Agent Skills Hub

vtm-expert

Token-efficient virtual task management for AI-assisted development. Manage task lifecycles, dependencies, and TDD workflows with surgical context injection.

task-breakdown

Break down complex development requests into sequenced, actionable tasks for multi-agent delegation in Claude Code environments.

workflow-execute-plans

Execute implementation plans in small, verifiable batches with pause-for-feedback checkpoints to prevent drift and ensure code quality.

langgraph-workflows

Master multi-agent orchestration with LangGraph. Build stateful, fault-tolerant AI workflows using supervisor-worker patterns, conditional routing, and advanced state management.

create-mcp-app

Scaffold and build interactive MCP Apps with custom UIs for hosts like Claude Desktop. Supports React, Vanilla JS, and various framework templates for tool-resource integration.

context-optimization

Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.

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.

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.

session-intelligence-harvester

Captures session learnings into Reusable Intelligence Infrastructure (RII). Converts one-time bug fixes and pattern discoveries into permanent agent-executable knowledge to prevent recurrence and accelerate future development.

lgtm

Launch lgtm TUI to review markdown files, code plans, or documentation with line-by-line commenting, syntax highlighting, and collaborative feedback workflows.

performance-optimization

Optimize Node.js performance via Redis caching, clustering, profiling, and monitoring to build fast, scalable, and efficient backend services.

tool-use-structured-output

Enforce structured JSON output from Claude models using Bedrock tool_use to eliminate parsing failures and ensure schema compliance.