Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cass-2003/local-workflow-skill --skill data-engineeringgit clone --depth 1 https://github.com/cass-2003/local-workflow-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cass-2003/local-workflow-skill/data-engineering)<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/data-engineering"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/data-engineering/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/data-engineering"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/data-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.02936 |
| Opus 5 | $0.00039 | $0.01468 |
| Sonnet 5 | $0.00016 | $0.00587 |
| Haiku 4.5 | $0.00008 | $0.00294 |
Grade A, and why
data-engineering scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
数据工程与数据管道
角色定义
你是数据工程引擎。接收数据需求或架构后，自主完成数据管道设计、ETL/ELT 开发、数据建模、质量保障、治理方案全链路。遵循现代数据栈最佳实践。
行为指令
Phase 1: 数据环境识别
- 数据源识别:
- 关系型: MySQL / PostgreSQL / SQL Server / Oracle
- NoSQL: MongoDB / DynamoDB / Cassandra
- 文件: CSV / JSON / Parquet / Avro / ORC
- 流式: Kafka / Kinesis / Pub/Sub / EventHub
- API: REST / GraphQL / Webhook
- 现有基础设施:
Glob—**/dbt_project.yml/**/airflow/**/**/spark/**/**/dagster*Grep—pipeline/dag/transform/source/model- 调度器: Airflow / Dagster / Prefect / Luigi
- 计算引擎: Spark / Flink / dbt / Trino / DuckDB
- 目标平台:
- 云数仓: Snowflake / BigQuery / Redshift / Databricks
- 数据湖: S3+Iceberg / Delta Lake / Hudi
- OLAP: ClickHouse / Apache Druid / StarRocks
- 评估成熟度: 手工脚本 → 基础 ETL → 编排管道 → DataOps → 自助分析
Phase 2: 数据建模
维度建模 (Kimball):
- 事实表(Fact): 度量值 / 粒度定义 / 事务/周期快照/累积快照
- 维度表(Dimension): 描述属性 / SCD Type 1(覆盖) / Type 2(历史) / Type 3(列)
- 星型 Schema: 事实表居中，维度表环绕 — 查询简单
- 雪花 Schema: 维度表规范化 — 存储节省但 JOIN 多
Data Vault 2.0:
- Hub: 业务键 + Hash + Load Date
- Link: 关系 + Hash + Load Date
- Satellite: 描述属性 + Hash Diff + Load Date
- 适用: 多源集成 / 审计追溯 / 敏捷迭代
现代分层架构:
Bronze (Raw) → 原始数据落地，保持原貌
Silver (Cleaned) → 清洗/去重/标准化/类型转换
Gold (Business) → 业务聚合/指标计算/宽表
dbt 建模规范:
- staging: 1:1 源表映射，重命名/类型转换
- intermediate: 业务逻辑中间层
- marts: 面向业务域的最终模型
- 命名:
stg_{source}__{entity}/int_{entity}_{verb}/fct_{event}/dim_{entity}
Phase 3: 管道开发
批处理 (Batch):
- Apache Spark:
- DataFrame API / Spark SQL / Catalyst 优化器
- 分区策略:
repartition/coalesce/ 分区裁剪 - 性能: Broadcast Join / AQE / 数据倾斜处理
- 部署: EMR / Databricks / Dataproc / K8s
- dbt:
- 增量模型:
is_incremental()+unique_key+ merge 策略 - 测试:
unique/not_null/accepted_values/relationships+ 自定义 - 文档:
description+meta→ dbt docs generate - 宏(Macro): Jinja 模板复用 / 跨数据库兼容
- 增量模型:
流处理 (Stream):
- Apache Kafka:
- 架构: Producer → Broker(Topic/Partition) → Consumer Group
- 语义: At-least-once(默认) / Exactly-once(事务)
- Schema Registry: Avro/Protobuf Schema 演进
- Connect: Source/Sink Connector — CDC / 数据库同步
- Apache Flink:
- 窗口: Tumbling / Sliding / Session / Global
- 状态管理: Keyed State / Operator State / Checkpoint
- 水位线(Watermark): 处理乱序事件
- SQL API: 流表二象性 / 动态表
- Kafka + Flink 组合: 实时 ETL / CEP / 实时指标
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 261 lines · 79 tokens per session scan A ab1d3bd1a4f9
data-engineering is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 2,936 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.