Applied legal reasoning
APM-installable agent skills for Lean 4 and Mathlib4 — proof tactics, math domains, review and research workflows, generic tooling.
npx -y skills add r-irbe/proof-skills --skill applied-legal-reasoningAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
USE FOR: Legal reasoning formalization — statutory interpretation, case-based reasoning, argumentation frameworks, defeasible rules, deontic norms, regulatory compliance, and their connection to provenance chains, governance structures, and formal verification for legal-adjacent AI systems. DO NOT USE FOR: formalising those legal models in Lean (use @lean-applied-reasoning); deontic reasoning specifically (use @ai-causal-deontic); security policy (use @applied-data-information-security). TRIGGERS: statutory interpretation, case-based reasoning, argumentation framework, defeasible rule, deontic norm, legal reasoning, regulatory.
SKILL.md
3.9 KB, as published. Nobody here has run it
Legal Reasoning
Formal frameworks for legal analysis, argumentation, normative reasoning, and their intersection with formal verification and AI governance.
Routing
- USE FOR: Legal reasoning formalization — statutory interpretation, case-based reasoning, argumentation frameworks, defeasible rules, deontic norms, regulatory compliance, and their connection to provenance chains, governance structures, and formal verification for legal-adjacent AI systems.
- DO NOT USE FOR: formalising those legal models in Lean (use @lean-applied-reasoning); deontic reasoning specifically (use @ai-causal-deontic); security policy (use @applied-data-information-security).
- TRIGGERS: statutory interpretation, case-based reasoning, argumentation framework, defeasible rule, deontic norm, legal reasoning, regulatory.
Workflow
- Classify the legal task: statutory interpretation, case-based reasoning, argumentation, or deontic-norm modelling.
- Pick the matching framework (ASPIC+, Carneades, defeasible-logic, deontic-action) from the body.
- Apply the framework; document the argument structure + defeaters.
- Hand off: to
@ai-causal-deonticfor deontic-logic encoding, to@lean-applied-reasoningfor Lean formalisation, to@lean-zettelkasten.
Recovery & STOP
- STOP if the question is about pure deontic logic — delegate to
@ai-causal-deontic. - STOP if the legal regime is jurisdiction-specific and not in the body — escalate to
@research-council. - STOP if security/privacy policy dominates — delegate to
@applied-data-information-security.
Handoffs
- Predecessors:
agent:gateway,skill:lean-research. - Successors:
skill:lean-applied-reasoning,skill:ai-causal-deontic,skill:lean-knowledge-formalization.
Detailed reference
Full content for applied-legal-reasoning lives in
references/applied-legal-reasoning-handbook.md.
Load that file when the skill is convened; the SKILL.md only carries
the dispatch contract and the parts index.
| Section | Topic |
|---|---|
| Part 1 | Legal Reasoning Paradigms |
| Part 2 | Argumentation Frameworks |
| Part 3 | Defeasible Legal Rules |
| Part 4 | Statutory Interpretation |
| Part 5 | Case-Based Reasoning (CBR) |
| Part 6 | Regulatory Compliance Formalization |
| Part 7 | AI & Legal Reasoning |
| Part 8 | Cross-References |
See also
../../references/applied-legal-reasoning-handbook.md— Full handbook (extracted from this skill)../lean-applied-reasoning/SKILL.md— Successor../ai-causal-deontic/SKILL.md— Successor../lean-knowledge-formalization/SKILL.md— Successor