Guides fault-tolerant workflow design with checkpoints, retries, rollbacks, idempotency, and circuit breakers. Useful for recovery in pipelines and deployments.
npx claudepluginhub joshuarweaver/cascade-code-general-misc-3 --plugin asiaostrich-universal-dev-standardsThis skill is limited to using the following tools:
Guide fault-tolerant workflow design with automatic recovery, checkpoints, and retry strategies.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Guide fault-tolerant workflow design with automatic recovery, checkpoints, and retry strategies.
引導容錯工作流程設計，包含自動恢復、檢查點與重試策略。
| Command | Purpose | 用途 |
|---|---|---|
/durable | Start interactive failure recovery guide | 啟動互動式故障恢復引導 |
/durable --checkpoint | Design checkpoint strategy | 設計檢查點策略 |
/durable --retry | Configure retry policies | 配置重試策略 |
/durable --rollback | Plan rollback procedures | 規劃回滾程序 |
/durable <workflow> | Analyze specific workflow for durability | 分析特定工作流的持久性 |
| Concept | Definition | 定義 |
|---|---|---|
| Checkpoint | Save execution state at known-good points | 在已知正確的位置儲存執行狀態 |
| Retry | Automatically re-attempt failed operations | 自動重新嘗試失敗的操作 |
| Rollback | Revert to last known-good state on failure | 失敗時回復到上一個已知正確狀態 |
| Idempotency | Operations produce same result on re-execution | 操作重新執行時產生相同結果 |
| Circuit Breaker | Stop retries when failure rate exceeds threshold | 失敗率超過閾值時停止重試 |
Failure detected
├── Is it transient? (network, timeout)
│ ├── Yes → Retry with backoff
│ └── No → Is state corrupted?
│ ├── Yes → Rollback to checkpoint
│ └── No → Is it a logic error?
│ ├── Yes → Stop, report, fix code
│ └── No → Escalate with diagnostics
| Strategy | When to Use | Config | 使用時機 |
|---|---|---|---|
| Immediate | Rare glitches, fast ops | max 2 retries | 罕見故障、快速操作 |
| Exponential Backoff | Network/API calls | base 1s, max 30s | 網路/API 呼叫 |
| Circuit Breaker | Downstream service issues | threshold 50%, window 60s | 下游服務問題 |
| Dead Letter | Unrecoverable after retries | max 5 retries then queue | 重試後仍不可恢復 |
| Granularity | Use Case | 使用場景 |
|---|---|---|
| Per-step | Long pipelines (> 5 steps) | 長管線（> 5 步驟） |
| Per-batch | Bulk data processing | 批量資料處理 |
| Per-phase | Multi-phase workflows | 多階段工作流程 |
| Start/End | Short, atomic operations | 短暫的原子操作 |
User: /durable deploy-pipeline
AI: Analyzing deploy-pipeline for durability...
Steps: build → test → deploy → verify
Risk: deploy step has no rollback strategy.
Recommendation: Add checkpoint after test,
configure rollback for deploy using blue-green strategy.
After /durable completes, the AI assistant should suggest:
持久性分析完成。建議下一步 / Durability analysis complete. Suggested next steps:
- 執行
/methodology選擇適合的開發方法論 ⭐ Recommended / 推薦 — Choose suitable methodology- 執行
/commit提交持久化設計變更 — Commit durability design changes
| Version | Date | Changes | 變更 |
|---|---|---|---|
| 1.0.0 | 2026-03-24 | Initial release | 初始版本 |
完整的 AI 行為定義請參閱對應的命令文件：
/durableFor complete AI agent behavior definition, see the corresponding command file:
/durable
CC BY 4.0