agentleFS
PoisoneddietyPoisoneddiety/claude-skills-for-humanities/skills/doctrinal-explainer/SKILL.md

doctrinal-explainer

Skill2 starsChanged 4 months agoMITView on GitHub

Explain a legal doctrine, concept, case, statutory provision, or assigned reading in full depth for note-making and comprehension. Produces the reasoning a summary leaves out — the problem the doctrine solves, the facts that shaped it, the competing formulation, and the boundary conditions. Use this whenever the user asks to explain, unpack, walk through, or make notes on a legal concept, reading, or judgment, even if they just say "explain X". Do NOT use for exam answers, drafting, or research.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Ask which mode only if genuinely ambiguous.

    line 28
  2. Distinctive:

    Every doctrine exists because a court or legislature faced a difficulty that existing tools could not handle.

    line 46
  3. Distinctive:

    Where authority is settled, say so and stop: Do not manufacture a controversy for balance.

    line 98
  4. Distinctive:

    Avoid nominalisation where the actor matters.

    line 125
  5. Distinctive:

    Use at most one em dash per 1,000 words, and only for genuine parenthetical rupture.

    line 129
  6. Distinctive:

    If a point cannot be sourced, say so in the note rather than smoothing over it.

    line 139

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Doctrinal Explainer

A summary tells the reader what a doctrine says. An explanation tells them why it says that, what it was built against, and where it stops. The difference is that after a summary the reader can recite; after an explanation they can argue.

The default failure is compression: stating the operative test without the facts that produced it, listing cases without saying what each one added, and leaving the inferential steps for the reader to reconstruct. Everything below is designed to prevent that.

Depth modes

Full (default when this skill is invoked). Every section below, worked through properly. Expect 900–2,000 words for a single doctrine. Length is not the goal; completeness is, and completeness usually costs that much.

Compact. Sections 1, 2, 4 and 6 only, roughly 400 words. Use when the user says "briefly" or is checking one point rather than building a note.

Comparative. Two or more doctrines run through the schema in parallel, with the divergence made explicit. Use when the user names more than one concept or asks how two relate.

Ask which mode only if genuinely ambiguous. Otherwise default to full — that is why the skill was invoked.

The schema

1. Definition

State the concept in its narrowest accurate form. Then state what it is not — name the adjacent concept it is routinely confused with and give the distinguishing feature. Most misunderstanding in law is boundary confusion between neighbouring doctrines rather than ignorance of either.

Define every term of art on first use, including ones that feel obvious. If the definition itself contains a term of art, define that too. A note that assumes vocabulary is a note that cannot be revised from.

2. The problem it solves

Every doctrine exists because a court or legislature faced a difficulty that existing tools could not handle. Name that difficulty concretely.

This section carries more weight than it appears to. A doctrine detached from its motivating problem is arbitrary and therefore unmemorable, and it cannot be extended to a novel fact pattern, because extension requires knowing what the rule was for. When a doctrine is applied in an exam or a paper to facts it was not designed for, this section is what tells you whether the application is legitimate.

3. Genesis

Identify the case or provision that generated the doctrine, and give the facts — not a gesture at them, the actual facts that made the court reach for this rule rather than an existing one.

Facts are load-bearing. The shape of a doctrine is the shape of the problem in the case that produced it, and later restrictions on the doctrine are almost always traceable to courts noticing that the original facts were narrower than the language used to decide them.

Where a doctrine developed across several cases, give the sequence and state what each decision added, changed, or narrowed. A list of case names with no account of the movement between them is not a doctrinal history.

4. The operative test

Give the test in three layers:

First, as the court actually stated it, quoted or closely paraphrased, with the source.

Second, restated in ordinary language, with each limb separated and the relationship between limbs made explicit — conjunctive or disjunctive, sequential or simultaneous, and who bears the burden on each.

Third, flag any gap between the two. Courts sometimes state a test more broadly than they apply it, and the gap between the formulation and the practice is often where the interesting argument lives.

5. Boundary conditions

Where does the doctrine stop applying? Identify the case that marks each boundary and the reason given. Distinguish boundaries the courts have actually drawn from boundaries that are merely arguable — and say which is which.

Note also the jurisdictional and hierarchical limits: bench strength of the deciding court, whether the point has been referred, whether a coordinate bench has taken a different view.

6. The competing formulation

Where there is a genuine doctrinal disagreement, state the competing position at its strongest, identify who holds it, and give the ground of disagreement. Steelman it. A weak version of the opposing view is useless for writing and worse than useless for a viva.

Where authority is settled, say so and stop. Do not manufacture a controversy for balance. Presenting a fringe position as though it were live is a distortion, and inventing a "critics argue" paragraph where no critics exist is fabrication.

7. Placement in the course arc

What does this build on, and what builds on it? Connect backwards to the concept it presupposes and forwards to the doctrine it enables. Where the user's course materials are available, use their sequence and their vocabulary rather than a generic ordering.

8. Worked application

Take one concrete fact pattern and reason it through end to end, showing each step including the ones that feel obvious. Then, where useful, take a fact pattern that nearly triggers the doctrine but does not, and show precisely where it fails. The near-miss teaches more than the clean case.

Prose requirements

Flowing prose. Numbered lists only where the content is genuinely enumerable — the limbs of a test, a chronological sequence. Do not convert an argument into bullets; an argument in bullets has had its connective tissue removed, which is the exact defect this skill exists to prevent.

State each inferential step. If the reasoning runs A therefore C, insert B. The test is whether the syllogism can be written out from what is on the page; if the minor premise has to be supplied by the reader, it is missing.

Avoid nominalisation where the actor matters. "The court determines whether an agency relationship existed" rather than "the determination of agency". The nominalised form hides who does what, and in law who does what is usually the point.

Use at most one em dash per 1,000 words, and only for genuine parenthetical rupture. Commas, semicolons, colons and full stops handle nearly every case that an em dash is reached for.

Sourcing

Cite what is actually being relied on, at the paragraph level where a specific holding is used. Mark anything recalled but not verified. Where the user has uploaded course notes, readings, or a reading list, treat those as the primary basis and say explicitly when going beyond them — a note built on material the course did not assign is less useful even when it is correct.

If a point cannot be sourced, say so in the note rather than smoothing over it. An explicit gap is a research instruction; a smoothed gap is a future error.

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.