Testing & Quality skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
extension-troubleshoot
Diagnose and fix piclaw extension issues (imports, DB init errors, watcher perms), update skel, and restart safely.
bpa-rules
Interactive BPA rule generation for Power BI semantic models; guided discovery, model investigation, and expert rule authoring. Automatically invoke when the user mentions "BPA rule", "Best Practice Analyzer", or asks to "create a BPA rule", "audit BPA rules", "recommend BPA rules", "set up BPA for my team", "check model for best practices", "validate BPA rules", "improve a BPA expression".
review-report
Actionable feedback on the quality, usage, and effectiveness of Power BI reports. Automatically invoke when the user asks to "review a report", "audit a report", "report usage analysis", "report health check", "find unused reports", "check if a report is being used", "assess report performance", "evaluate report quality".
dax
DAX performance optimization for semantic models. Automatically invoke when the user asks to "optimize DAX", "fix slow DAX", "DAX performance", "tune a measure", "debug a measure", "DAX anti-patterns", or mentions slow queries, server timings, or DAX authoring.
increase-coverage
Systematic guidelines for executing code coverage tools, analyzing gaps in testing, and implementing targeted tests to maximize code coverage across the reactive framework.
signals-lint
Standardized compiler diagnostics, static analysis lints, and automated IDE quick-fixes.
review-responsibility
EC-CUBE 4.4 で実装・改修したコードを実装直後に自己レビューする全層チェックリスト。「責務分離を確認して」「実装後のレビューをして」「Fatコントローラ/Fatサービスになってないか見て」「レイヤ違反がないか確認して」「認可/CSRF/XSSの抜けを確認して」「リファクタの観点を出して」などと言われたとき、またはコントローラ/サービス/フォーム/テンプレート等の実装・改修が一区切りついた直後に使用する。責務分離・セキュリティ・レイヤ違反を横断的に点検する。
cavekit-validation-first
Validation-first design for Cavekit — every kit requirement must be automatically verifiable. Six-gate validation pipeline, phase gates, merge protocol, completion signals, acceptance criteria patterns. Use when designing acceptance criteria, wiring CI gates, or debugging why an agent is producing output that nobody can verify.