Claude Code Skills

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities.

Distinctive, production-grade frontend interfaces that reject generic AI aesthetics through intentional design choices.

React and Next.js performance optimization across 70 rules prioritized by impact.

Relentless interviewing skill that stress-tests plans and designs through systematic questioning.

Fast, persistent browser automation with session continuity across sequential agent commands.

Audit UI code against Vercel's Web Interface Guidelines for design and accessibility compliance.

Relentless design interrogation that stress-tests plans against your domain model and sharpens terminology inline.

End-to-end deployment, evaluation, and management of AI agents on Microsoft Foundry.

Analyze codebases for architectural friction and propose module-deepening refactors as testability improvements.

Unified access to Azure AI services: Search, Speech, OpenAI, and Document Intelligence.

Test-driven development with vertical slices, behavior-focused tests, and incremental red-green-refactor cycles.

Domain-specific knowledge base for building videos with Remotion and React.

Build and deploy GitHub Copilot SDK applications to Azure with flexible model configuration.

Recommend Azure VM sizes, scale sets, and configurations based on workload requirements and budget.

Configuration scaffold for engineering skills to locate issue tracker, triage labels, and domain documentation.

Assess and migrate cloud workloads from AWS, GCP, and other providers to Azure services.

State machine-driven issue triage with role-based workflow management and agent brief generation.

Synthesizes conversation context into a structured PRD and publishes it to your project issue tracker.

Create, read, edit, and manage Lark documents with content extraction, summarization, and formatting support.

Comprehensive Lark Base operations via CLI with table, field, record, view, formula, lookup, workflow, dashboard, and form management.

Summarize conversations into handoff documents for seamless agent-to-agent transitions.

Send and receive messages, manage group chats, and handle files in Lark IM.

Ultra-compressed communication mode cutting token usage ~75% while preserving technical accuracy.

Create reusable Lark API Skills by wrapping atomic operations or orchestrating multi-step workflows.

Break a plan into independently-grabbable vertical-slice issues for your project tracker.

Throwaway code that answers a single design or logic question through an interactive prototype.

Lark approval instance and task management via CLI commands.

Check and manage Azure quotas and usage across regions for deployment planning and capacity validation.

Create, test, and iteratively improve AI agent skills with structured evaluation and benchmarking.

Assess and automate upgrades of Azure workloads across plans, tiers, and SKUs.

Create and edit Lark Office slides with XML protocol, supporting presentation creation, page management, and content modification.

Postgres performance optimization rules across 8 priority categories, from query tuning to advanced features.

Enterprise Azure infrastructure architect generating Bicep or Terraform from workload descriptions.

azure kubernetes

Structured design dialogue that validates ideas before implementation begins.

Markdown file operations for Feishu Drive: create, read, edit, patch, and compare native

Comprehensive design intelligence for web and mobile UI/UX across 10 technology stacks.

Concise, distinctive landing pages and portfolios that avoid templated AI aesthetics.

Query historical Azure costs, forecast future spending, and identify optimization opportunities across subscriptions and resource groups.

React composition patterns for scaling components and avoiding boolean prop proliferation.

Web search, scraping, extraction, crawling, and monitoring via ScrapeGraph AI CLI.

Lightweight brainstorming framework for fast, focused design decisions before implementation.

Terse, conventional commit messages that prioritize reasoning over description.

Robot meeting participation: join/leave active meetings by 9-digit number and stream real-time events.

Ultra-compressed code review comments: location, problem, fix on one line each.

teach

Complete shadcn/ui component management for adding, searching, fixing, styling, and composing UI.

Compress natural language memory files into caveman-speak to reduce input tokens.

Structured debugging workflow for reproducing, minimizing, and fixing hard bugs and performance regressions.