Agent Skills Hub

research-review

Get deep, critical, NeurIPS/ICML-style peer reviews of your research, paper drafts, and experimental setups using external LLMs via Codex MCP.

trench

High-performance Solana meme coin trading for AI agents: sniping, MEV-protected execution, rug detection, and automated position management.

arduino-mcp

An MCP server enabling agents to edit, manage, and compile Arduino IDE 2.0 sketches, including source code manipulation and automated build capabilities via arduino-cli.

social-media

Drafts engaging social media posts, writes hooks, creates thread structures, and generates companion images for LinkedIn and X/Twitter.

pdf-generation

Professional PDF generation from markdown using Pandoc. Supports Eisvogel templates, EB Garamond typography, and dual-layout optimization (A4 for print/desktop, 6x9 for mobile/Telegram).

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.

agentic-workflows

Build production-grade AI agents using LangGraph, Anthropic/OpenAI/vLLM, and structured outputs. Features streaming, A2A protocol, Pydantic validation, vector memory, and guardrails for resilient, multi-agent workflows.

query-sub-agent

Specialized IDF (Information Display Frame) sub-agent for generating and reviewing CQRS Query Side implementations across Java, TypeScript, and Go.

metadata-optimization

Optimize your App Store and Google Play metadata with expert ASO frameworks. Craft high-ranking titles, descriptions, and keyword fields to maximize search visibility and conversion rates for iOS and Android.

cross-repo-coordination

Coordinates cross-repository updates for GitHub Actions runner configurations, ensuring workflow labels match runner scale sets to prevent job queuing.

reflect-appworld-failure

Analyze AppWorld task failures to extract specific API patterns and generate actionable playbook bullets with concrete code examples.