菜单
Designs scheduling, reruns, and backfills safely for data systems. Use when changing orchestration, retries, dependency timing, historical reprocessing, or publish sequencing.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Forces replay-safe rollout plans, reconciliation gates, and rollback paths before executing any data backfill or historical reprocessing. Use when running /backfill, rerunning pipelines, repairing publish windows, or any work that risks double-counting or downstream corruption.
Helps agents classify data engineering work, choose the right preset and skill bundle, and pick the safest next command. Use when starting a session, triaging an ambiguous request, or deciding how to proceed.
Guides agents through resiliency testing for data platforms. Use when designing or running failure drills, recovery validation, failover tests, replay-safety checks, dependency outage exercises, or fault injection for pipelines and publishes.
Guides agents through production data incidents. Use when a pipeline fails, publishes bad data, misses an SLA, partially loads, corrupts state, or requires rollback, replay, or stakeholder communication.
Enforces production Kafka guardrails including non-breaking schema evolution, dead-letter queues for poison messages, and acks=all producer durability. Use when designing or changing Kafka topics, producers, consumers, schema registry policies, or streaming recovery paths.
Guides agents to wire Model Context Protocol servers for live data platform observability including Spark execution plans, OOM diagnosis, Kafka consumer lag, and orchestration run state. Use when agents need cluster metrics, streaming lag, or job diagnostics instead of blind code changes.
| name | orchestration-and-backfills |
| description | Designs scheduling, reruns, and backfills safely for data systems. Use when changing orchestration, retries, dependency timing, historical reprocessing, or publish sequencing. |
Reliable data systems are shaped as much by rerun behavior as by transformation logic. This skill ensures schedules, retries, and backfills are deliberate, safe, and reversible.
Define execution semantics. Specify:
Separate normal runs from backfills.
Historical reprocessing should not silently behave like daily incremental runs unless that has been proven safe.
For /backfill or publish-bound replay, load safe-backfill-and-replay-orchestration first and complete templates/backfill-plan.yaml before execution.
Design the recovery path before rollout. Include:
Estimate cost and blast radius. Backfills can overload warehouses, queues, clusters, or downstream consumers.
Prove the run strategy. Use a dry run, limited slice, or non-production environment when possible.
| Rationalization | Reality |
|---|---|
| "The scheduler will handle retries for us." | Default retries may duplicate writes or hide real data issues. |
| "Backfill is just rerunning the job for older dates." | Historical loads often need different concurrency, checks, and cutover rules. |
| "We can figure out rollback during the incident." | Recovery plans created during outage pressure are usually incomplete. |
