Run a multi-lens agent QA sweep of the RUNNING product: spawn `qa` agents (one per lens — user-flow · edge-state · honesty · contract · ux-critique), collect their structured findings, integrator-verify the load-bearing ones, and land verified findings as backlog tickets + a run record in the project's qa/ folder.
安装
npx skills add awrshift/agent-memory-kit --skill qa-sweepnpx skills add awrshift/agent-memory-kit --skill qa-sweep -a claude-code -gnpx skills add awrshift/agent-memory-kit --skill qa-sweep -a codex -ggemini skills install https://github.com/awrshift/agent-memory-kit.git --path plugins/memory-kit/skills/qa-sweepgh skill install awrshift/agent-memory-kit qa-sweepgit clone --depth 1 https://github.com/awrshift/agent-memory-kit /tmp/awrshift__agent-memory-kit
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/awrshift__agent-memory-kit/plugins/memory-kit/skills/qa-sweep ~/.claude/skills/qa-sweep # Claude Code
cp -R /tmp/awrshift__agent-memory-kit/plugins/memory-kit/skills/qa-sweep ~/.agents/skills/qa-sweep # Codex, Cursor, Gemini CLI, Copilot, OpenCode