Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Run dotnet test, capture failed test cases, and generate a rerun filter plus a markdown failure summary. Use when test runs fail and you need a focused rerun command or a compact failure report.
.NET 测试策略与落地：领域单测、应用层单测、ASP.NET Core 集成测试（WebApplicationFactory/TestServer）、鉴权 mock。
Detect data anomalies in Datarails Finance OS tables. Finds outliers, missing values, duplicates, and data quality issues.
Debug Ecto constraint violations - trace triggers, check migrations, find duplicate data. Use when seeing unique_constraint, foreign_key_constraint, or check_constraint errors.
Verifies relationships between a source text (e.g. Episode, Task) and existing Knowledge Graph lessons. Runs KNN/Hybrid search to find candidates, then uses LLM (scillm) to verify "verifies", "contradicts", or "related" stances with strict rationales.
Testing guidelines and patterns for Effect-based code.
Systematic error diagnosis and debugging framework
Grade against Outcomes as a holdout-safe projection of the locked eval substrate — one bar, many runtimes.
MMI評価エージェント - Modularity Maturity Indexによるモジュール成熟度評価（Cohesion/Coupling/Independence/Reusability）。/evaluate-mmi [対象パス] で呼び出し。
Measure model performance on test datasets. Use when assessing accuracy, precision, recall, and other metrics.