levnikolaevich avatar

Ln 636 Manual Test Auditor

Audits bash test scripts in `tests/manual/` against seven quality dimensions: harness adoption, golden file completeness, config sourcing, fail-fast behavior, template compliance, idempotency, and documentation. It's a specialized L3 worker that scores test evidence quality (X/10) and flags scripts that need rewrites versus ones you can keep. The two-layer detection is smart about context: it won't ding setup scripts for missing golden files or complain about harness adoption when no shared harness exists. Use this when you've got manual test suites producing evidence artifacts and need an audit of whether they're actually reproducible and useful. The severity weighting is reasonable: missing fail-fast or golden files gets flagged HIGH, template divergence is MEDIUM, missing READMEs are LOW.

skills.sh installs
198
GitHub stars
591
last updated
Aug 21, 2026

Install

$ npx -y skills add levnikolaevich/claude-code-skills --skill ln-636-manual-test-auditor --agent claude-code

Installs into .claude/skills of the current project.

Files

Audits bash test scripts in `tests/manual/` against seven quality dimensions: harness adoption, golden file completeness, config sourcing, fail-fast behavior, template compliance, idempotency, and documentation. It's a specialized L3 worker that scores test evidence quality (X/10) and flags scripts that need rewrites versus ones you can keep. The two-layer detection is smart about context: it won't ding setup scripts for missing golden files or complain about harness adoption when no shared harness exists. Use this when you've got manual test suites producing evidence artifacts and need an audit of whether they're actually reproducible and useful. The severity weighting is reasonable: missing fail-fast or golden files gets flagged HIGH, template divergence is MEDIUM, missing READMEs are LOW.

Browse the repository on GitHub

Sponsors

Details

Repository
github.com/levnikolaevich/claude-code-skills
Categories
Testing & QA, Documentation, Code Review & Quality
First seen
Jun 3, 2026

More from levnikolaevich/claude-code-skills

All 128
1sickn33 avatarscreen-reader-testingsickn33/antigravity-awesome-skillsscreen reader testing187skills.sh installs
2vercel-labs avatarbenchmark-e2evercel-labs/vercel-pluginbenchmark e2e187skills.sh installs
3sickn33 avatarsmtp-penetration-testingsickn33/antigravity-awesome-skillssmtp penetration testing186skills.sh installs
4cinience avataralicloud-network-alb-testcinience/alicloud-skillsSmoke test for Alibaba Cloud ALB skill. Validates SDK auth, script compilation, list instances, and health check flows.184skills.sh installs
5levnikolaevich avatarln-637-test-structure-auditorlevnikolaevich/claude-code-skillsAudits test maintainability and structure: layout drift, orphan tests, fragmented duplicates, test-to-source mapping, and domain grouping. Use when auditing tes184skills.sh installs
6nexu-io avatarhtml-ppt-testing-safety-alertnexu-io/open-design红琥珀警示 deck — 顶/底 45° 红黑 hazard 条纹、红色删除线否定标题、L1/L2/L3 绿/琥珀/红 tier 卡片、圆点状态 alert box、policy-yaml 代码块(红左边框 + bad 关键词高亮)、红绿 checklist、Q1 事故堆叠柱状图。适合安全 / 风险 / 事故复盘 / 182skills.sh installs