Agent Skills Hub

hegelion

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

tavily-web

Advanced web search, content extraction, and site crawling capabilities using the Tavily API, optimized for AI agent research and data gathering.

toh-framework

Security-first auditing framework for AI-generated code. Provides multi-level protection including hardcoded secret detection, dangerous pattern identification, and comprehensive vulnerability audits for modern web applications.

fix

Automated code maintenance tool for React developers to resolve linting, formatting, and CI validation errors.

diagram

Maintain and synchronize Unified Impact Diagrams using the Diagram Driven Development (DDD) methodology to connect technical architecture with user value.

pali-me

Automatically keep technical documentation in sync with codebase changes by analyzing git diffs.

orchestrator

Autonomous multi-agent orchestration framework for Claude Code with memory-driven workflows, parallel-first task execution, Aristotle-based deconstruction, and multi-stage quality gates.

pr-template

Generate professional pull request descriptions using Grey Haven Studio standards, ensuring clear summaries, motivation, technical implementation details, and testing strategies.

dev-workflow

Full-stack SDLC agent workflow managing the entire production lifecycle from intake and planning to automated testing, CI/CD, and infrastructure deployment using MCP tools.

cc-stack-analysis

Expert tool for auditing and validating the structural integrity, naming conventions, and best practices of Claude Code configurations, including skills, hooks, and commands.

secure-claude-code

Monitor Runwall security posture, enabled guardrails, and recent audit logs for Claude Code, Codex, and MCP-based development environments.

evaluating-code-models

Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.