Testing & Quality skills

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

crater-devel-review

Crater 全仓库代码审查与 PR 描述:纵览 backend/frontend/cli/charts/docs/website 的变更,按核心规范/优化建议分级反馈,并生成双语 PR 描述。用户要求审查 PR、diff、变更或撰写 PR 描述时使用;开始前须应用 crater-devel-shared。

542 repo starsObserved in 1 repos
Testing & Quality

create-e2e-test

Create E2E test file for a specified module. Use when adding end-to-end tests for controllers or unit tests for services and repositories.

542 repo starsObserved in 1 repos
Testing & Quality

mx-pg-controller-migration

Use when verifying and porting an mx-core controller (Post/Note/Page/Comment/Category/etc.) after the MongoDB→PostgreSQL cutover, or when its data shape no longer matches what api-client and admin-vue3 expect. Triggers on "校验 controller"、"check controller"、"迁移 controller"、"修复迁移后的接口"、"data missing after PG migration"、"related/category 字段丢了" and similar.

542 repo starsObserved in 1 repos
Testing & Quality

mx-review

Review code for MX Space project conventions. Checks NestJS patterns, Drizzle ORM repositories, Zod schemas, API design, etc.

542 repo starsObserved in 1 repos
Testing & Quality

nsys-profiling

Profile GPU workloads with NVIDIA Nsight Systems (nsys). Use this skill when the user says 'profile', 'nsys', 'capture a trace', 'GPU profiling', 'kernel breakdown', 'where is time spent', 'decode is slow', 'prefill is slow', 'TPOT regression', 'TTFT regression', or wants to understand where GPU time is going. Also trigger when the user pastes nsys output and asks for help interpreting it. This skill covers the full lifecycle: capturing traces with the right flags, analyzing kernel/API summaries, detecting tail latency problems, and diagnosing performance regressions.

542 repo starsObserved in 1 repos
Testing & Quality

vllm-bench

Use vllm-bench to benchmark OpenAI-compatible or vLLM serving endpoints, especially multi-turn chat load tests. Use when the user asks for vllm bench, vllm-bench, multi-turn benchmark, chat serving benchmark, TTFT/TPOT/throughput measurement, concurrency sweep, load test, 压测, 多轮压测, or wants help installing, running --help, choosing flags, validating a local OpenInfer/vLLM server, saving JSON results, or interpreting vllm-bench metrics.

542 repo starsObserved in 1 repos
Testing & Quality

QC10_TimeConsistency

时间一致性检查工具。读取被检验表,按时间序列检查数据的时间一致性, 判断相邻时间点的数据变化是否在合理范围内,识别并标记异常数据,最后输出为相同格式的文件。 当用户提到时间一致性检查、时间序列校验、数据变化检查、时序一致性等需求时使用此skill。 即使用户没有说出"时间一致性",只要任务涉及检查数据的时间序列一致性,就应该使用此skill。

541 repo starsObserved in 1 repos
Testing & Quality

QC2_EnumerationFieldCheck

公共基础项枚举校验工具。读取被检验表和标准词典文件,将被检验表中的属性项值与标准词典进行比对, 检查是否超出词典规定的固有词表枚举值范围,超出范围的记录会标记质控标识并输出异常数据。 当用户提到枚举校验、枚举值检查、属性项校验、词表校验等需求时使用此skill。 即使用户没有明确说出"枚举校验",只要任务涉及将被检验数据与标准词典进行比对,就应该使用此skill。

541 repo starsObserved in 1 repos
Testing & Quality

QC4_AssociationRuleCheck

数值关联规则校验工具。读取被检验表,根据用户自定义的条件表达式(类似Hive SQL规则)进行数据校验, 具有关联关系的数据项需满足特定约束条件。不满足条件的数据会标记质控标识并输出异常数据。 当用户提到关联规则校验、数据约束校验、自定义规则校验、条件表达式校验等需求时使用此skill。 即使用户没有说出"关联规则",只要任务涉及根据自定义条件表达式进行数据校验,就应该使用此skill。

541 repo starsObserved in 1 repos
Testing & Quality

QC5_BatchThresholdCheck

批量阈值检验工具。读取被检验表和阈值表,将数据列的值与阈值表中定义的上下限进行比对, 识别并标记超出允许范围(包括上限和下限)或为空值的数据点,最后输出为相同格式的文件。 当用户提到批量阈值检验、阈值表校验、多字段阈值检查、范围校验等需求时使用此skill。 即使用户没有明确说出"批量阈值",只要任务涉及根据阈值表进行多字段范围校验,就应该使用此skill。

541 repo starsObserved in 1 repos
Testing & Quality