Agent Skills Hub

p9

P9 Tech Lead mode: Manages P8 agent teams via Task Prompts (six-element) without direct coding. Orchestrates 3+ parallel agents for project management, task decomposition, and architecture.

qcc-git

Git workflow and branch management tool for the qcc_plus project, enforcing standardized commit conventions and secure deployment processes.

writing-skills

A Test-Driven Development (TDD) framework for writing agent skills, using pressure scenarios to ensure documentation guides agent behavior effectively.

using-git-worktrees

Creates isolated git worktrees for parallel development, automatically handling directory selection, .gitignore safety checks, dependency installation, and baseline test verification.

Investigating Code Patterns

Systematically trace code flows, locate implementations, diagnose performance issues, and map system architecture to understand complex codebases.

playwright-pro

Production-grade Playwright testing toolkit. Automate E2E testing, fix flaky tests, perform migrations from Cypress/Selenium, and integrate with CI/CD, TestRail, and BrowserStack.

visual-testing-advanced

Advanced visual regression testing with pixel-perfect and AI-powered diff analysis, cross-browser validation, and responsive design checks to prevent UI regressions in CI/CD pipelines.

backend-core

Language-agnostic backend architectural patterns covering API design, authentication, security protocols, and database modeling.

upstash-ratelimit-ts

A connectionless, HTTP-based rate limiting SDK for TypeScript, ideal for serverless, edge functions, and distributed environments using Upstash Redis.

home-assistant-master

Home Assistant OS (HAOS) operations skill for agents. Features read-only diagnostics, automation design, health auditing, and safety-first configuration management.

openclaw-test-heap-leaks

Investigate and resolve OpenClaw test memory leaks, Vitest OOMs, and RSS growth using heap snapshots.

claude-ralph

An autonomous AI agent loop that executes Claude Code repeatedly to build features from structured PRDs until completion.