agentleFS
Sign inStart free
alvarofppalvarofpp/lgpd-skill/CLAUDE.md

lgpd-skill

CLAUDE.md4 starsChanged 4 months agoMITView on GitHub

Claude Code skills for Brazilian data protection and digital law compliance (LGPD). The project scrapes official legislation and ANPD resources, then generates specialized skills from that content. Uses Task as task runner. See Taskfile.yml for all available tasks.

The file

We split this CLAUDE.md into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Commit after every file change.

    line 53
  2. Very specific:

    Always use task commands, never run docker compose or uv directly

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Claude Code skills for Brazilian data protection and digital law compliance (LGPD). The project scrapes official legislation and ANPD resources, then generates specialized skills from that content.

Target Skills

SkillScope
lgpd-complianceLGPD compliance in code: legal bases, consent, anonymization, retention, data subject rights
lgpd-document-generatorGenerate documents: privacy policy, terms of use, ROPA, consent forms
digital-eca-complianceChildren/adolescent data (LGPD Art. 14 + ECA Digital)
lgpd-sanctionsANPD sanctions reference for risk assessment
marco-civil-complianceMarco Civil da Internet + regulatory decree

Commands

Uses Task as task runner. See Taskfile.yml for all available tasks.

task scrape        # Run the scraper via Docker Compose
task scrape:down   # Stop and remove containers
task check         # Run ty type checker
task lint          # Run ruff linter
task lint:fix      # Run ruff linter with auto-fix
task format        # Run ruff formatter
task format:check  # Check formatting without modifying
task test          # Run tests
task install       # Install dependencies
task add -- <pkg>      # Add a dependency
task add:dev -- <pkg>  # Add a dev dependency

Architecture

  • sources.yaml — URLs to scrape, organized by category (legislation, ANPD resources, STF/STJ case law)
  • scraper/ — Python package managed with uv, runs inside Docker
    • main.py — Reads sources.yaml, fetches pages, converts HTML to markdown, saves to output/
    • cleaners.py — Post-processing: removes noise (headers, banners, obsolete text)
    • certs/ — Pinned GlobalSign intermediate cert (STF servers send an incomplete TLS chain; verification stays enabled)
    • pyproject.toml — Dependencies, project metadata, ruff and ty config
  • docker-compose.yml — Mounts sources.yaml as read-only and output/ as writable volume
  • output/ — Generated markdown files from scraping (gitignored)
  • docs/normative-reference.md — Every numeric threshold used by the skills, with verification status against output/; re-verify after each task scrape
  • docs/DECISION_LOG.md — Chronological log of medium decisions

Conventions

  • Communication with the user in pt-BR; all code, variables, and commits in English
  • Commit after every file change; never push
  • Always use task commands, never run docker compose or uv directly

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free