# QA Sweep

> 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. Adapter pointing to the canonical repo skill; refer to that for the full protocol.

- Skill: `zaxbyhub/qa-sweep-3` (Agent Skill)
- Install (CLI): `npx get-skill add zaxbyhub/qa-sweep-3`
- Raw SKILL.md: https://api.skillmd.com/api/skills/zaxbyhub/qa-sweep-3/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: zaxbyhub (https://skillmd.com/u/zaxbyhub)
- Updated: 2026-11-11
- Page: https://skillmd.com/skills/zaxbyhub/qa-sweep-3

---


# qa sweep (Claude Code adapter)

This is a thin pointer to the canonical skill at
`.agents/skills/qa-sweep/SKILL.md`. Claude Code runners should load the canonical SKILL.md
there for the full protocol; this adapter exists only so Claude Code's
`.claude/skills/` discovery finds the skill.

Canonical tree for repo-specific skills: `.agents/skills/` (see
`docs/engineering/skill-conventions.md`).

