Claude Skills by s977043

Ensure design changes stay consistent across ADRs, diagrams, and specs; decisions are traceable; and drift is explicitly managed.

Detect missing validation plans (how to verify the design is correct) in design documents and ADRs.

Ensure architecture docs capture availability targets, failover strategy, capacity headroom, and resilience trade-offs for critical services.

Ensure architecture docs define bounded contexts, ownership, and a consistent ubiquitous language to prevent domain drift and coupling.

Detect undefined or inconsistent cache strategies (layers, consistency, invalidation, TTL, failure handling) in design documents.

Ensure architecture/design docs state traffic assumptions, performance budgets, resource limits, and cost risks for critical paths.

Ensure architecture updates document affected stakeholders, notification plan, and deprecation/retirement signals to keep knowledge aligned.

Generate React/Next.js component test skeletons (RTL) from specifications.

Generate PHP/Laravel (PHPUnit) test skeletons from specifications.

Generate generic React component test skeletons (RTL) from specifications.

Generate Remix loader/action and route component test skeletons.

Generate Python/pytest unit test skeletons from specifications.

Generate TypeScript unit test skeletons (Jest/Vitest) from specifications.

Generate Vue.js component test skeletons (Vue Test Utils) from specifications.

.river-review.{yaml,json} の context.budget / ranking / reviewMode 設定をモデル仕様とリポジトリ規模に合わせて調整するレビュー観点。

Ensure designs define data flow, state ownership, consistency boundaries, and cross-boundary writes to prevent drift and incidents.

Ensure data model/DB designs cover constraints, integrity, indexes, migrations, rollback, and operational impacts.

Ensure architecture docs define RPO/RTO, failover paths, data consistency, and DR drillability.

新規 skill SKILL.md PR で `fixtures/` と `eval/` の happy-path × guard ペアが揃っているかを確認し、欠けている場合は eval cycle (#688) に乗せる手順を案内する。

Ensure event-driven designs specify delivery guarantees, ordering, idempotency, schema evolution, and replay/backfill strategy.

Ensure designs document third-party dependencies, SLAs, quotas, failure modes, and vendor lock-in mitigation.

Ensure designs specify failure modes, timeouts, error contracts, and observability for critical flows.

Ensure cross-service integration defines contracts, ownership, failure handling, versioning, and rollout/rollback expectations.

Reviews Laravel migrations for destructive operations, change() dropping modifiers, locking index creation on large tables (PostgreSQL), and asymmetric down().

Ensure design/ADR changes include a concrete migration plan, rollout strategy, rollback conditions, and compatibility considerations.

スキーマ/データ移行の安全性を framework 非依存で審査する。破壊的スキーマ変更・ロック誘発・backfill・ロールバック可逆性・expand-contract の段階適用を、prisma / typeorm / Rails / Django / Alembic / 生 SQL などに横断適用する。

マルチテナント前提の設計差分から、テナント分離（データ/権限/リソース/障害影響）の抜けや越境リスクを検出

Ensure OpenAPI specs define consistent request/response schemas, error model, auth, pagination, and backward compatibility.

Ensure designs define operability basics: SLO/SLI, monitoring, alerting, on-call actions, and incident handling expectations.

実装計画（plan.md / pbi-input.md）に含まれる危険操作・触れてはならないスコープ・人間承認必須条件を検出し、AI 自律実行前のゲートとして機能する

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

River Review の artifact / memory / log に対して、retention 設定 + hard guards + excludes から決定論的に KEEP/REMOVE を判定する GC skill

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

運用で発見されたレビューパターン (findings / retrospective) を分析し、新 skill への昇格候補 / 既存 skill 更新候補 / 人間判断が必要な項目に分類する

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

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

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

変更が将来インシデントや技術的負債を引き起こすと仮定し、その原因と経路を逆算して設計の盲点を可視化する

Ensure requirement docs define scope, terminology, acceptance criteria, edge cases, and non-functional requirements.

Applies standard AI review policy guidelines for upstream (design) phase reviews.

Review data retention, deletion, backup residency, and cross-border data transfer.

Ensure designs define trust boundaries, authn/authz responsibilities, and propagation of identity/claims across services.

A minimal agent skill without id or category

A rich agent skill with extra metadata