$ loading_
End-of-semester case handoff memos — the mirror of /ramp. Produces per-case transition memos and a cohort summary so the departing cohort hands work to the incoming cohort cleanly. Reads deadlines, client-comms, and case history. Use when the professor or departing students need to wrap up the semester, build transition memos, or offboard a graduating/withdrawing student.
复制安装指令，让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "semester-handoff" 技能： 1. 下载 https://raw.githubusercontent.com/anthropics/claude-for-legal/main/legal-clinic/skills/semester-handoff/SKILL.md 2. 保存为 ~/.claude/skills/semester-handoff/SKILL.md 3. 装好后重载技能，告诉我可以用了
~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md → clinic profile, semester dates, supervision style.~/.claude/plugins/config/claude-for-legal/legal-clinic/deadlines.yaml and ~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[case-id]/log.md per case.~/.claude/plugins/config/claude-for-legal/legal-clinic/handoffs/[semester]/[case_id].md.~/.claude/plugins/config/claude-for-legal/legal-clinic/handoffs/[semester]/_summary.md.Every semester, clinics lose their entire workforce and rebuild. /ramp solves half the problem — it onboards the new cohort. This skill solves the other half: it offboards the departing cohort by producing handoff memos that capture what the next student needs to know about every active case.
Without this, case knowledge walks out the door with the student. The new student starts from the case file and intake summary, which is never enough. Two weeks are wasted re-learning the case before the new student can do anything useful. The client experiences the re-learning as a regression — calls go unanswered while the new student catches up, questions already answered get asked again.
Professor or departing students. The professor runs it to orchestrate the full cohort offboarding; individual students can run it on their own cases if they're transitioning mid-semester (graduation, withdrawal).
~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md → clinic profile, semester, practice areas, supervision style~/.claude/plugins/config/claude-for-legal/legal-clinic/deadlines.yaml → all active deadlines, grouped by case~/.claude/plugins/config/claude-for-legal/legal-clinic/client-comms/[case-id]/log.md (per case) → communications history~/.claude/plugins/config/claude-for-legal/legal-clinic/deadlines.yaml case_ids + client-comms folders)If the clinic doesn't maintain a central active-case list, the skill needs one input: a list of active cases. Ask for it. Don't guess.
For each case:
# Case Handoff — [case name] — [semester ending]
**Case ID:** [case_id]
**Practice area:** [area]
**Outgoing student:** [name]
**Incoming student:** [name or "TBD"]
**Supervising attorney:** [professor]
**Client:** [name or client ID]
---
## Where we are
[One paragraph: current posture. What's been done, what's pending, where the case is heading. If the case is at a natural pause point or between filings, say so.]
## Pending deadlines
*Pulled from `~/.claude/plugins/config/claude-for-legal/legal-clinic/deadlines.yaml`. Incoming student's first job is to confirm these are accurate and owned.*
| Due | Type | Description | Notes |
|---|---|---|---|
| [date] | [type] | [one-line] | [if tight: "URGENT — due within [N] days of semester start"] |
## What's been done
- [Key actions this semester: intake, filings, hearings, major correspondence]
- [Documents produced — with pointers to where they live]
## What's open
- [Decisions pending: e.g., "client hasn't decided whether to accept settlement offer"]
- [Research gaps: e.g., "need to confirm whether [jurisdiction] allows [remedy]"]
…
Ask questions against an open investigation log — what witnesses said, where accounts conflict, what gaps exist, what the strongest evidence is on each issue. Use when the attorney needs to query the investigation record without re-reading every entry.
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer, distributor, authorized representative, product manufacturer) and risk tier (prohibited, high-risk, limited, minimal, GPAI, GPAI+systemic). Role and tier are assessed per system, not per company. Use when the user says "ai inventory", "add an ai system", "what systems do we have", "classify this ai system", "eu ai act register", or "ai system registry".
Draft a firm AI usage policy from published model policies, adapted to your practice profile — a research-and-synthesis tool whose output is a draft for attorney review and adoption, not a finished policy. Use when user says "draft an AI policy", "we need an AI policy", "build an AI usage policy", "our firm needs a GenAI policy", or similar requests to generate a first-cut internal AI policy.
Review vendor AI terms — agreement, addendum, or ToS AI provisions — against your governance positions; flag training-on-data, liability, model changes, and AI policy consistency. Use when user says "review this AI agreement", "check OpenAI terms", "what did we agree to with [vendor]", "vendor sent an AI addendum", "is this AI contract okay", or attaches vendor AI terms.
Route a contract issue to the right approver per the escalation matrix in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`, and draft the ask. Use when the user says "who needs to approve this", "escalate this", "does this need GC sign-off", "route this for approval", or when another skill finds an issue that exceeds the reviewer's authority.
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent counsel review. This skill never concludes a product is clear to launch.