Dingduff Legal Analysis logo

Dingduff Legal Analysis

Organization
DingDuff
dingduff-legal-analysis

Analyze a legal question rigorously and produce a citation-anchored analysis or proof skeleton — frame the issues, synthesize the governing rule, analyze the facts, organize the proof (CRAC/CREAC), and deploy authority. Use for ANY legal-reasoning task — "what's the law on X," "do we have a claim," "will this hold up," "analyze whether," "what are the issues," "how would we argue this" — and to build the analytical skeleton before drafting any memo, brief, or letter. Pairs with dingduff-legal-writing (which turns the analysis into a finished document) and the dingduff research and citation skills. Detailed method for each step lives in references/ and is loaded as needed. (v1.2)

Overview

PublisherDingDuff
Repositorydingduff-public
Skill namedingduff-legal-analysis
Stars
63
Forks
8
Bundled files
5
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.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Dingduff Legal Analysis 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/DingDuff/dingduff-public/tree/main/plugins/dingduff/skills/dingduff-legal-analysis
  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/DingDuff/dingduff-public.git /tmp/dingduff-public
mkdir -p .claude/skills
cp -r /tmp/dingduff-public/plugins/dingduff/skills/dingduff-legal-analysis .claude/skills/dingduff-legal-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dingduff Legal Analysis 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 Dingduff Legal Analysis 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 Dingduff Legal Analysis 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.

Legal Analysis

This skill is the reasoning engine: it turns a legal question, facts, and retrieved authority into a sound, inspectable analysis — and, when a document will follow, the proof skeleton that dingduff-legal-writing drafts from. It covers issue framing, rule synthesis, fact analysis, proof structure, and the use of authority. Keep this file in context as the spine; pull in a references/ file for the step you're on.

CRITICAL discipline (the whole skill rests on this)

  • Retrieved authority only. Never state a rule, holding, quote, or citation from memory or a search snippet. Retrieve the source first (via dingduff-legal-research, or sources the user supplied), then state it. Every rule and authority in the analysis must trace to a real, retrieved source.
  • Skeleton before prose. Produce the analytical skeleton — conclusion, rule, proof, application, each tagged with a real citation — before writing any polished prose. Fluent prose is where wrong analysis hides; the skeleton forces the reasoning into the open.
  • Calibrate depth to the stakes. Most questions need one disciplined pass. For high-stakes matters — appellate briefs, dispositive motions, formal opinions, novel/first-impression issues — go exhaustive: each reference has a "Going further" section describing the deeper work (full issue inventories, every rule formulation, alternative proof structures, complete authority neutralization).
  • Escalate, don't paper over. If a step exposes a gap — missing authority, an unsettled rule, an unsupported fact — stop and go back (to research, or to the earlier step) rather than writing confident prose over the hole.
  • Predictive vs. persuasive. Predictive analysis (for a memo or client advice letter, "will we win") is objective and weighs both sides. Persuasive analysis (for a brief, motion, or demand letter) orders and frames for advantage but never misstates the law or facts.

The workflow

Run these in order; each consumes the previous step's output. Load the cited reference for method detail.

  1. Frame the issues — work from the user's question and the facts/record they provide; gather or confirm the factual record first, and if determinative facts are missing, ask the user. Then spot, select, narrow, and order the issues; fix the theory of the case and the controlling perspective. → references/issue-framing.md
  2. Get the authority — if the governing law isn't in hand, use dingduff-legal-research until it is, validity-checked. Return here whenever a later step surfaces a new question — research and analysis interleave.
  3. Synthesize the rule — state the governing rule and structure it (elements / factors / standard); reconcile conflicts. → references/rule-synthesis.md
  4. Analyze the facts — identify the legally significant facts, classify them, map them to the rule's elements. → references/fact-analysis.md
  5. Structure the proof — organize each conclusion's proof conclusion-first (CRAC/CREAC), separate rule proof from application, calibrate depth, nest multiple conclusions. → references/proof-structure.md
  6. Deploy authority — analogize/distinguish cases and build statutory-interpretation arguments as you build the proof. → references/applying-authority.md

Output: a labeled proof skeleton (ordered, nested, citation-anchored). When a document will follow — predictive or persuasive — the skeleton is the required hand-off to dingduff-legal-writing. Write the analysis up as the finished deliverable only when the analysis itself is what the user wants (no document to follow).

The proof unit (the spine, in brief)

Every legal conclusion is proved with one unit, in this order — Conclusion (stated first) → Rule → Explanation/rule proof → Application to the facts → Connection-conclusion. Never intermingle rule proof and application: finish proving what the rule is before applying it. Simple, uncontested points get a compressed unit; contested, dispositive points get a full one. Full method, depth calibration, and worked examples in references/proof-structure.md.

References map

Load the one you need:

  • references/issue-framing.md — spotting, selecting, narrowing, framing, and ordering issues; the four-question classification (fact / definition / evaluation / procedure); theory of the case; idea-generation techniques; going further (exhaustive inventory, competing framings, preservation, cross-issue interaction).
  • references/rule-synthesis.md — the four kinds of rules; structuring a rule (elements / factors / standard); inductive synthesis across authorities; reconciling conflicts; weight-of-authority hierarchy; going further (every formulation, definitional architecture, mapped splits, trajectory).
  • references/fact-analysis.md — identifying legally significant facts; classifying by significance, valence, and status; characterizing accurately; mapping facts to rule elements; fact-vs-conclusion discipline.
  • references/proof-structure.md — the CRAC/CREAC proof unit; conclusion-first ordering; depth calibration (conclusory / substantiating / comprehensive; Ignore / Tell / CRAC / CREAC); nesting and umbrellas; predictive vs. persuasive ordering; worked example; going further (alternatives, fallbacks, counter-structures, coherence audit).
  • references/applying-authority.md — using precedent (analogize/distinguish, holding vs. dicta, parentheticals, quotation); statutory argument (text, canons, intrinsic/extrinsic); handling adverse authority; the canons table; going further (every analogy and canon, full neutralization).

Related skills

Input: dingduff-legal-research (gathers and validity-checks the authority, flagging statutory currency for confirmation; interleaves with this skill so analysis guides research and research guides analysis). Next step: dingduff-legal-writing (drafts a document from the skeleton). QC: dingduff-legal-citation-format, dingduff-citation-check.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Dingduff Legal Analysis AI skill do?

Analyze a legal question rigorously and produce a citation-anchored analysis or proof skeleton — frame the issues, synthesize the governing rule, analyze the facts, organize the proof (CRAC/CREAC), and deploy authority. Use for ANY legal-reasoning task — "what's the law on X," "do we have a claim," "will this hold up," "analyze whether," "what are the issues," "how would we argue this" — and to build the analytical skeleton before drafting any memo, brief, or letter. Pairs with dingduff-legal-writing (which turns the analysis into a finished document) and the dingduff research and citation...

Why use Dingduff Legal Analysis on TypingMind?

Because you install it once and use it with any model. Dingduff Legal Analysis 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 Dingduff Legal Analysis in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/DingDuff/dingduff-public/tree/main/plugins/dingduff/skills/dingduff-legal-analysis. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Dingduff Legal Analysis?

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 Dingduff Legal Analysis?

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

Is the Dingduff Legal Analysis AI skill free?

It is published on GitHub by DingDuff. 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 👇