Stage7 — Testing skill for Claude Code
7단계 QA 자동화 — qa-automation 의 방법론으로 target_dir 의 통합 테스트를 자동 생성·실행하고 결함/위험을 리팩토링 요구서로 만듭니다.
How to install Stage7
Installs to ~/.claude/commands/leebriller96-project-agents-public-stage7.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/leebriller96/project-agents-public/HEAD/.claude/commands/stage7.md -o ~/.claude/commands/leebriller96-project-agents-public-stage7.md Restart Claude Code, or start a new session, for it to be picked up.
What Stage7 does
description: 7단계 QA 자동화 — qa-automation 의 방법론으로 target_dir 의 통합 테스트를 자동 생성·실행하고 결함/위험을 리팩토링 요구서로 만듭니다. argument-hint: "[full|generate-only|run-only] (기본 full)"
/stage7 — QA 자동화
인자: `$ARGUMENTS` (모드)
절차
.claude/skills/pipeline-core/SKILL.md§1·§8. 선행:stage5_integration: done인 slice 1개 이상.config/tools.yaml → qa_automation.path존재 확인.stages.stage7_qa: in_progress→qa-runner호출. 전달: target_dir 절대경로, 모드, 프로필들, 외부 스킬 경로(config/tools.yaml → qa_automation), 5단계 시나리
Alternatives in Testing
- Playwright — claude-plugins-official Browser automation, E2E testing, screenshots 29.4k ★
- Playwright Automation — git clone Browser automation skill for end-to-end testing and web interaction 2.3k ★
- Test Automation Pack — Test automation skills collection 1.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
QA Sync
Sync generated/healed tests from the plugin output dir into the target app repo.
Smart Browser
Browser automation and API testing MCP server on Playwright + Chrome DevTools Protocol. Numbered element refs
Claudemd Uninstall
Pre-uninstall cleanup. Run BEFORE /plugin uninstall claudemd@claudemd to clear the plugin manifest, state dir,
Feature Map
Build or refresh a source-cited, agent-checkable feature inventory for ANY target project you point it at: per
Continuous Retest Loop
Re-test a target on every change instead of once per engagement — detect drift, then re-run ONLY the affected
Dogfood
Exploratory web QA against a target URL — drives a real browser, captures evidence, writes a structured report
Related Agents
Android Check Build
변경된 모듈 기준으로 컴파일 + 단위 테스트를 독립적으로 실행하고 결과를 보고. Use when: 빌드 체크, PR 올려도 되는지 확인, 빌드/테스트 검증
Lane Implementer
Implementation lane with the full gate battery baked in - private target dir, all-targets clippy, targeted tes
Blind Scorer
Blind quality scorer for skill-improver runs. Spawn explicitly with a rubric dir and target dir — not for gene