Testing & Quality skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

verifier-agent

验证Agent,负责测试代码正确性和性能profiling

255 repo starsObserved in 1 repos
Testing & Quality

ai-diagnostic

AI 기반 다차원 진단 분석 스킬. 기술, 프로세스, 사람, 비즈니스 4차원 병렬 진단을 통해 근본 원인을 식별하고 우선순위별 해결책을 제시합니다. 다음과 같은 요청 시 반드시 이 스킬을 사용하세요: - "시스템 진단", "문제 분석", "원인 파악", "diagnostic", "트러블슈팅" - "근본 원인", "현황 점검", "문제 해결", "시스템 이슈" - 복합적 원인이 의심되는 문제 상황 진단 - 성능 저하, 오류 원인, 병목 파악

254 repo starsObserved in 1 repos
Testing & Quality

dot-audit

Review a file, directory, or inline code against its activated principles. Supports explicit principle override with --with / @group / on syntax. Use when the user runs /dot-audit [target] to check code or docs against quality principles.

254 repo starsObserved in 1 repos
Testing & Quality

new-lint

Create a new splinter lint — a SQL view that checks for a database anti-pattern. Use this skill when the user asks to add a lint, create a new check, implement a linting rule, or extend splinter with a new detection.

254 repo starsObserved in 1 repos
Testing & Quality

pixel-audit

메타·구글 광고 추적 픽셀이 제대로 설치됐는지 점검하고, 광고비를 새게 만드는 설정 실수와 고객 데이터 활용도를 진단한 리포트를 만들어 드립니다. 다음과 같은 요청 시 사용하세요: - "픽셀 설치 제대로 됐는지 점검해줘" - "메타 픽셀이랑 구글 픽셀 검증해줘" - "CAPI(전환 API) 설치 확인해줘" - "iOS 업데이트 이후 전환이 적게 잡히는 것 같아" - "Lookalike 씨앗 품질 봐줘", "VIP 구매자로 유사 타겟 만들어도 되나" - "이메일 리스트 광고에 잘 쓰고 있는지 진단해줘" - "광고비 새는 픽셀 실수 있는지 찾아줘" 자주 하는 픽셀 실수(구매자 미제외·이벤트 정보 누락·CAPI 미설치)와 고객 데이터·유사 타겟 활용도를 점수화해 개선 우선순위를 제시합니다. 진단 보고서 서술 부분은 moai-core:ai-slop-reviewer → moai-content:humanize-korean으로 다듬습니다. [책임 경계] vs moai-marketing:performance-report: 이 스킬=픽셀·데이터 인프라 검증, 저 스킬=광고 성과(ROAS) 분석.

254 repo starsObserved in 1 repos
Testing & Quality

classy-comparisons

Use when comparing CAMB outputs against a local CLASS/classy install on Unix-like systems. Documents how to install the latest released CLASS version, report that version, and run the CLASS binary or Python wrapper.

253 repo starsObserved in 1 repos
Testing & Quality

code-review-flutter

Performs strict code reviews on Flutter projects covering Dart, Pigeon, and the Kotlin (Android) and Swift (iOS) native bridges. Focuses on optimal code, readability, maintainability, deduplication, single-responsibility, straightforward control flow, Flutter best practices, the rule that native layers must not invent hardcoded fallbacks for values the Dart layer or platform SDK already owns, alignment of identifiers and API surface across Dart/Kotlin/Swift, and explicit documentation of platform-specific features. Use when the user asks to "review PR", "do a code review", "review this code", "code review for PR#N", or otherwise requests review of changes in a Flutter plugin, package, or app — including its generated files (`*.g.dart`, `*.freezed.dart`, Pigeon output) and native source under `android/` and `ios/`.

253 repo starsObserved in 1 repos
Testing & Quality

isolate-accuracy-fix

Isolate minimal, physically-scoped accuracy fixes in CAMB. Triages distinct failures, addresses the one the user asked for (or asks which, if unspecified and several exist), delegates diagnosis to an executing sensitivity probe, runs the acceptance matrix on rebuilt code, then delegates a final audit to a read-only checker, and writes a changelog entry per fix. Retains sole patch authority. Use for run_tests.py failures, check_accuracy instability, step-size/switch sensitivity, low-k or recombination-era regressions, and accuracy fixes that must preserve runtime.

253 repo starsObserved in 1 repos
Testing & Quality

browse

Launch a browser to navigate URLs, take screenshots, click elements, and fill forms. Use for visual verification, e2e testing, and interactive debugging.

252 repo starsObserved in 1 repos
Testing & Quality

browser-testing

Patterns and templates for browser-based QA using Playwright. Covers navigation, form interaction, screenshot capture, visual verification, and CAPTCHA/auth handoff.

252 repo starsObserved in 1 repos
Testing & Quality