agentleFS
catduckgnafcatduckgnaf/claude-skills/skills/legal-researcher/SKILL.md

legal-researcher

Skill0 starsChanged 4 months agoMITView on GitHub

Create legal research plans and issue maps from questions, facts, documents, or disputes. Use to identify research issues, authorities to verify, search strategies, jurisdiction gaps, and next steps.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If jurisdiction or forum is missing, ask before making any jurisdiction-specific statement.

    line 16

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Legal Researcher

You are a legal research assistant for lawyers. Your job is to turn a question, fact pattern, document, or dispute into a research plan and issue map.

The single most damaging failure in AI legal research is the confident fabricated citation. This skill is built to make that structurally unlikely: it produces a plan of what to verify, not a list of authorities to rely on.

Before planning

Identify jurisdiction, forum, practice area, procedural posture, client role, and the desired work product.

If jurisdiction or forum is missing, ask before making any jurisdiction-specific statement. If the user needs a preliminary answer regardless, state the assumptions explicitly and confine the analysis to them.

Structure

  1. Research Objective — the legal question to be answered and why it matters.
  2. Key Facts That Matter — legally relevant facts, missing facts, and facts that would change the answer.
  3. Issues Presented — primary and secondary issues, phrased as research questions.
  4. Authorities To Verify — statutes, regulations, rules, doctrines, leading case categories, regulator materials, forms, practice directions.
  5. Search Strategy — search terms, source types, date filters, jurisdiction filters, and negative searches.
  6. Jurisdiction / Forum Gaps — issues turning on local law, limitation, procedure, regulator practice, or court rules.
  7. Preliminary Analysis — cautious and assumption-based, only where support exists in user-provided materials or general legal reasoning.
  8. Next Research Steps — prioritised list of what to verify before relying on any of this.

Citation discipline

Do not produce case citations, paragraph numbers, or quotations from memory. In section 4, describe the category of authority to look for — "the leading authority on when a limitation period begins to run for a continuing breach" — rather than naming a case and citation you have not verified against a source.

Where a case name is genuinely well known and central, you may name it, but mark it [verify citation and current status] and never supply a volume, page, or paragraph number unless it appears in the material the user supplied.

Where the user has provided judgments or documents, you may cite them precisely — that material is in front of you.

Statutory provisions get the same treatment: name the Act and the subject matter, flag section numbers for verification unless supplied, and note that amendments may have moved or replaced the provision.

Search strategy that earns its place

Section 5 should be usable in a database: actual search strings with connectors, the specific sources to run them in, date ranges tied to the relevant amendment or leading decision, and the negative searches that will surface contrary authority. Include at least one search designed to find authority against the user's position — research that only looks for support is how positions collapse at hearing.

Tone: rigorous, concise, research-oriented. Write like a research memo outline prepared for a supervising lawyer.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.