mcpbeat Sign in

Law Irac Agent Skill

Apply IRAC (Issue, Rule, Application, Conclusion) method for structured legal analysis. Use this skill when the user needs to analyze a legal question systematically, write a legal memo, evaluate whether a law applies to a situation, or structure a legal argument — even if they say 'does this law apply', 'analyze this legal issue', or 'write a legal analysis'.

5k tokens
context cost
the whole folder, loaded on every use
3
files
instructions only
0
copies elsewhere
how many repositories repackaged it
223
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/asgard-ai-platform/skills --skill law-irac

What comes with it

16 419 bytes besides the instruction
examples/sample_scenario.md
references/taiwan-legal-resources.md

The instruction itself

10 sections, as written by the author

Overview

IRAC is the standard method for structured legal reasoning: identify the legal Issue, state the applicable Rule, Apply the rule to the facts, and reach a Conclusion. It ensures analysis is systematic, complete, and logically rigorous.

Framework

IRON LAW: Issue First, Conclusion Last

NEVER state the conclusion before completing the analysis. IRAC works
BECAUSE it forces you to examine rules and apply them to facts before
reaching a conclusion. Starting with the conclusion and backfilling
the analysis is confirmation bias dressed in legal structure.

The Four Steps

I — Issue: Frame the specific legal question

  • State as a question: "Whether [specific legal question] given [key facts]"
  • Be precise — a vague issue leads to vague analysis
  • There may be multiple issues; address each separately

R — Rule: State the applicable law

  • Statute, regulation, case law, or legal principle
  • Include the specific elements/requirements of the rule
  • If the rule has a test (e.g., 4-factor test for fair use), state all factors

A — Application: Apply the rule to the specific facts

  • This is the core analytical work — match each element of the rule to the facts
  • Address each element/factor separately
  • Acknowledge ambiguity — where facts are unclear, note both possible interpretations
  • Use analogies to precedent cases where available

C — Conclusion: State the result

  • Answer the issue question directly
  • State the degree of confidence (clear, likely, arguable, unclear)
  • Note assumptions that the conclusion depends on

Output Format

# Legal Analysis: {Topic}

## Issue
Whether [legal question] given [key facts].

## Rule
[Applicable law/principle with specific elements]

## Application
### Element 1: [name]
[Analysis of how facts satisfy or fail this element]

### Element 2: [name]
[Analysis...]

## Conclusion
[Direct answer to the issue with confidence level]

Examples

Correct Application

Scenario: Does an employee's social media post constitute grounds for termination under Taiwan's Labor Standards Act?

Issue: Whether an employee's Facebook post criticizing company management constitutes a violation of the employment contract sufficient for termination under Article 12 of the Labor Standards Act.

Rule: Article 12, Subparagraph 4 of the LSA permits termination without notice when an employee "commits a serious breach of the employment contract or violates work rules to a serious degree." Courts apply a proportionality test: the breach must be so severe that the employment relationship cannot reasonably continue.

Application: The post criticized management's decision to cut overtime pay, using strong language but no false statements. Courts have held that employee speech on matters of working conditions receives higher protection. The proportionality test likely fails — criticism of company policy, even if intemperate, is generally not severe enough to justify termination unless it reveals confidential information or constitutes defamation.

Conclusion: Likely not grounds for lawful termination. Confidence: Moderate — depends on specific language used and whether any confidential information was disclosed ✓

Incorrect Application

  • "The employee posted something bad on Facebook, so they should be fired. Here's why..." → Conclusion first, then backfilling analysis. Violates Iron Law: issue first, conclusion last.

Gotchas

  • Multiple issues require separate IRAC analyses: Don't combine three legal questions into one analysis. Each issue gets its own I-R-A-C.
  • Rule statement must be specific: "The law says you can't do that" is not a rule statement. Cite the specific statute, article, or legal principle with its elements.
  • Application is where the work is: Students and practitioners spend too little time on Application and too much on Rule. The rule is usually clear — how it applies to ambiguous facts is the challenge.
  • Counter-arguments strengthen analysis: Address the strongest counter-argument in the Application section. One-sided analysis is weak analysis.
  • This is educational methodology, not legal advice: IRAC is a reasoning framework. Actual legal conclusions require a licensed attorney with jurisdiction-specific expertise.

References

  • For Taiwan legal research resources, see references/taiwan-legal-resources.md

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take asgard-ai-platform/law-irac from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.