Data Tools Skill
netresearch/data-tools-skill
Manipulação segura de dados estruturados com ferramentas especializadas
Ver no GitHubSkill para agentes Claude que ensina manipulação estruturada de dados usando ferramentas especializadas (jq, yq, dasel, qsv, mlr) em vez de processamento frágil com grep/sed/awk. Cobre JSON, YAML, TOML, XML, CSV e TSV com padrões robustos e receitas práticas.
Instalação
npx convez-ai netresearch/data-tools-skill1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Transformar e filtrar arquivos JSON em pipelines
- Editar arquivos YAML (CI/CD, Docker Compose, Kubernetes)
- Converter entre formatos de dados (JSON, YAML, TOML, XML)
- Processar e analisar dados CSV/TSV em larga escala
- Executar operações estatísticas e joins em Miller
Veredito

Skill bem arquitetada que resolve um problema real: substituir manipulações de texto frágeis por ferramentas CLI especializadas. Documentação clara com cookbooks para cada ferramenta. Recomendado para quem trabalha com DevOps, data pipelines ou automação de infraestrutura.
README
A tradução para o português deste README ainda está na fila.
data-tools-skill
AI agent skill for structured data manipulation. Teaches agents when and how to use dedicated tools instead of fragile text processing (grep/sed/awk) on structured formats.
Tools Covered
| Tool | Format | Use Case |
|---|---|---|
| jq | JSON | Query, filter, transform JSON data |
| yq | YAML | Edit CI configs, docker-compose, K8s manifests |
| dasel | JSON/YAML/TOML/XML | Universal selector, format conversion |
| qsv | CSV/TSV | Fast data exploration, filtering, analysis |
| mlr | CSV/TSV/JSON/JSONL/PPRINT/XTAB/NIDX | Name-indexed records, DSL stats/joins, in-place edits |
Core Principle
Never use grep, sed, or awk on JSON, YAML, TOML, XML, or CSV data. These tools treat structured data as flat text and break on multi-line values, nested structures, quoted strings, and encoding differences.
Installation
Marketplace (Recommended)
Add the Netresearch marketplace once, then browse and install skills:
# Claude Code
/plugin marketplace add netresearch/claude-code-marketplace
npx (skills.sh)
Install with any Agent Skills-compatible agent:
npx skills add https://github.com/netresearch/data-tools-skill --skill data-tools
Download Release
Download the latest release and extract to your agent's skills directory.
Git Clone
git clone https://github.com/netresearch/data-tools-skill.git
Composer (PHP Projects)
composer require netresearch/data-tools-skill
Requires netresearch/composer-agent-skill-plugin.
npm (Node Projects)
npm install --save-dev \
@netresearch/agent-skill-coordinator \
github:netresearch/data-tools-skill
Requires @netresearch/agent-skill-coordinator, which discovers the skill in node_modules and registers it in AGENTS.md via a postinstall hook. For pnpm, also allowlist the coordinator's postinstall:
{
"pnpm": {
"onlyBuiltDependencies": ["@netresearch/agent-skill-coordinator"]
}
}
Structure
skills/data-tools/
SKILL.md # Main skill file (tool selection, patterns, anti-patterns)
references/
jq-cookbook.md # Comprehensive jq patterns
yq-cookbook.md # YAML manipulation patterns
dasel-cookbook.md # TOML/XML/universal selector patterns
csv-processing.md # qsv workflows and recipes
mlr-cookbook.md # Miller for JSONL, DSL, stats, joins
License
This project uses split licensing:
- Code (scripts, workflows, configs): MIT
- Content (skill definitions, documentation, references): CC-BY-SA-4.0
See the individual license files for full terms.