agentleFS
elpabloultronelpabloultron/open-legal-chile/.github/copilot-instructions.md

open-legal-chile

Copilot instructions5 starsChanged 47 days agoApache-2.0View on GitHub

  • Commits and pushes

The file

We found no rules to list in this file: it reads as prose or reference rather than instructions.

Files
copilot-instructions.md

Open Legal Chile — GitHub Copilot & Commit Instructions (github/awesome-copilot + commit-commands)

1. Filosofía y Jurisdicción

  • Este repositorio implementa Open Legal Chile, la suite de inteligencia artificial jurídica para el Derecho Continental Codificado de la República de Chile.
  • Prohibición estricta de términos del Common Law (no usar figuras anglosajonas inexistentes en Chile).
  • Ortotipografía académica RAE/ASALE (« », N.°, mayúsculas con tilde preceptiva) y formato obligatorio de citas [BCN - ...], [CS - ...], [Doctrina - ...], [Hugging Face - ...].

2. Protocolo de Commits Atómicos (Conventional Commits + commit-commands)

Todo commit debe seguir el estándar <tipo>(<alcance>): <descripción concisa en español>:

  • Tipos permitidos: feat, fix, perf, docs, refactor, test, chore, ci.
  • Alcances frecuentes: graphify, hf, pjud, baremo, critique, skills, plugin, web, conectores, forense, ci.
  • Cuerpo del commit: Explicar qué se hizo, por qué se hizo y qué pruebas/auditorías lo respaldan.

3. Compuerta Pre-Commit de 9 Capas (.github/workflows/audit.yml)

Antes de ejecutar git commit y git push, verificar siempre:

  1. skills-lock.json sincronizado con los hashes SHA-256 de .agents/skills/*/SKILL.md.
  2. .venv/bin/ruff check . (0 errores).
  3. .venv/bin/bandit -r . -x ./tests,./.venv,./doctrina_raw -s B101,B110,B310,B311,B404,B603 -q (0 alertas).
  4. .venv/bin/vulture . --min-confidence 80 --exclude .venv,tests (0 código muerto).
  5. .venv/bin/mypy --ignore-missing-imports --explicit-package-bases --exclude '(\.venv|doctrina_raw|brag-output)' . (0 errores de tipos).
  6. .venv/bin/pytest tests/test_legal_design.py tests/test_empaquetado.py tests/test_web_actualizada.py (100 % verde).

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.