Agent Skills Hub

jina-cli

A powerful CLI for converting web content and search results into LLM-friendly formats like Markdown, text, or HTML using the Jina AI Reader API.

pytorch-lightning

PyTorch Lightning skill for scalable deep learning: automates model training, multi-GPU orchestration, data pipelines, and distributed training strategies like DDP, FSDP, and DeepSpeed.

react-vite-best-practices

React and Vite performance optimization guidelines. Use when writing, reviewing, or optimizing React components built with Vite.

semgrep

Run Semgrep static analysis scans on codebases using parallel subagents, multi-language detection, and Pro-enabled cross-file taint tracking.

structured-outputs-advisor

Expert advisor for implementing Anthropic's structured outputs. Choose between JSON mode and strict tool use for guaranteed schema compliance and validated agentic workflows.

turborepo

High-performance build system for JavaScript/TypeScript monorepos. Optimized for parallel task execution, remote caching, and dependency graph analysis.

Wheels Test Generator

Generate TestBox BDD test specs for Wheels models, controllers, and integration tests. Supports validations, associations, and workflow testing.

constant-time-analysis

Detects timing side-channel vulnerabilities in cryptographic code through static and dynamic analysis across multiple programming languages.

jira-cli

Interactive terminal interface for Atlassian Jira that streamlines issue management, sprint tracking, and ticket workflows directly from the command line.

split-pdf

Automated pipeline to download, split, and deeply analyze academic PDFs in structured batches to avoid context window limits and ensure high-quality comprehension.

hegelion

Dialectical reasoning and adversarial coding agent for MCP-enabled editors, forcing LLMs to resolve internal contradictions for higher quality outputs.

jules-skill

Manage Jules (Google's async AI coding agent) directly from your terminal. Create, monitor, and interact with Jules coding sessions, approve plans, and handle feedback loops across repositories.