Skip to the rows

agentsclimarketplace

Data engineering

Skill Tiao553/sdd-harness-copilot/.github/skills/data-engineering

AI-powered assistant for Harness-based software delivery, helping automate CI/CD, testing, deployments, and pipeline optimization with faster, safer, and more reliable workflows.

Install

npx -y skills add Tiao553/sdd-harness-copilot --skill data-engineering

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

AgentSpec commands for data-engineering. Use /data-engineering-commands + intent. Reads .github/config/grounding.md before executing. Commands: /ai-pipeline, /data-contract, /data-quality, /lakehouse, /migrate, /pipeline, /schema, /sql-review

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

4.0 KB, as published. Nobody here has run it

Data-Engineering Commands

Invoke: /data-engineering-commands + descrição da tarefa

Regras Globais Obrigatórias

Estas regras valem para todos os comandos desta skill.

Grounding e Roteamento

Antes de executar qualquer comando, leia .github/config/grounding.md.
Leia .github/config/routing.json e selecione o agente pelo comando solicitado.
Leia o arquivo do agente selecionado (ver tabela de comandos abaixo).
Carregue KB quick-reference do domínio indicado na tabela de routing (lazy loading).
Toda resposta operacional deve iniciar com o bloco [GROUNDING] exigido por .github/config/grounding.md.

Delegação de Agentes

Cada comando delega a um agente primário. Se o escopo exigir, o agente primário pode escalar para agentes complementares:

Agente primário: executa o core da tarefa
Agente de escalação: ativado para edge cases, cross-domain, ou validação complementar
Cada agente delegado deve ler seu agent file e carregar KB quick-reference se declarado

Caminhos Canônicos

Tipo	Caminho correto
Agentes data-engineering	`.github/agents/data-engineering.{name}.agent.md`
Agentes architect	`.github/agents/architect.{name}.agent.md`
Agentes test	`.github/agents/test.{name}.agent.md`
KB domains	`.github/kb/{domain}/quick-reference.md`
Templates	`.github/sdd/templates/*.md`
Instruções Copilot	`.github/copilot-instructions.md`

Regras de Caminho

Nunca use caminhos .claude/** ou .agents/**.
KB loading é lazy: carregue apenas quick-reference.md do domínio relevante.
Se um domínio KB não existir, registre e continue sem ele.

Constraints

Não inicie fases SDD a partir desta skill.
Não use sintaxe #skill: ou skill:.
Output de comandos que geram código deve ir para ./projects/{feature-name}/ quando em contexto de build.

Comandos Disponíveis

Comando	Descrição	Arquivo	Agente Primário	KB Domains
`/ai-pipeline`	RAG, embeddings, vector DBs, feature stores	`commands/ai-pipeline.md`	`ai-data-engineer`	`ai-data-engineering`, `streaming`
`/data-contract`	Contratos de dados (ODCS), SLAs, governance	`commands/data-contract.md`	`data-contracts-engineer`	`data-quality`, `data-modeling`
`/data-quality`	Regras de qualidade, expectations, test suites	`commands/data-quality.md`	`data-quality-analyst`	`data-quality`, `dbt`, `data-modeling`
`/lakehouse`	Table formats, catalogs, medallion architecture	`commands/lakehouse.md`	`lakehouse-architect`	`lakehouse`, `cloud-platforms`, `spark`
`/migrate`	Migrações de ETL legado para stacks modernos	`commands/migrate.md`	`dbt-specialist` / `spark-engineer`	`dbt`, `spark`, `airflow`, `sql-patterns`
`/pipeline`	Orquestração de pipelines (Airflow, dbt, etc.)	`commands/pipeline.md`	`pipeline-architect`	`airflow`, `dbt`, `data-quality`
`/schema`	Design de schema, modelagem dimensional	`commands/schema.md`	`schema-designer`	`data-modeling`, `sql-patterns`, `data-quality`
`/sql-review`	Review de SQL, performance, anti-patterns	`commands/sql-review.md`	`code-reviewer`	`sql-patterns`, `data-quality`, `dbt`

Escalação Cross-Command

Quando um comando detectar necessidade de outro domínio:

Pipeline + qualidade → delegue checks para /data-quality
Schema + contratos → delegue governance para /data-contract
Migration + lakehouse → delegue table format para /lakehouse

O agente deve informar a escalação e continuar ou pedir confirmação, dependendo do impacto.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.