Dispute Issue Identification logo

Dispute Issue Identification

Community
THUYRan
dispute-issue-identification

Dispute-issue identification means, after legal-element extraction, extracting the issues in dispute from the legal facts and further converting case relationships into questions of legal relationship. It can exclude undisputed matters and effectively focus subsequent analysis on the parties' disputed facts, evidence, and application of law. By further refining disputed issues through fact investigation and evidence review, one can approach the essence of the dispute more deeply and analyze the case more thoroughly.

Overview

PublisherTHUYRan
RepositoryLegal-Skills-Chinese
Skill namedispute-issue-identification
Stars
876
Forks
97
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by THUYRan on GitHub. Read the source before you install it.

Installation

Install the Dispute Issue Identification AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/THUYRan/Legal-Skills-Chinese/tree/main/English/skills/dispute-issue-identification
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/THUYRan/Legal-Skills-Chinese.git /tmp/Legal-Skills-Chinese
mkdir -p .claude/skills
cp -r /tmp/Legal-Skills-Chinese/English/skills/dispute-issue-identification .claude/skills/dispute-issue-identification
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dispute Issue Identification in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dispute Issue Identification on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dispute Issue Identification is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Chinese source (authoritative): ../../skills/dispute-issue-identification/SKILL.md

Dispute Issue Identification

Capabilities

This skill can:

  • Identify disputed issues from case materials.
  • Determine which disputes are factual disputes and which are legal disputes.
  • Convert scattered content into legal questions that provide a foundation for subsequent analysis.

How to Use

Step-by-step instructions:

  1. Identify the parties to the case (two or more).

    Identify the parties' identities and clarify how many parties are involved and who each party is.

  2. Identify each party's claims.

  3. Determine whether the parties' disputes center on facts or on legal evaluation. Clarify the content of the dispute—i.e., where the parties' claims differ. Distinguish between: differences of fact and differences of legal evaluation.

    Factual disputed issues, often also called general disputed issues, are mainly facts about which the parties dispute the formation, modification, or extinction of a legal relationship. For example, in a private lending case, whether the borrower actually received the funds; in a creditor's subrogation dispute, whether the debtor neglected to exercise its own rights in a way that impaired the creditor's claim, and so on.

    The most common legal disputed issues concern the correct interpretation and application of law. Their formulation is more specialized and often intertwined with facts, making boundary-drawing and characterization objectively difficult. When factual disputed issues encounter problems of legal application or evidence rules, they can easily convert into legal disputed issues, including allocation of the burden of proof, evidentiary validity and probative force, interpretation of legal provisions, and correct application of law.

    Accurately grasping the core elements of what the parties are contesting, and appropriately summarizing the disputed issues, not only directly affects the outcome of the case but also has a directional effect on protecting the parties' substantive rights. For example, whether the parties constitute repetitive litigation involves both factual disputes over whether the parties, claims, and subject matter are the same, and legal disputes over how the parties understand each element differently, and directly determines the adjudicative direction of the parties' substantive rights.

  4. Convert disagreements into standardized disputed issues. Convert scattered dispute content into problem statements that have legal-analytical significance. Formulations of disputed issues should be as objective, concise, and adjudicable as possible, avoiding purely emotional or colloquial language.

  5. Assess the hierarchy of different disputed issues. Not all disagreements are equally important; further distinguish core issues, secondary issues, and background disagreements. Specifically:

  • Core issues: questions that directly affect whether a claim is established, whether a defense is established, whether liability is borne, and how legal effects are determined;
  • Secondary issues: usually affect the scope of liability, amount of damages, arrangement of the burden of proof, auxiliary fact-finding, or specific forms of relief;
  • Background disagreements: although contested, they have weaker impact on the adjudicative conclusion and mainly serve narrative supplementation or factual background.
  1. Separately organize the supporting grounds for each party's claims—i.e., which facts, evidence, and legal bases each party relies on to support its position.

    This step usually includes: what key facts the plaintiff's claims rest on; what key facts the defendant's defenses rest on; which evidence each side cites; and which legal norms or legal effects each side's claims attempt to map onto.

  2. Dynamic adjustment check. Disputed issues are not fixed. As litigation progresses, new facts or evidence may appear; disputed issues must be dynamically adjusted based on trial developments, and the parties' views should be sought before the close of trial to ensure the disputed issues accurately reflect the case's core disputes.

Input Format

Expected input forms:

  • Format 1: Case fact materials that have already been preliminarily organized.

    Input may be case materials after legal-fact extraction, including subject facts, conduct facts, temporal facts, result facts, causation, etc. This type of input is suitable for directly conducting disputed-issue identification.

  • Format 2: Case fact narratives that have not undergone legal-fact extraction.

    Input may also be judgment case summaries, trial dispute statements, summaries of advocacy opinions, consultation records, or case materials containing the plaintiff's claims, the defendant's defenses, evidence status, and preliminary legal disagreements. This type of input is suitable for further extracting disputed issues from the factual structure.

Output Format

Will generate:

  • Disputed-issue descriptions:

    Descriptions of disputed issues are generally expressed as interrogative sentences, e.g., "Whether Zhang San constitutes unauthorized possession," "Whether Li Si's acquisition of property has a legal basis." Output may follow a "conclusion → reasons → basis" format.

    Output as a structured list of disputed issues, usually including core disputed issues, secondary disputed issues, and brief explanations, and indicating the main factual disagreements and legal questions corresponding to each issue.

  • Disputed-issue format:

    May output a disputed-issue checklist or table. For complex cases, may also output a chronologically expanded issue structure, suitable for organizing complex cases and visual presentation.

Example Usage

Examples:

  • Example 1:

    Based on the following case materials, identify the disputed issues in this case and distinguish which are factual disputes and which are legal disputes:

    Party A claims that in May 2024 it transferred RMB 100,000 to Party B, with an agreement to repay within one month; Party B contends that the RMB 100,000 was not a loan but cooperative investment funds. Party A demands that Party B return the loan principal and interest; Party B disagrees.

  • Example 2:

    Based on the following sale-of-goods dispute materials, extract core disputed issues suitable for civil claim analysis, and explain which key facts, evidence, and legal questions each disputed issue corresponds to:

    The plaintiff claims that when purchasing a computer on a second-hand platform, the seller clearly stated it was 'brand new and unopened'; the defendant contends it never promised the computer was brand new and only said 'good appearance.' After receiving the goods, the plaintiff discovered repair marks on the motherboard and requests return and refund.

  • Example 3:

    Based on this case summary, organize the disputed issues by the hierarchy 'core issues—secondary issues—background disagreements':

    The plaintiff claims a platform disclosed its mobile number to a third party without consent, causing continuous harassment; the defendant platform contends the information at issue is not sensitive personal information and that the plaintiff failed to prove causation between the harassment and the platform's conduct.

  • Example 4:

    Based on the following trial dispute statement, organize each side's supporting grounds and map them under the respective disputed issues:

    The plaintiff claims the contract was formed and the payment obligation has been performed; the defendant claims the contract has not yet taken effect, and even if it has, non-performance was caused by the plaintiff's prior breach.

Scripts (if applicable)

Best Practices

  1. Identify issues centered on claims and defenses

    Disputed issues should revolve around whether claims are supported and defenses are established. Only disagreements that affect judgments of rights and obligations, allocation of liability, or legal effects should be identified as true disputed issues.

  2. Disputed issues should be formulated as adjudicable questions

    Issue formulations should be as objective, concise, and standardized as possible, avoiding emotional, partisan, or conclusion-presuming language, and should focus on what facts and normative questions need to be decided.

Limitations

  • Limitation 1

    Disputed-issue identification depends on the quality of case-fact organization. If underlying fact extraction is incomplete, the parties' claims are unclear, or evidence materials are severely insufficient, the issue-identification results may be relatively vague.

  • Limitation 2

    This skill cannot replace resolution of the dispute; it can only serve as a preliminary step in legal analysis.

Frequently asked questions

What does the Dispute Issue Identification AI skill do?

Dispute-issue identification means, after legal-element extraction, extracting the issues in dispute from the legal facts and further converting case relationships into questions of legal relationship. It can exclude undisputed matters and effectively focus subsequent analysis on the parties' disputed facts, evidence, and application of law. By further refining disputed issues through fact investigation and evidence review, one can approach the essence of the dispute more deeply and analyze the case more thoroughly.

Why use Dispute Issue Identification on TypingMind?

Because you install it once and use it with any model. Dispute Issue Identification is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dispute Issue Identification in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/THUYRan/Legal-Skills-Chinese/tree/main/English/skills/dispute-issue-identification. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dispute Issue Identification?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dispute Issue Identification?

As many as you like. As long as a model supports skills, you can use Dispute Issue Identification with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dispute Issue Identification AI skill free?

It is published on GitHub by THUYRan. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇