← Back to Skills Marketplace
msgnoki

LegalFrance

by msgnoki · GitHub ↗ · v1.0.1
cross-platform ✓ Security Clean
755
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install legalfrance
Description
Assistant juridique français RAG sur codes et lois consolidés (LEGI/DILA). Utiliser pour questions de droit français, recherche d'articles, explication de textes législatifs, synthèse juridique avec citations vérifiables.
README (SKILL.md)

LegalFrance

Assistant juridique FR basé sur un retrieval hybride (FTS + vector) avec citations d'articles.

Première utilisation — initialisation du référentiel

Si les index sont absents (data/chroma_db ou data/fts_index.db manquants), demander confirmation à l'utilisateur avant d'exécuter :

python scripts/ingest.py

⚠️ Cette étape télécharge le corpus LEGI (HuggingFace) et le modèle d'embeddings BGE-M3 (~2 Go au total) puis écrit les index sur disque. Durée estimée : 20–40 min selon la connexion.

Demander : "L'initialisation va télécharger ~2 Go de données (corpus juridique + modèle). Confirmer ?"

Utilisation

Question juridique :

python scripts/one_shot.py "\x3Cquestion>"

Mode structuré JSON :

python scripts/one_shot.py "\x3Cquestion>" --json

Recherche brute dans les codes :

python scripts/search.py "\x3Crequête>" 5

Règles de réponse

  • Citer uniquement les sources retrouvées dans les index
  • Ne jamais inventer d'article ou de décision
  • Si sources insuffisantes : le dire explicitement
  • Format recommandé : Principe → Application → Limites → Sources
  • Disclaimer obligatoire en fin de réponse (information générale, pas conseil juridique personnalisé)

Module jurisprudence (optionnel)

Le module search_jurisprudence (Cour de cassation / Conseil d'État) est optionnel. S'il est absent, le skill fonctionne normalement sur les codes législatifs uniquement.

Usage Guidance
This skill appears to do what it says: build a local RAG assistant over the LEGI dataset and produce SYSTEM+USER prompts for an LLM. Before installing/running: (1) review the scripts yourself (they are included) and run them in an isolated environment/VM if you are concerned; (2) ensure you have ~2+ GB free and sufficient disk space for indexes; (3) be prepared to install Python packages (datasets, chromadb, sentence_transformers) and possibly provide a HuggingFace token if a model requires authentication; (4) note the skill will write persistent indexes under data/, so back up or choose an appropriate working directory; (5) understand the skill supplies a strict system prompt that will control downstream LLM outputs — this is normal for RAG but worth reviewing if you plan to run the LLM with different safety settings.
Capability Analysis
Type: OpenClaw Skill Name: legalfrance Version: 1.0.1 The OpenClaw skill 'legalfrance' is designed as a RAG-based legal assistant. All code and instructions align with this stated purpose. The `SKILL.md` explicitly instructs the AI agent to ask for user confirmation before executing the `scripts/ingest.py` command, which downloads approximately 2GB of legal corpus and embedding models from HuggingFace. This is a critical safeguard against unauthorized resource consumption. The Python scripts use standard practices, including parameterized queries for SQLite, mitigating common injection vulnerabilities. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to subvert the agent's intended behavior or compromise the system. All network and disk operations are directly tied to the skill's legitimate functionality.
Capability Assessment
✓ Purpose & Capability
Name/description match the code and scripts: ingestion from AgentPublic/legi, ChromaDB + SQLite FTS search, RAG prompt builder and helpers. No unrelated env vars, binaries, or external services are requested.
ℹ Instruction Scope
SKILL.md instructs running ingest/search/one_shot scripts and requires user confirmation before the ingest (which downloads ~2 GB). The code builds a strong SYSTEM_PROMPT for the LLM (this triggered a 'system-prompt-override' pattern). That is expected for a RAG assistant, but you should be aware the skill supplies explicit system-level instructions that will guide any LLM used with the prompts.
ℹ Install Mechanism
There is no automated install spec (instruction-only), which lowers automated install risk. Running the scripts requires third-party Python packages (datasets, chromadb, sentence_transformers) and will download a large embedding model (BAAI/bge-m3) and the HF dataset. Downloads come from known hosts (HuggingFace, model hub) rather than arbitrary URLs, but expect heavy network and disk activity.
ℹ Credentials
The skill declares no required environment variables or credentials (good). One caveat: downloading some models or private HF resources can require a HuggingFace token (HF_TOKEN) or similar not declared here; this may cause runtime prompts or failures but is not evidence of hidden credential demands.
✓ Persistence & Privilege
The skill writes indexes to a local data/ directory (chroma_db and fts_index.db) as expected for a local RAG assistant. It does not request always:true or modify other skills or system-wide settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install legalfrance
  3. After installation, invoke the skill by name or use /legalfrance
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Correctifs sécurité : confirmation explicite avant ingest, import search_jurisprudence optionnel (gracieux si absent), SKILL.md révisé.
v1.0.0
Version initiale en français : base RAG juridique FR avec initialisation automatique du référentiel.
Metadata
Slug legalfrance
Version 1.0.1
License —
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is LegalFrance?

Assistant juridique français RAG sur codes et lois consolidés (LEGI/DILA). Utiliser pour questions de droit français, recherche d'articles, explication de textes législatifs, synthèse juridique avec citations vérifiables. It is an AI Agent Skill for Claude Code / OpenClaw, with 755 downloads so far.

How do I install LegalFrance?

Run "/install legalfrance" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is LegalFrance free?

Yes, LegalFrance is completely free (open-source). You can download, install and use it at no cost.

Which platforms does LegalFrance support?

LegalFrance is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created LegalFrance?

It is built and maintained by msgnoki (@msgnoki); the current version is v1.0.1.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463815 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259802 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200680 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191345 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190333 · by oswalpalash

💬 Comments