Lgpd Legal Basis logo

Lgpd Legal Basis

Community
goul4rt
lgpd-legal-basis

Choose and document the lawful basis (base legal) for each personal data processing activity under LGPD Art. 7 (common data) or Art. 11 (sensitive data). Use when the user is designing a new feature that processes personal data, reviewing an existing activity, asking "qual base legal usar", "consentimento ou legítimo interesse", "podemos coletar isso", or running an LGPD audit step. Produces `.lgpd/legal-basis.md` with one entry per activity. Always cite the article. Use whenever someone is about to write code that touches personal data.

Overview

Publishergoul4rt
Repositorylgpd-skills
Skill namelgpd-legal-basis
Stars
107
Forks
15
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by goul4rt on GitHub. Read the source before you install it.

Installation

Install the Lgpd Legal Basis AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/goul4rt/lgpd-skills/tree/main/skills/lgpd-legal-basis
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/goul4rt/lgpd-skills.git /tmp/lgpd-skills
mkdir -p .claude/skills
cp -r /tmp/lgpd-skills/skills/lgpd-legal-basis .claude/skills/lgpd-legal-basis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lgpd Legal Basis in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lgpd Legal Basis on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lgpd Legal Basis is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Base Legal LGPD

Decida e documente a base legal de cada atividade de tratamento antes de qualquer outra coisa. Sem base legal válida, o tratamento é ilícito (Art. 7º e Art. 11 LGPD).

Árvore de decisão

O dado é sensível? (Art. 5º, II — saúde, biometria, religião, política, sindicato, sexualidade, raça, genético)
├── SIM → Art. 11
│   ├── Consentimento específico e destacado (Art. 11, I)
│   └── OU uma das 7 hipóteses sem consentimento (Art. 11, II):
│       (a) obrigação legal, (b) política pública, (c) pesquisa anonimizada,
│       (d) exercício regular de direitos, (e) proteção da vida,
│       (f) tutela da saúde por profissional, (g) prevenção a fraude / segurança em autenticação
│
└── NÃO → Art. 7º — 10 bases:
    I    consentimento (livre, informado, inequívoco, finalidade determinada)
    II   obrigação legal ou regulatória
    III  administração pública (políticas públicas)
    IV   pesquisa por órgão de pesquisa (anonimização sempre que possível)
    V    execução de contrato OU procedimentos pré-contratuais a pedido do titular
    VI   exercício regular de direitos em processo judicial/administrativo/arbitral
    VII  proteção da vida ou incolumidade física
    VIII tutela da saúde por profissional ou autoridade sanitária
    IX   legítimo interesse (Art. 10 — apoio/promoção de atividades, proteção do titular,
         estritamente necessário, transparência, sujeito a LIA e possível RIPD)
    X    proteção do crédito (bureaus, Serasa, SPC)

Regras de ouro

  1. Legítimo interesse e execução de contrato NÃO valem para dados sensíveis.
  2. Consentimento deve ser específico por finalidade — não use "concordo com tudo".
  3. Marketing direto → consentimento (Art. 7º, I) ou legítimo interesse com opt-out (Art. 7º, IX + Art. 10).
  4. Analytics agregada → legítimo interesse OU anonimização (sai do escopo da LGPD).
  5. Pagamento e autenticação → execução de contrato (Art. 7º, V).
  6. Prevenção a fraude → Art. 11, II, g para sensíveis; Art. 7º, IX para comuns.
  7. Dados de crianças → consentimento parental específico (Art. 14, § 1º) + ECA Digital se aplicável.

Workflow

  1. Para cada atividade de tratamento (input vindo de lgpd-data-mapping), preencha uma entrada no template abaixo.
  2. Se a base for legítimo interesse, complete o LIA (Legitimate Interest Assessment) — ver assets/lia-template.md.
  3. Se a finalidade mudar, base legal precisa ser reavaliada e titular informado (Art. 9º, § 2º).
  4. Salve em .lgpd/legal-basis.md no formato do template.
  5. Atualize .lgpd/STATUS.md ao concluir.

Template — .lgpd/legal-basis.md

markdown
# Bases Legais por Atividade de Tratamento

**Última atualização**: {data}

## Atividade: {nome curto}

- **Finalidade**: {específica, determinada — Art. 6º, I}
- **Dados tratados**: {lista}
- **Sensíveis?**: Sim / Não
- **Base legal**: Art. {7º/11} inciso {N} — {nome}
- **Justificativa**: {por que esta base e não outra}
- **LIA**: (se Art. 7º, IX) link para `.lgpd/lia/{slug}.md`
- **Retenção**: {prazo + critério}
- **Revogação possível?**: (consentimento = sim, outras = depende)
- **Última revisão**: {data}

Cláusulas armadilha (revise sempre)

  • "Consentimento" via checkbox pré-marcado → inválido (não é livre).
  • "Concordo com tudo" como base única → inválido (não é específico).
  • Legítimo interesse para dados sensíveis → proibido.
  • "Aceitar para usar o serviço" para finalidades não essenciais → inválido (Art. 9º, § 2º).

Ao terminar, escreva uma seção em .lgpd/STATUS.md:

markdown
## F1 — Legal basis ✓
- {N} atividades mapeadas
- {N} usam consentimento
- {N} usam legítimo interesse (LIA pendente: {lista})
- {N} usam execução de contrato
- Próximo: lgpd-data-mapping

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Lgpd Legal Basis AI skill do?

Choose and document the lawful basis (base legal) for each personal data processing activity under LGPD Art. 7 (common data) or Art. 11 (sensitive data). Use when the user is designing a new feature that processes personal data, reviewing an existing activity, asking "qual base legal usar", "consentimento ou legítimo interesse", "podemos coletar isso", or running an LGPD audit step. Produces `.lgpd/legal-basis.md` with one entry per activity. Always cite the article. Use whenever someone is about to write code that touches personal data.

Why use Lgpd Legal Basis on TypingMind?

Because you install it once and use it with any model. Lgpd Legal Basis is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lgpd Legal Basis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/goul4rt/lgpd-skills/tree/main/skills/lgpd-legal-basis. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Lgpd Legal Basis?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lgpd Legal Basis?

As many as you like. As long as a model supports skills, you can use Lgpd Legal Basis with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lgpd Legal Basis AI skill free?

Yes. It is published on GitHub by goul4rt under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇