Agent Skills Hub

code-quality-review

Holistic, multi-dimensional code review skill providing prioritized, actionable feedback on correctness, security, performance, design, and accessibility.

Confidence Check

Pre-implementation confidence assessment tool for developers. Ensures 90%+ readiness via duplicate checks, architecture compliance, official docs verification, and root cause analysis.

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.

screenpipe-cli

Manage screenpipe pipes (AI-driven automations) and integrations via CLI. Create, run, schedule, and debug local agents to automate tasks based on your computer activity.

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.

Quality Assurance

Automated quality assurance system that validates markdown deliverables against defined checklists for PB-000 market research workflows.

CCOS MCP Tools

Reference for all MCP tools exposed by the CCOS server, enabling capability discovery, session management, and governed RTFS execution for autonomous agent workflows.

weather

Retrieve current weather conditions, forecasts, and temperature data for global locations to assist with daily planning and travel.

use-railway

Operate Railway infrastructure: manage projects, services, databases, object storage, deployments, environments, variables, logs, and performance metrics.

qc

Automated quality gate using 5 parallel AI agents to review code changes for correctness, style, and consistency.

request-optimizer

An intelligent gateway that analyzes, scores, and routes user requests across 27 agents, 27 skills, and 14 MCPs to optimize Claude Code execution.

research-review

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