UltraQA

Skill Verified Active

QA cycling workflow - test, verify, fix, repeat until goal met

Purpose

To provide an automated, persistent QA cycling workflow that ensures code quality goals are met without continuous manual oversight.

Features

Autonomous QA cycling workflow
Automated goal parsing (tests, build, lint, typecheck, custom)
Multi-agent orchestration for diagnosis and fixing
Iterative execution with cycle limits and early exit conditions
State tracking and cancellation support

Use Cases

Automating repetitive QA cycles in development
Ensuring build and test suites pass before deployment
Continuously improving code quality through automated fixing
Running complex verification tasks autonomously

Non-Goals

Performing manual QA testing
Replacing developer-specific debugging tools
Handling environment setup or dependency installation

Workflow

Parse goal from arguments (tests, build, lint, typecheck, custom).
Execute verification based on the goal type.
Check the result: if successful, exit; otherwise, proceed.
Spawn an architect agent to diagnose the failure.
Apply recommended fixes using an executor agent.
Repeat the cycle up to a maximum of 5 times or until specific exit conditions are met.

Practices

Autonomous agent workflow design
QA automation
Error handling and recovery
State management

Prerequisites

Claude Code CLI
Claude Max/Pro subscription or Anthropic API key
tmux installed
Project with standard build/test commands

Installation

First, add the marketplace

/plugin marketplace add Yeachan-Heo/oh-my-claudecode

/plugin install oh-my-claudecode@omc

Quality Score

Verified

99 /100

Analyzed about 23 hours ago

Trust Signals

Last commit1 day ago

GitHub owner Yeachan-Heo

Stars33.7k

Downloads 38.8k

LicenseMIT

Websiteoh-my-claudecode.dev

Status

View Source

Similar Extensions

Telegram Crabbox E2e Proof

100

Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.

Skill

steipete

Project Session Manager

100

Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions

Skill

Yeachan-Heo

Acp Router

100

Route plain-language requests for Pi, Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only `sessions_spawn` for thread creation. Codex chat binding defaults to the native Codex app-server plugin unless ACP is explicit or background spawn needs ACP.

Skill

steipete

Openclaw Testing

100

Choose, run, rerun, or debug OpenClaw tests, CI checks, Docker E2E lanes, release validation, and the cheapest safe verification path.

Skill

steipete

Agent Browser

100

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

Skill

shanraisshan

Swarm Orchestration

100

Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.

Skill

ruvnet