This skill provides access to the inference.sh CLI platform, which lets you run over 150 AI applications without requiring local GPU resources. Generate images with FLUX, create videos with Veo, query LLMs like Claude and Gemini, perform web searches, and automate Twitter posts through simple bash commands.

Running Python safely across data, web, and media tasks is difficult when environments differ. This skill runs code in a managed sandbox with common libraries and file outputs.

Run 150+ AI applications including image generation, video creation, LLM calls, and web search directly from the command line without GPU setup.

Running AI models locally requires expensive GPU hardware. This skill provides seamless access to 150+ cloud AI models including image generation, video creation, LLMs, and web search through a simple CLI interface.

Vet helps AI coding assistants identify issues in their code changes by analyzing git diffs and conversation history. Run it immediately after any logical unit of code changes to catch misunderstandings between what was requested and what was implemented.

Ensure your web pages have correct, complete metadata for SEO and social sharing. Identifies violations, duplicates, and missing tags with specific fixes to improve search visibility and social card previews.

Code reviews help identify maintainability issues before they become technical debt. This skill provides AI assistants with systematic guidelines to evaluate code across seven key dimensions including naming, functions, duplication, and project conventions.

Writing custom linting rules and code transformations is complex and error-prone. This skill provides ready-to-use ast-grep YAML patterns for creating precise AST-based code search and rewrite rules.

Hooks enable event-driven automation in Claude Code plugins. Use hooks to validate tool calls, enforce completion standards, load project context, and integrate external tools into workflows. The skill covers both prompt-based hooks for intelligent decisions and command hooks for deterministic checks.

Developers need tools to build, test, and deploy Apple platform applications efficiently. This skill provides command-line workflows for Swift Package Manager, Xcode projects, simulator management, and code signing.

This skill provides expert guidance for PowerShell development including script templates, best practices for parameters and error handling, Windows Forms and WPF GUI creation patterns, and PowerShell Gallery integration for module management.

Automates iterative website development using Stitch MCP tools and a baton-passing loop pattern. Agents generate pages autonomously, maintain project context, and continue development through continuous improvement cycles.

Transform visual designs from Stitch into clean, modular React code with TypeScript and Tailwind CSS. Eliminate manual coding from design mockups with automated AST validation ensuring consistent code quality.

Manually checking CI status, gathering review feedback, and pushing fixes is repetitive and time-consuming. This skill automates the entire feedback-fix-push-wait cycle so you can focus on writing code while the skill handles PR maintenance.

AI-generated code often includes excessive comments, defensive checks, and unnecessary patterns. This skill reviews git diffs against main and systematically removes code slop while preserving legitimate changes.

Code reviews often miss security vulnerabilities, performance issues, or design problems. This skill provides systematic guidelines to identify common issues across Python, Django, TypeScript, and React while maintaining constructive feedback.

Automatically generate comprehensive unit tests for Java projects using JUnit 5 and Mockito. This skill helps you write test cases that cover happy paths, edge cases, and error scenarios while maintaining best practices.

Accurate GPU kernel benchmarking is challenging due to measurement overhead. This skill provides step-by-step instructions for using CUPTI hardware profiling to get precise kernel execution times. Compare different backends like FlashAttention and cuDNN to find the fastest implementation for your workload.

Translating Figma designs into production-ready code manually is time-consuming and error-prone. This skill provides a structured workflow for pixel-perfect UI implementation with automated design token mapping.

Manual code review is time-consuming and error-prone. This AI code reviewer automatically analyzes source code to identify bugs, security vulnerabilities, style issues, and performance problems with actionable fix suggestions.