ai-inventory
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer,…
Build a deposition outline for a witness — pull their documents from the eDiscovery platform, organize topics around the case theory, and surface impeachment material. Use when the user says "depo prep for [witness]", "build a depo outline", or "prepare for [name]'s deposition".
$ npx -y skills add anthropics/claude-for-legal --skill deposition-prep --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/deposition-prepContext preview
The summary Claude sees to decide when to auto-load this skill.
Build a deposition outline for a witness — pull their documents from the eDiscovery platform, organize topics around the case theory, and surface impeachment material. Use when the user says "depo prep for [witness]", "build a depo outline", or "prepare for [name]'s deposition".
name: deposition-prep description: Build a deposition outline for a witness — pull their documents from the eDiscovery platform, organize topics around the case theory, and surface impeachment material. Use when the user says "depo prep for [witness]", "build a depo outline", or "prepare for [name]'s deposition". argument-hint: "[witness name]"
1. Load `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` → case theory, key facts. 2. Follow the workflow and reference below. 3. Pull docs authored by / mentioning witness from eDiscovery platform. 4. Build outline: background, key docs, topics tied to theory, impeachment material.
---
If the user's jurisdiction includes England & Wales and they're asking for a trial witness statement for the Business & Property Courts (or any CPR-governed proceeding), PD 57AC applies. The statement must be in the witness's own words, must not contain argument, must identify the documents the witness used to refresh their memory, and must carry the required confirmation of compliance and the legal representative's certificate.
**Drafting a narrative "as the witness" from a chronology, document set, or your account of the case is exactly what PD 57AC was designed to prevent.** Courts are actively sanctioning AI-assisted witness statement drafting. If you ask me to do it, I won't.
What I WILL do: prepare question prompts to elicit the witness's actual recollection; capture and organize what the witness says (their words, not mine); generate the list of documents they were shown; run a PD 57AC compliance checklist against a statement they've drafted; draft the solicitor's certificate of compliance. I help you get the witness's evidence into the statement. I don't write the evidence.
For US depositions, declarations, and affidavits: different rules, but the same discipline applies. A declaration in the declarant's voice that the declarant didn't write is a credibility problem at best.
Before producing output, check where it's going. If the user has named a destination (a channel, a distribution list, a counterparty, "everyone"), ask whether it's inside the privilege circle. Public channels, company-wide lists, counterparty/opposing counsel, vendors, and clients (for work product) waive the protection. When the destination looks outside the circle, flag it and offer (a) the privileged version for legal only, (b) a sanitized version for the broader channel, or (c) both — don't silently apply a privileged header and then help paste it somewhere the header won't protect it. See the canonical `## Shared guardrails → Destination check` in this plugin's CLAUDE.md.
A depo outline is a map: background → lock in the good facts → confront with the bad ones → box in on the theory. This skill builds the map from the documents and the case theory.
Two rules that govern every citation and every quotation pulled from the record into this outline. Canonical statement lives in the plugin's `CLAUDE.md` shared guardrails; repeated here because an impeachment confrontation built on a misquoted prior statement or a misgrounded transcript cite collapses the impeachment.
**Verbatim quotes from the record must be verbatim.** Never put quotation marks around words attributed to opposing counsel, the witness, another deponent, the court, or any record document unless you have the exact passage in front of you and can cite to it. When you want to characterize what someone said but can't find the exact words:
**Pinpoint cites must support the whole proposition.** If an impeachment point is "the witness said X, Y, and Z on [date]," verify the pinpoint cite supports X AND Y AND Z. If it only supports Z, split the cite — "said X (Tr. p. 10), Y (Tr. p. 12), Z (Tr. p. 15)" — or narrow the proposition. A cite that supports part of an impeachment is the failure mode where opposing counsel asks the witness to read more of the surrounding transcript and your confrontation falls apart.
A depo outline is read aloud in real time. That's oral advocacy, not written. It means:
"Too thorough" for oral work reads as unfocused. If the outline is long because the record is deep, say so and flag where the lawyer should collapse.
`~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` → case theory (theory, pivot fact, key facts for/against), eDiscovery platform.
**Conflicts gate — unbypassable.** Before building an outline, check `~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml` for the matter slug. If the matter is not in `_log.yaml`, refuse and route:
> "I don't see [matter slug] in the matter log. Run `/litigation-legal:matter-intake` first so the conflicts check runs a
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…