Test design, vulnerability assessment, and quality assurance (13K skills)
Auditoria e evolucao do ecossistema de skills. Qualidade de codigo, seguranca, custos, gaps, duplicacoes, dependencias e relatorios de saude.
The English summary is being prepared. Showing the original description.
Audit a project and recommend the highest-value skills to add or update.
The English summary is being prepared. Showing the original description.
Measurement-driven model router for Claude Code. Routes Haiku/Sonnet/Opus per task class, logs every routed task with real $ numbers, and A/B tests cheaper tiers before you trust the savings.
The English summary is being prepared. Showing the original description.
Answer repository questions grounded entirely in source code evidence. Use when user asks a question about the codebase, user wants to understand a specific file, function, or component, or user asks "how does X work" or "where is Y defined".
The English summary is being prepared. Showing the original description.
Scaffolds eval.yaml test files for agent skills in the dotnet/skills repository. Use when creating skill tests, writing evaluation scenarios, defining assertions and rubrics, or setting up test fixture files. Handles eval.yaml generation, fixture organization, and overfitting avoidance. Do not use for running or debugging existing tests nor for skills authoring.
The English summary is being prepared. Showing the original description.
Ship current branch — CI, SonarCloud, code review, security review, fix all issues, merge. Assumes code is already committed and pushed.
The English summary is being prepared. Showing the original description.
Review data retention, deletion, backup residency, and cross-border data transfer.
The English summary is being prepared. Showing the original description.
TDD を主張する実装の RED/GREEN/REFACTOR VERIFY 証跡（tdd-ledger）の妥当性を検査し、フェーズ順序・exitCode・test-cases との対応の欠落や偽装を検知する
The English summary is being prepared. Showing the original description.
実装差分が plan / todo / test-cases アーティファクトの方針と一致しているかを検査し、逸脱・漏れ・意図外変更を検知する
The English summary is being prepared. Showing the original description.
既存のレビュー結果 (review-self / review-external) を再点検し、漏れ・誤検知・ハルシネーション・根拠欠落を検出する W チェック skill
The English summary is being prepared. Showing the original description.
pbi-input, plan, todo, test-cases 間の整合性をチェックし、実装着手前の仕様漏れを検知する
The English summary is being prepared. Showing the original description.
Generate Vue.js component test skeletons (Vue Test Utils) from specifications.
The English summary is being prepared. Showing the original description.
Generate TypeScript unit test skeletons (Jest/Vitest) from specifications.
The English summary is being prepared. Showing the original description.
Generate Python/pytest unit test skeletons from specifications.
The English summary is being prepared. Showing the original description.
Generate React/Next.js component test skeletons (RTL) from specifications.
The English summary is being prepared. Showing the original description.
Evaluates downstream tests for coverage and edge cases.
The English summary is being prepared. Showing the original description.
PRテンプレートの必須項目（日本語記載、Diátaxis、検証コマンド、チェックリスト）が明確かを確認し、抜けや誤解を生む文言を指摘する
The English summary is being prepared. Showing the original description.
Generate PHP/Laravel (PHPUnit) test skeletons from specifications.
The English summary is being prepared. Showing the original description.
Generate Remix loader/action and route component test skeletons.
The English summary is being prepared. Showing the original description.
Generate generic React component test skeletons (RTL) from specifications.
The English summary is being prepared. Showing the original description.
Detects Vitest test-isolation hazards: unrestored vi.spyOn/vi.mock without afterEach cleanup or restoreMocks config, un-awaited resolves/rejects assertions, and shared mutable module state across tests.
The English summary is being prepared. Showing the original description.
Checks Next.js Server Actions ('use server') for missing authentication/authorization before mutations, missing input validation, and untrusted client-supplied IDs — treating each action as a public HTTP endpoint.
The English summary is being prepared. Showing the original description.
コミット/PR の「全部置換した」「-N%削減」等の完了主張を grep で反証できる残骸や best/typical/worst 試算で検証し、抽出・集約リファクタでは並列度(Promise.all)/fast-path/遅延評価の性能特性退行と、Map/Set 集約キーの cross-kind 衝突による検出漏れも監査する
The English summary is being prepared. Showing the original description.
Review whether the PR description is review-ready and consistent with the diff (Why/What, impact, tests, linked issues).
The English summary is being prepared. Showing the original description.