Skills

Part of Azure Agent Skills, a curated collection of production-ready agentic skills for Azure cloud development. These skills follow the Agent Skills open standard and provide expert-level guidance on Azure services for Claude Code, Gemini CLI, Codex, and other AI coding assistants.

Part of Microsoft's Azure Agent Skills collection, providing production-ready agentic skills for Azure cloud development that follow the Agent Skills open standard and work with Claude Code, GitHub Copilot, Gemini CLI, and other AI coding assistants.

Part of the Azure Agent Skills collection offering production-ready agentic skills for Azure cloud development. Follows the Agent Skills open standard and works with Claude Code, Gemini CLI, Codex CLI, Cursor, and other AI coding assistants.

Salesforce Commerce Cloud B2C controllers skill for building and debugging B2C storefront controllers. Part of the B2C developer tooling collection.

BDI (Beliefs-Desires-Intentions) mental states skill from the Antigravity Skills collection, providing agent architecture patterns based on cognitive modeling.

Part of the DDC collection of 221 skills for automating construction company processes with AI coding assistants, covering BIM, quantity takeoff, scheduling, compliance, and project management across 5 categories.

Agent skills that enable AI coding agents to operate the BlitzReels video API for creating, editing, and exporting production-ready short-form videos for TikTok, Instagram Reels, and YouTube Shorts.

An AI-driven agile development framework with scale-adaptive intelligence that adjusts from bug fixes to enterprise systems, featuring 12+ specialized agents, structured workflows grounded in agile best practices, and a complete project lifecycle from brainstorming to deployment.

Part of a comprehensive 245-skill library covering 14 business domains including Engineering, Marketing, C-Level, Compliance, and Legal, with support for 11 AI assistants and 653 Python automation tools.

A brand guidelines skill that applies Anthropic official brand colors and typography to artifacts for consistent visual formatting.

Browserbase cloud browser infrastructure skill for AI agents to create sessions, persist contexts, and automate browsers.

Integrates with Burp Suite web application security testing tools via the Membrane CLI, enabling interaction with scans, proxies, intruders, repeaters, and other penetration testing features with automatic authentication.

An ultra-compressed communication mode skill that reduces token usage by approximately 75% while maintaining full technical accuracy. Supports multiple intensity levels from lite to ultra, plus classical Chinese (wenyan) modes.

Auto-generated agent skills from the fastest-growing Claude Code open source projects on GitHub, with a bot that scans for trending repos every 30 minutes and creates installable skill files.

Part of the cc-skills marketplace providing 36 Claude Code plugins with meta-skills, foundational tools, and self-revising autonomous-loop primitives. Includes internet search across 15+ platforms, terminal recording automation, booking management, session sharing, and autoloop patterns for long-running tasks.

A comprehensive digital marketing engagement methodology with 25 specialist agents, 150 skills, and 71 Python scripts that runs brand engagements through a canonical 12-part strategy flow, designed for agencies and teams managing 50-200+ brands with auditable handoffs.

An open-source web interface for managing Codex and Claude Code sessions, featuring project workspace browsing, session history with token usage tracking, real-time AI response streaming via SSE, and cross-platform support for Windows, Linux, and macOS with system tray integration.

A code review skill from the Dedalus ERP-PAS foundation skills library, providing reproducible instructions for AI assistants to perform reliable code reviews alongside skills for coding standards, backend patterns, and TDD.

from api/git

Analyzes code architecture and structure to detect layer violations, circular dependencies, god objects, anemic domain models, missing boundaries, and configuration problems, generating severity-scored findings with fix prompts.

A CodeProbe skill that performs senior-engineer-level code review across 9 categories including security, SOLID principles, architecture, performance, and code smells, with severity-scored findings and automatic tech stack detection.

An OSINT-grade intelligence skill from the OpenFang Agent OS that continuously monitors targets (companies, people, topics) with change detection, sentiment tracking, knowledge graph construction, and critical alerts when important shifts occur.

A skill backed by the Exa MCP server that enables AI assistants to research any company, retrieving business information, recent news, and market insights through Exa's neural search API.

The largest open-source cybersecurity skills library for AI agents, featuring 754 skills across 26 security domains and compatible with 5 major agent frameworks.

Part of a 245-skill library covering 14 business domains including engineering, marketing, compliance, legal, PM, and more. Supports 11 AI platforms (Claude Code, Cursor, Codex, Gemini CLI, etc.) with cross-domain personas, compound sub-skill systems, and slash commands for common workflows.

Context degradation diagnosis skill for identifying lost-in-middle issues, context poisoning, attention pattern failures, and agent context problems.

A cross-platform AI skills library with 245 skills across 14 domains including engineering, marketing, compliance, legal, and finance, featuring 653 Python tools, 32 agents, and 7 personas that work with 11 AI assistants from Claude Code to Codex.

A control systems skill from Skills for Antigravity, a collection of development skills compatible with Antigravity and other AI coding platforms.

Part of a collection of 135+ production-ready skills and 2 MCP servers for Claude Code, built by a former Meta ML engineer. Skills teach Claude domain expertise through decision frameworks, mental models, best practices, and proven methodologies.

A skill that extracts large inline test modules into adjacent test files while preserving visibility, helper access, and coverage shape, keeping production files clean without weakening tests.