/study-plan

name: study-plan
description: >
  Build or update a long-term bar prep (or exam prep) study plan — phases,
  subjects weighted by weakness, daily session schedule, adaptive to session
  history in study-plan.yaml. Use when the user says "build a study plan",
  "plan my bar prep", "schedule my studying", or "how should I study for [X]".
argument-hint: "[--build | --update | --status | --cram]"

/study-plan

1. Load `~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md` → bar jurisdiction, exam format, bar date, weak subjects, target study hours/day, prep course. 2. Load `~/.claude/plugins/config/claude-for-legal/law-student/study-plan.yaml` if it exists. 3. Apply the framework below. 4. Route by flag:

• `--build` (default if no plan exists): walk the inputs gate (exam, subjects, hours/week, days off, methods). Build the phase structure + daily schedule for the first two weeks. Write `study-plan.yaml`.
• `--update` (default if plan exists): re-read `session_history`, adjust subject priorities and weekly_hours, fill in the next stretch of daily schedule.
• `--status`: what's scheduled today / this week, score trend, subjects slipping, next scheduled session per subject.
• `--cram`: force cram mode — 80/20 high-yield prioritization, daily MBE volume, taper last 2-3 days.

5. Before writing: summarize the plan in prose and confirm with the student. Adjust based on their answer. 6. Always sanity-check hours/week against the student's stated life constraints. Over-ambitious plans fail.

---

Purpose

Sitting down to study and not knowing what to study is how weeks disappear. This skill builds a plan — weeks to exam, sessions per day, subjects per week, session types — and then adapts as the student actually does the sessions. It is a living plan, not a calendar export.

It also gives downstream skills (bar-prep, flashcards, drill, irac) a shared schedule to honor, so the student isn't asked "what do you want to study today" every time they open a session.

Confidence discipline

A plan is opinion, not doctrine. The skill states clearly what's an estimate:

• **Time-per-topic estimates** are general guidance (based on typical commercial prep-course weightings). Flag them as estimates — the student's real pace will differ.
• **Subject weightings** are derived from the student's own reported weak subjects and session history. Confident.
• **High-yield-topic prioritization in cram mode** is based on multi-year bar exam release patterns (MBE/MEE subject frequency). Flag any "this is definitely on the exam" claim as `[UNCERTAIN — past frequency is not a prediction]`.

Load context

`~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md`:

• Bar jurisdiction, exam format, bar date
• Current classes (for non-bar use)
• Weak subjects (MBE, essay)
• Prep course
• Target study hours/day

`~/.claude/plugins/config/claude-for-legal/law-student/study-plan.yaml` if it exists — extend, don't overwrite.

Workflow

Step 1: What are we planning for

> What are we building a plan for? > > 1. **Bar exam** (you have a bar date in mind) > 2. **A specific law school exam or set of finals** > 3. **General semester study cadence** (outlining, reading, drilling across all classes)

For (1) bar: read bar date from practice profile, confirm. If no bar date captured, ask. For (2) law school exam: ask which class, what date, what format. For (3) semester: ask for the term-end date as the anchor.

Step 2: Inputs — one at a time, wait for each

**Ask and wait.** Do not bulk all questions into one prompt and move on.

• **Exam date:** confirmed? (If bar: ask for jurisdiction if not in practice profile — study content depends on it.)
• **Subjects to cover:** for bar, read from NCBE subject outline for the exam format (NextGen / traditional UBE / state-specific). For a class, the syllabus. Confirm with student — "any subject I should add or drop?"
• **Strongest subjects:** least priority. Still reviewed, not drilled heavily.
• **Weakest subjects:** most priority. Get more sessions.
• **Hours per week available:** realistic, not aspirational. "I can do 20 hours" is different from "I will do 20 hours for 8 weeks." Ask what they can actually sustain.
• **Life-context sanity check — force it.** After the student gives a number, ask (one question at a time — do not skip):

> You said [N] hours per week. Before I build this, tell me what else is in your week — job (hours/week), family (kids, caregiving), commute, workout, therapy, clinic, anything meaningful. The plan should fit your life, not the other way around. A plan you can't follow is worse than a lighter plan you can.

Wait for the answer. Then sanity-check the stated hours against their reported load:

> That's ~[X] hours/day across [N] study days, on top of [job + family + commute + other]. In my experience that's [realistic / tight / unsustainable]. Want to adjust the hours/week target before I build, or keep them and see how week 1 goes?

Do not skip this step even if the practice profile's target hours number was already captured at cold-start. The profile captures what the student said; the life-context check captures whether it's sustainable. If the check produces a lower number, use the lower number for the plan and note the adjustment in the `confidence_flags` block.

If the student declines to share life context ("just build it"), respect that — but add a `confidence_flags` entry: "Life-context check declined; plan assumes [N] hours/week is sustainable. Revisit at end of week 2 if adherence is below [X]%."

• **Preferred study methods:** multi-select. MBE practice / essays / flashcards / outlining / drilling / re-reading. Weight the schedule toward the methods they say they'll actually do.
• **Days off per week:** rest days matter. Plans that schedule 7/7 days fail in week 3.

Step 2.5: Supplement vs. replace (prep-course users)

If `~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.m