expert-test-runner
Skill0 starsChanged 21 days agoNo licenceView on GitHub
Skill CHUYÊN GIA thực thi + ĐÁNH GIÁ + PHÂN TÍCH kiểm thử tầng chuyên gia (trên UAT) cho mọi hệ thống — generic, domain-adaptive, đa stack. Nhận danh mục case từ `expert-test-writer` (hoặc tự suy nếu thiếu), rồi: (1) phát hiện stack và chọn công cụ phù hợp (property-based hypothesis/fast-check/jqwik; mutation mutmut/cosmic-ray/Stryker/PIT; perf k6/locust; fuzz atheris/jazzer); (2) SINH test asset chạy được (property, metamorphic, golden-master, model-based/stateful, fuzzing, performance, security); (3) CHẠY và thu kết quả; (4) chạy MUTATION TESTING đo bộ test có thật sự bắt bug (kill rate) và chỉ ra mutant sống = lỗ hổng test; (5) QUAN SÁT hệ chạy thật để ĐÁNH GIÁ UI/UX — phát hiện bất thường thao tác màn hình, vô lý luồng dữ liệu (Nielsen + cognitive walkthrough + data-flow sanity) kèm ĐỀ XUẤT CẢI THIỆN cụ thể; (6) phân tích độ phủ bất biến; (7) tổng hợp NHẬN ĐỊNH CHUYÊN GIA + GO/NO-GO + sinh CI. Đây là nơi đặt trí tuệ/phán xét. Output 100% tiếng Việt. Dùng khi user nói "chạy expert test", "test chuyên gia", "mutation test", "đánh giá chất lượng test", "phân tích UX chuyên gia", "kiểm thử sâu" — kể cả prompt tiếng Anh.
In this repository70 other files it gives its agents.
- autoplanSkill
- benchmark-modelsSkill
- benchmarkSkill
- browseSkill
- canarySkill
- carefulSkill
- checkpointSkill
- codexSkill
- connect-chromeSkill
- context-restoreSkill
- context-saveSkill
- csoSkill
- deploySkill
- design-consultationSkill
- design-htmlSkill
- design-reviewSkill
- design-shotgunSkill
- deslop-shared-libsSkill
- devex-reviewSkill
- diagramSkill
- document-generateSkill
- document-releaseSkill
- expert-test-writerSkill
- freezeSkill
- _gstack-commandSkill
- gstack-upgradeSkill
- guardSkill
- hallmarkSkill
- healthSkill
- implementSkill
- investigateSkill
- ios-cleanSkill
- ios-design-reviewSkill
- ios-fixSkill
- ios-qaSkill
- ios-syncSkill
- land-and-deploySkill
- landing-reportSkill
- learnSkill
- make-pdfSkill
- mobile-contextSkill
- office-hoursSkill
- open-gstack-browserSkill
- pair-agentSkill
- plan-ceo-reviewSkill
- plan-design-reviewSkill
- plan-devex-reviewSkill
- plan-eng-reviewSkill
- plan-tuneSkill
- qa-mobileSkill
- qa-onlySkill
- qaSkill
- retroSkill
- reviewSkill
- scrapeSkill
- setup-browser-cookiesSkill
- setup-deploySkill
- setup-gbrainSkill
- shipSkill
- skillifySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.