ai-inventory
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer,…
Brief a case in your preferred format. In drill-me mode, makes the student state the holding first. Use when the user says "brief [case]", "what's the holding in", "case brief", or pastes a case.
$ npx -y skills add anthropics/claude-for-legal --skill case-brief --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/case-briefContext preview
The summary Claude sees to decide when to auto-load this skill.
Brief a case in your preferred format. In drill-me mode, makes the student state the holding first. Use when the user says "brief [case]", "what's the holding in", "case brief", or pastes a case.
name: case-brief description: > Brief a case in your preferred format. In drill-me mode, makes the student state the holding first. Use when the user says "brief [case]", "what's the holding in", "case brief", or pastes a case. argument-hint: "[case name or citation, or paste the case]"
1. Load `~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md` → outline/brief preferences. 2. Apply the workflow below. 3. Brief in the student's format. If drill-me mode: ask the student to state the holding first.
---
A case brief is a tool for remembering what a case does. This skill makes one in your format — the format you'll actually use in your outline.
Case briefs state holdings, rules, and reasoning. Getting them wrong turns your outline into a false map. The rule for this skill:
A brief built on my guess and your good faith is worse than no brief. Better to err toward "I'm not sure — read it yourself" than to invent.
`~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md` → outline/brief preferences (format, depth), learning style.
A brief you didn't write is a brief you won't remember. Every mode of this skill defaults to scaffolding the student's brief-writing, not to writing the brief.
**What this skill will do in every mode:**
**What this skill will not do, even if asked:**
**Exception** (the only one): the student explicitly overrides — "I've read it three times, I'm stuck on phrasing the holding, just give me a starter sentence so I can rewrite it." Then write a minimal starter with `[VERIFY]` flags and prompt them to rewrite in their own words before it goes into an outline.
**Drill-me mode:** Ask the student to state the holding before anything else: > "You've read this case. What's the holding? One sentence."
If they can't state it, make them read it again. The brief is a memory aid, not a substitute for reading. Then proceed to the scaffold — ask them to state facts, issue, reasoning, and rule in turn. Push back on thin or wrong statements.
**Explain-to-me mode:** Same scaffolded workflow, softer tone. The skill walks the student through each section, offers structural prompts ("a good holding is one sentence, yes/no + the rule"), but still waits for the student to write the content. **Explain-to-me does not mean "write the brief for me."** It means "explain what a good brief looks like, and guide me through writing mine."
If the student pastes the case text in either mode, the skill can extract the court's own language into the Facts/Holding/Reasoning slots — that's not writing-for-them, that's pointing at the source.
The skill produces the **template with questions**, not the filled-in brief. Student fills each section; skill reviews, pushes back, suggests what's missing.
Per the student's format in `~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md`. If none captured, default:
## [Case Name], [cite] **Court:** [court, year] **Facts:** [The facts that matter to the holding. Not every fact — the ones the court relied on. Two to four sentences.] **Procedural posture:** [How did this get here? Trial court ruled X, this is an appeal from that. One sentence.] **Issue:** [The question the court answered. Phrased as a yes/no question.] **Holding:** [The answer. One sentence. Yes/no + the rule.] **Reasoning:** [Why. The court's logic. This is where the law is. Three to five sentences.] **Rule:** [The rule you'd put in your outline. The portable takeaway.] **Notes:** [Dissent worth knowing? Distinguishable on these facts? How professor emphasized it?] --- **Citation check.** The case cite, quoted language, and any supporting authority above were generated by an AI model and have not been verified. Before you rely on them — in a brief, memo, outline entry, or exam answer — look them up on Westlaw, CourtListener, or your school's research tool. AI-generated citations are sometimes fabricated or misquoted.
Per `~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md` — some students want one-line briefs (rule + cite), some want full treatment. Match their format.
If they're a 1L still learning to read cases: fuller briefs. If they're a 3L doing bar prep: rules only.
Reference agents, skills, and data connectors for the legal workflows we see most — in-house commercial, privacy, product, corporate, employment, litigation, regulatory, AI governance, IP, and the learning side of the practice (law school clinics and
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer,…
Run an AI impact assessment — structured intake, risk analysis, regulatory classification per…
Run the cold-start interview — learns your AI governance practice and writes…
Guided customization of your AI governance practice profile — change one thing without…
Manage matter workspaces — new, list, switch, close, or detach (practice-level).…
Keep the AI policy current with practice — weekly sweep of saved AIAs, triage results, and…