Agent Skills Hub

playwright-cli

Token-efficient CLI for browser automation, web testing, and agentic workflows using Playwright.

saving-codeacts

Preserve successful Python code executions as reusable tools within the gentools package structure, utilizing Pydantic models for structured output and type-safe interfaces.

frontend-design-review

Review, audit, and build production-grade frontend interfaces with high design quality, accessibility standards, and design system compliance.

visual-design-foundations

Establish cohesive visual systems using design tokens, modular typography scales, 8-point spacing grids, and accessible color palettes for consistent UI development.

code-security

Comprehensive secure coding guidelines for 15+ languages, covering OWASP Top 10, infrastructure security, and best practices to identify vulnerabilities in code, configurations, and cloud setups.

solve-challenge

A CTF solver agent that performs triage on challenges, identifies the vulnerability category, and routes tasks to specialized skills for web, pwn, crypto, forensic, and reverse engineering analysis.

hegelion

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

ui-implementer

Implements UI components from Figma/mockups with pixel-perfect accuracy, intelligent design validation, and adaptive agent switching.

code-review-facilitator

Automated static code review for Arduino, ESP32, and RP2040 projects. Identifies memory safety issues, structure improvements, and best practices to enhance firmware quality and reliability.

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

web-shader-extractor

Extract, deobfuscate, and port WebGL/Canvas/Shader visual effects from websites into standalone, native JavaScript projects.

semantic-compression

Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.