Agent Skills Hub

Observability

Real-time observability dashboard for PAI multi-agent activity, featuring live WebSocket streaming, session tracing, and agent workflow debugging.

ride

Analyze codebases to generate evidence-grounded Loa artifacts using Enterprise-Grade Managed Scaffolding for structured reality mapping.

acceptance-testing

Plan, implement, and execute user acceptance tests (UAT) and end-to-end scenarios to validate requirements against user-visible behavior.

worker

Autonomous agent for ticket-driven development, managing the full software lifecycle from polling providers to automated PR creation with ERNE standard validation.

repo-sync

Automated repository synchronization for multi-repo ecosystems, featuring intelligent failure diagnosis, auto-repair for Git state issues, and integrated ecosystem health checks.

libafl

A modular Rust-based fuzzing library for creating custom fuzzers, advanced mutation strategies, and research-grade vulnerability testing.

mcp-setup

Automated setup and configuration of Model Context Protocol (MCP) servers for Claude Code to enable seamless integration with external databases, APIs, and file systems.

maybe-finance

Personal finance management skill for the Maybe Finance OS. Track transactions, monitor budgets, calculate net worth, and generate financial reports via API.

ash

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

review-collector

Automated compliance validation tool for collector bot packages using 8 specialized parallel agents.

triage-ci-flake

Systematic triage and reproduction workflow for investigating flaky CI test failures in Payload CMS repositories.

sherlock-review

Evidence-based code review using Sherlock Holmes-style deductive reasoning to verify implementation claims, investigate bugs, and conduct root cause analysis.