qa-sweep

Name: qa-sweep
Availability: InStock
Author: trader-rm

Coordinate parallel sub-agent implementation and independent adversarial review with a 95% confidence gate.

Updated Aug 27, 2026

Search Tags:#automation #qa #review #code-quality #quality-assurance #parallel-subagents #adversarial-review

Ready to run

npx skills add https://github.com/trader-RM/ultra-swarm --skill qa-sweep-trader-rm

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: qa-sweep
Source: https://github.com/trader-RM/ultra-swarm/tree/main/base/opencode-swarm/.claude/skills/qa-sweep
Command: npx skills add https://github.com/trader-RM/ultra-swarm --skill qa-sweep-trader-rm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Apply when implementing features, fixing bugs, debugging errors, investigating failures, tracing root causes, reviewing tech debt, tracing issues, planning fixes, or completing any task. Enforces parallel sub-agent implementation, independent adversarial review, and a 95% confidence gate before stopping.

Core Features & Use Cases

Enables structured, multi-agent review workflows for feature delivery, bug fixes, and debugging tasks.
Enforces mandatory independent adversarial review and cross-checks to surface edge cases and regressions.
Provides a governance gate (>=95% confidence) to ensure high-quality outcomes before finalizing work.

Quick Start

Run a project-wide QA sweep to orchestrate parallel sub-agents, initiate independent adversarial review, and validate completion with >=95% confidence.

Frequently Asked Questions about qa-sweep

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate code review for feature implementation and bug fixes?▼

Automate code review for feature implementation and bug fixes by orchestrating parallel sub-agent implementation followed by independent adversarial review. This structured workflow enforces cross-checks and a 95% confidence gate to surface regressions before finalizing work.

What is an adversarial review workflow for quality assurance?▼

An adversarial review workflow for quality assurance is a process where independent sub-agents cross-check feature implementation to surface edge cases. It imposes explicit phases including parallel implementation and completeness verification to achieve high confidence in delivery.

How do I run a project-wide QA sweep with parallel sub-agents?▼

Run a project-wide QA sweep by initiating parallel sub-agent implementation, then triggering independent adversarial review agents. The process applies mandatory guardrails and a completeness verification phase to validate task completion with at least 95% confidence.

Does the 95% confidence gate stop task completion for debugging errors?▼

Yes, the 95% confidence gate stops task completion for debugging errors if independent adversarial review fails. It enforces mandatory review phases and guardrails to ensure high-quality outcomes before allowing any debugging or failure investigation to finalize.

What is the best way to trace tech debt and investigate failures with code quality automation?▼

The best way to trace tech debt and investigate failures is using parallel sub-agent implementation combined with independent adversarial review. This approach applies a structured completeness verification phase to ensure high confidence before stopping the investigation.