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.

n8n-security-testing

Automated security scanning for n8n workflows: detects credential exposure, validates OAuth flows, tests API key management, and checks data sanitization.

pr-operations

Manage PR review workflows, resolve threads, and handle discussion comments using specialized erk exec commands.

ash

GitHub workflow assistant with integrated git and gh CLI support for managing repositories, branches, pull requests, and issues.

gh-fix-ci

Debug failing GitHub Actions CI checks by fetching logs, summarizing failures, and planning fixes.

solana

Expert Solana Anchor development: build programs, manage PDAs, implement SPL tokens, handle security audits, and perform fuzz testing with Trident.

markdown-token-optimizer

Analyzes markdown files to identify token-wasting patterns, providing actionable suggestions to optimize documentation for LLM consumption and token efficiency.

anp-agent

Cross-agent interaction skill via ANP protocol. Use decentralized identity (DID) to discover and invoke remote agents like maps, booking, and logistics services across the ANP network.

mijia-control

Control and monitor Xiaomi Mijia smart home devices including status switching, device discovery, automation scenes, and environmental statistics.

jlens-mcp

Expert-level Java codebase analysis and Maven dependency management skill. Enables deep bytecode inspection, multi-version dependency conflict resolution, and automated project building via MCP integration.

context-bar

A color-coded, real-time context usage progress bar for the Claude Code statusline and manual on-demand checks.

youtube-rl-tracker

A reinforcement learning-inspired tracker for YouTube performance, using systematic logging to optimize thumbnails, titles, and hooks.