failures with rich traces, and plug test execution into CI pipelines.

Generates cy.intercept() stubs from recorded HAR files for deterministic E2E tests. Uses cy.session() for authentication caching and cy.origin() for cross-origin testing workflows.

Runs visual regression tests comparing screenshots captured via Cypress cy.screenshot() against baseline images using pixelmatch diffing. Integrates with Percy SDK for cross-browser visual snapshots.

Automates pixel-level visual regression testing using Cypress with cypress-image-snapshot plugin. Compares screenshots against baselines using pixelmatch algorithm with configurable diff thresholds.

D2 is a modern diagram scripting language that turns text into diagrams. It compiles declarative text files into SVG, PNG, and PDF outputs with automatic layout, multiple themes, and support for sequence diagrams, class diagrams, and network topologies.

Dagger is an open-source automation engine for building, testing, and shipping any codebase. It replaces shell scripts and proprietary YAML with real code using SDKs in Go, Python, TypeScript, and 5 other languages, with built-in caching and OpenTelemetry tracing.

Orchestrate data pipelines using Dagster, the cloud-native data orchestration platform. Define data assets as Python functions with automatic lineage tracking, scheduling, and observability.

Batch-generates brand assets using the OpenAI Images API with DALL-E 3. Manages prompt engineering for consistent brand identity across icons, banners, and social media templates.

Structured prompt generation for OpenAI's DALL-E 3 API (images/generations endpoint) with style modifiers, aspect ratio control, and batch variation generation. Includes negative prompt patterns and quality presets.

Generates multiple image variations from a single brief using the OpenAI Images API (POST /v1/images/generations) with DALL-E 3, applying brand guidelines via structured prompt templates. Handles concurrent generation requests with retry logic for rate limit compliance.

Generates and manages batch image creation jobs using the OpenAI Images API /v1/images/generations endpoint. Supports DALL-E 3 with size, quality, and style parameters plus automatic prompt revision tracking.

Generates image variations and edits using the OpenAI Images API v1 with DALL-E 3 model selection. Supports inpainting via base64-encoded mask uploads, handles 1024x1024/1792x1024 aspect ratios, and implements content policy pre-screening with the Moderation API.

Manages OpenAI DALL-E 3 API workflows for brand-consistent image generation with style references, aspect ratio control, and automated prompt refinement using GPT-4 Vision feedback loops.

Generates and iterates DALL-E 3 image prompts using the OpenAI Images API with size, quality, and style parameters. Chains edits via the images/edits endpoint with mask-based inpainting.

Generates image variations and edits using OpenAI's DALL-E 3 API with mask-based inpainting, style consistency scoring via CLIP embeddings, and automatic prompt refinement loops.

Generates image variations and edits using the OpenAI Images API (DALL-E 3 and gpt-image-1). Manages prompt engineering for consistent style, handles mask-based inpainting, and outputs multiple sizes with quality presets.