<Skill Name>
Free<What this skill does>
The English summary is being prepared. Showing the original description.
s977043/river-review7Updated Oct 22, 2026
FreePublished on GitHub
Cache Strategy Consistency Guard
Detect undefined or inconsistent cache strategies (layers, consistency, invalidation, TTL, failure handling) in design documents.
The English summary is being prepared. Showing the original description.
See how to installFiles included (9)
- SKILL.md1.9 KB
- eval/promptfoo.yaml1.3 KB
- fixtures/01-undefined-cache-layer-happy.md992 B
- fixtures/02-well-defined-cache-strategy.md2.3 KB
- golden/01-undefined-cache-layer-happy.md1.7 KB
- golden/02-well-defined-cache-strategy.md444 B
- prompt/system.md5.4 KB
- prompt/user.md2.7 KB
- README.md3.4 KB
SKILL.md (original)
Review the instructions the agent will receive before you install.
Pattern declaration
Primary pattern: Reviewer Secondary patterns: Inversion Why: キャッシュ戦略の整合性・無効化・障害対策をチェックリスト型で評価し、設計段階での不整合を防ぐ
Guidance
- Confirm cache layers (CDN/app/DB) and cache keys are specified with owners.
- Check consistency and invalidation strategy per layer, including TTL and refresh triggers.
- Ask for failure/backup behaviour when cache is stale or unavailable.
- Ensure the cache plan aligns with the source of truth and expected SLA.
Non-goals
- キャッシュ実装の好み（ライブラリ選定など）を推測で押し付けない。
Pre-execution Gate / 実行前ゲート
このスキルは以下の条件がすべて満たされない限りNO_REVIEWを返す。
- 差分に設計ドキュメント（設計書/spec/RFC）の変更がある
- 差分にキャッシュ戦略・キャッシュレイヤー・TTL・無効化に関わる記述の追加または変更がある
- inputContextにdiffが含まれている
ゲート不成立時の出力: NO_REVIEW: cache-strategy-consistency — キャッシュ戦略に関わる変更が検出されない
False-positive guards
- 既に整合性・無効化・TTL が別ドキュメントで明示されている場合は重複指摘しない。
Reviews
No reviews yet. Tell others what you thought.
Comments
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
More skills from this repository
画像・ボタン・フォーム要素に適切なアクセシブルネームがあるか確認する。
The English summary is being prepared. Showing the original description.
s977043/river-review7Updated Oct 22, 2026
Ensure ADRs capture context, decision, alternatives, tradeoffs, and follow-ups in a way that prevents future drift.
The English summary is being prepared. Showing the original description.
s977043/river-review7Updated Oct 22, 2026
敵対的分析手法を統合したレビューの entry skill。認知バイアス対策の3手法 （Pre-mortem / War Game / Logic Torturing）と、宣言・主張と実態の乖離を突く claim-vs-actual 検出3パターン（Self-Contradiction / Refactor-Claim Audit / Cross-File Leakage）へルーティングし、通常のレビューでは見えない設計の盲点・ 防御の穴・論理の弱点・宣言と実装のズレを可視化する。
The English summary is being prepared. Showing the original description.
s977043/river-review7Updated Oct 22, 2026
Review changes to the Agent Skills import/export bridge for path safety, round-trip fidelity, and validation correctness.
The English summary is being prepared. Showing the original description.
s977043/river-review7Updated Oct 22, 2026
Checks whether AI-assisted work defines review criteria, accessible context, explicit review loop, human judgment boundary, and feedback capture before delegating to an agent.
The English summary is being prepared. Showing the original description.
s977043/river-review7Updated Oct 22, 2026