New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Deposition Prep

by anthropics in anthropics/claude-for-legal

Build a deposition outline for a witness — pull their documents from the eDiscovery platform, organize topics around the case theory, and surface impeachment material.

OfficialApache-2.0Auto-check passed

Install Deposition Prep

skills CLI
$ npx skills add anthropics/claude-for-legal --skill deposition-prep -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install anthropics/claude-for-legal deposition-prep --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/litigation-legal/skills/deposition-prep .claude/skills/deposition-prep && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deposition-prep
GitHub stars
9.6k
Used in
1 other repo
Token cost
~3.5k tokens
SKILL.md length
1,600 words
Files
1
Skills in repo
147
Repo updated
First seen
Licence
Apache-2.0

At a glance

Build a deposition outline for a witness — pull their documents from the eDiscovery platform, organize topics around the case theory, and surface impeachment material.

  • Works in 4 steps: Who is this witness? → Pull their documents → Build topics → …
  • The user says depo prep for [witness]
  • SKILL.md covers Witness statements for England…, Destination check, Purpose and Record fidelity — quotes and…, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Deposition Prep is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. 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".

Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: A suite of plugins for legal workflows. The licence is Apache-2.0.

When your agent uses it

  • The user says depo prep for [witness]
  • Build a depo outline
  • Prepare for [name]s deposition

Example prompts

  • “depo prep for [witness]”
  • “build a depo outline”
  • “prepare for [name]”
  • “/deposition-prep”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Who is this witness?
  2. Pull their documents
  3. Build topics
  4. Write the outline

What it can do on your machine

Read from SKILL.md and the folder at commit 4a6c651. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deposition Prep loads about 3.5k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 1,600 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~3.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from anthropics/claude-for-legal at commit 4a6c651, republished under its Apache-2.0 licence (© anthropics). 1,600 words, ~3,505 tokens.

Download SKILL.mdSave it as .claude/skills/deposition-prep/SKILL.md (or your agent's skills folder).
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]

/deposition-prep

  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.

Deposition Prep

Witness statements for England & Wales — PD 57AC

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.

Destination check

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.

Purpose

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.

Record fidelity — quotes and pinpoints

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:

  • Paraphrase without quotation marks, attributing clearly: "Witness previously testified that X [verify against record — Tr. p. __]."
  • Mark the placeholder: [verify exact quote — record cite pending]
  • Never fill the gap. An invented prior statement destroys the impeachment the moment the witness disavows it and the transcript doesn't back you up. Every [verify exact quote] must be flagged in the reviewer note.

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.

Oral calibration

A depo outline is read aloud in real time. That's oral advocacy, not written. It means:

  • Pick the 3-4 topics that actually matter. Don't try to cover everything — a 200-question outline on a 4-hour depo makes the lawyer skim, and skimming is how lines of questioning get lost mid-sequence.
  • Lead with your strongest confrontation. The witness is freshest at the start, and the transcript's opening pages are the ones a judge or jury is most likely to see.
  • For adverse witnesses: the tightest questions go in the tightest sequences. Everything else is scaffolding.
  • If you're preparing a rebuttal closing after the depo, the calibration is stricter still — the tribunal remembers the first two minutes and the last two.

"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.

Load context

~/.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 and the matter workspace is set up. I won't build a deposition outline on a matter that hasn't been intaken — the conflicts check is the gate."

Do not proceed on an unintaken matter. Intake is what runs conflicts and writes the _log.yaml row this skill reads from.

Workflow

Step 1: Who is this witness?
  • Name, role, relationship to the case
  • Why are we deposing them — what do we need from this witness?

The "why" connects to the theory. If the witness can establish the pivot fact, that's the centerpiece of the outline.

Show full SKILL.md (670 more words)Show less
Step 1a: Witness posture — branch before drafting questions

Prep structure differs by posture. Identify the witness posture before writing a single question:

  • Adverse / hostile — cross-examination style: closed, leading, one fact at a time. Build the box.
  • Friendly / your own — direct-examination style: open questions that let the witness tell the story. Closed leading questions with your own witness are usually improper and undercut credibility with the factfinder.
  • Neutral third-party — mix; often open to get the story, closed to pin specifics.
  • Corporate representative (30(b)(6) or state equivalent) — topic designation, binding-the-entity rules, and the witness's personal-knowledge vs. corporate-knowledge distinction all have distinct rules. Research the applicable deposition rule for the forum and the 30(b)(6) / state-equivalent procedure. Confirm: what topics were designated, who was produced, scope of binding testimony.

Research the applicable deposition rules for the forum and witness type (FRCP 30 / state equivalent, local rules, judge's standing orders on depositions). Cite primary sources. Don't apply a one-size prep structure — the question form, the approach to documents, and the use of impeachment material all depend on posture.

No silent supplement. If a research query to the configured legal research tool (Westlaw, CourtListener, Trellis, Descrybe, or firm platform) returns few or no results for the forum's deposition rules or a cite you need for impeachment, report what was found and stop. Do NOT fill the gap from web search or model knowledge without asking. Say: "The search returned [N] results from [tool]. Coverage appears thin for [rule / authority]. Options: (1) broaden the search query, (2) try a different research tool, (3) search the web — results will be tagged [web search — verify] and should be checked against a primary source before relying, or (4) leave the [UNCERTAIN] marker and stop here. Which would you like?" A lawyer decides whether to accept lower-confidence sources; the skill does not decide for them.

Source attribution. Tag every rule reference, case cite, and authority in the outline with where it came from: [Westlaw], [CourtListener], [Trellis], [Descrybe], or the MCP tool name for citations retrieved from a legal research connector; [web search — verify] for web-search citations; [model knowledge — verify] for citations recalled from training data; [user provided] for citations the partner or senior associate supplied. Document citations (Bates, production numbers) retain their native source. Citations tagged verify carry higher fabrication risk and should be checked before the deposition. Never strip or collapse the tags.

Step 2: Pull their documents

From the eDiscovery platform (Everlaw/Relativity/DISCO if connected):

  • Documents authored by witness
  • Documents sent to or from witness
  • Documents mentioning witness by name
  • Calendar entries and meeting notes with witness present

Organize by date. Flag the hot docs — the ones that matter most for the theory.

Step 3: Build topics

Each topic is a thing you want to establish or explore. Organize around the theory:

Background (always first — lock in uncontroversial facts before the witness is defensive):

  • Role, tenure, responsibilities
  • Reporting structure
  • How they interacted with the key players

Good facts (lock them in before confronting):

  • Facts from ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md → key facts for us, that this witness can establish
  • Documents that support our theory, authored or received by this witness

Bad facts (confront with documents):

  • Facts against us that this witness will be asked about anyway — get your version first
  • Documents that hurt — know how the witness will explain them

Impeachment (if hostile or if they contradict):

  • Prior inconsistent statements (from docs, prior testimony, declarations)
  • Documents that contradict what you expect them to say

The pivot fact:

  • The sequence of questions that establishes (or undermines) the fact the case turns on
  • This is the most carefully constructed section. Question form follows witness posture from Step 1a: tight closed leading on adverse, controlled open on friendly, mixed on neutral. Don't default to one pattern.
Step 4: Write the outline
markdown
[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]

# Deposition Outline: [Witness Name]

**Date:** [depo date]
**Witness role:** [title, relationship to case]
**Witness posture:** [adverse / friendly / neutral / 30(b)(6) or state equivalent] — drives question form
**Applicable deposition rules:** [FRCP 30 / state rule / local rule / standing order — with pinpoint cites] `[UNCERTAIN — verify currency]`
**Why we're taking this depo:** [one sentence — the goal]
**Theory connection:** [how this witness fits the case theory]

---

## I. Background

[Questions — closed, one fact each. Lock in the uncontroversial stuff.]

## II. [Good fact topic]

**Goal:** Establish [fact] for use at summary judgment / trial.

**Documents:**
- [Bates] — [description] — [why it matters]

**Questions:**
[The sequence. Each question closed. Build to the admission.]

## III. [Bad fact topic]

**Goal:** Get the witness's explanation of [bad fact] on our terms before they're prepped for trial.

[Same structure]

## IV. Impeachment material (use if needed)

[Prior statements / documents to confront with, if the witness contradicts]

## V. [Pivot fact sequence]

**Goal:** [The thing the case turns on]

[This is the tightest section. Every question is a yes/no. Every question establishes one fact. Build the box.]

---

## Exhibit list

| # | Bates | Description | Used in section |
|---|---|---|---|

## Marker discipline

Use inline while building and reviewing:
- `[VERIFY: factual assertion]` — any fact not confirmed against the record
- `[UNCERTAIN: legal proposition]` — any legal point (rule, deadline, scope-of-questioning limit) not confirmed against current authority
- `[CITE NEEDED: specific cite]` — record or authority cite pending

## Notes for the attorney

- [Anything the outline doesn't capture — witness demeanor notes, strategic calls to make in the moment]

---

**Privileged / work-product material.** This outline is built from case materials and work product and inherits their protection status. Keep it in the privileged-materials folder, mark it appropriately, and make any distribution decision (co-counsel, client, experts) deliberately — distribution outside the privilege circle can waive protection.

**Cite check any authority relied on.** Rule citations (FRCP 30, state equivalents, local rules, standing orders) and any case law pulled into the outline were generated by an AI model. Verify each against Westlaw, CourtListener, or your research platform — confirm currency and scope before using at the deposition. Source tags on each citation (e.g., `[Westlaw]`, `[web search — verify]`) show where the cite came from; `verify` tags carry higher fabrication risk and should be checked first.

What this skill does not do

  • Take the deposition. The outline is a map; the attorney drives.
  • Predict what the witness will say. It prepares for likely answers, but witnesses surprise.
  • Decide what to ask on the fly. Follow-ups are the attorney's judgment in the room.

© anthropics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in litigation-legal/skills/deposition-prep of anthropics/claude-for-legal.

Open the folder on GitHubat commit 4a6c651

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in anthropics/claude-for-legal, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Deposition Prep next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deposition Prep compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deposition Prep this skillanthropics/claude-for-legal9.6k1 repos~3.5kAutomated safety check: PassApache-2.0
Witnessruvnet/ruflo74k—~1.2kAutomated safety check: PassMIT
Deadline Prepdavila7/claude-code-templates32k—~739Automated safety check: PassMIT
Interview PrepRightNow-AI/openfang18k—~973Automated safety check: PassApache-2.0
Outlines Structured GenerationOrchestra-Research/AI-Research-SKILLs13k9 repos~4kAutomated safety check: PassMIT
Wit AI AutomationComposioHQ/awesome-claude-skills77k3 repos~727Automated safety check: PassNone

Similar skills

  • Witness

    ruvnet/ruflo

    Sign, verify, and track fix-marker regressions over time using a deterministic Ed25519 witness manifest.

    74k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Deadline Prep

    davila7/claude-code-templates

    Generate a structured demo outline from your session's change log and git history.

    32k GitHub stars~739 tokensUpdated today
    DevelopmentAuto-check passed

  • Interview Prep

    RightNow-AI/openfang

    Technical interview preparation expert for algorithms, system design, and behavioral questions

    18k GitHub stars~973 tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed

  • Outlines Structured Generation

    Orchestra-Research/AI-Research-SKILLs

    Uses the Outlines library to constrain model output to a JSON schema, Pydantic model, regex or fixed set of choices when running local models.

    13k GitHub starsUsed in 9 repos~4k tokens
    AI & LLM EngineeringAuto-check passed

  • Wit AI Automation

    ComposioHQ/awesome-claude-skills

    Automate Wit AI tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.

    77k GitHub starsUsed in 3 repos~727 tokens
    Productivity & AutomationAuto-check passed

  • Iot Witness Verify

    ruvnet/ruflo

    Verify witness chain integrity and detect provenance gaps. An agent skill from ruvnet/ruflo.

    74k GitHub stars~160 tokensUpdated today
    Auto-check passed

More from anthropics/claude-for-legal

All 147 skills in this repo

  • Legal Clinic Client Intake

    anthropics/claude-for-legal

    Official

    Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.

    9.6k GitHub starsUsed in 3 repos~3.2k tokens
    Auto-check passed

  • Supervisor Review Queue

    anthropics/claude-for-legal

    Official

    Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.

    9.6k GitHub starsUsed in 3 repos~1.1k tokens
    Auto-check passed

  • Tabular Document Review

    anthropics/claude-for-legal

    Official

    Builds a review grid with one row per document and one column per data point, each cell cited to a verbatim quote, built for M&A diligence and other batch reviews.

    9.6k GitHub starsUsed in 3 repos~4.3k tokens
    Auto-check passed

  • Product Launch Legal Review

    anthropics/claude-for-legal

    Official

    Runs a category-by-category legal review of a product launch from a PRD or tracker ticket, calibrated to your team's framework, and writes a review memo in house format.

    9.6k GitHub starsUsed in 2 repos~5k tokens
    Auto-check passed

  • Legal Skills Registry Browser

    anthropics/claude-for-legal

    Official

    Searches watched registries for community legal skills, shows matches with descriptions and offers the full SKILL.md before anything is installed.

    9.6k GitHub starsUsed in 2 repos~620 tokens
    Auto-check passed

  • Contract Renewal Tracker

    anthropics/claude-for-legal

    Official

    Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.

    9.6k GitHub starsUsed in 2 repos~3.1k tokens
    Auto-check passed

Questions about Deposition Prep

What does Deposition Prep do?

Build a deposition outline for a witness — pull their documents from the eDiscovery platform, organize topics around the case theory, and surface impeachment material. Deposition Prep is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Build a deposition outline for a witness — pull their documents from the eDiscovery platform, organize topics around the case theory, and surface impeachment material.

When should I use Deposition Prep?

Deposition Prep fits situations like: the user says depo prep for [witness]; build a depo outline; prepare for [name]s deposition.

How do I install Deposition Prep in Claude Code?

Run `npx skills add anthropics/claude-for-legal --skill deposition-prep -a claude-code`. Or copy the skill folder (litigation-legal/skills/deposition-prep in anthropics/claude-for-legal) into .claude/skills/deposition-prep in your project. Claude Code loads it when a task matches its description.

How do I install Deposition Prep in Codex?

Run `npx skills add anthropics/claude-for-legal --skill deposition-prep -a codex`. Or copy the skill folder (litigation-legal/skills/deposition-prep in anthropics/claude-for-legal) into .agents/skills/deposition-prep in your project. Codex loads it when a task matches its description.

Can I use Deposition Prep in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anthropics/claude-for-legal --skill deposition-prep -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deposition-prep, .gemini/skills/deposition-prep, .github/skills/deposition-prep and .opencode/skills/deposition-prep in your project.

What does Deposition Prep need to run?

SKILL.md names no scripts, command-line tools or credentials: Deposition Prep is instructions for the agent only.

Does Deposition Prep access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deposition Prep safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deposition Prep use?

Deposition Prep is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deposition Prep use?

About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deposition Prep?

Skills that share tags, products or a category with Deposition Prep: Witness (ruvnet/ruflo, 74k stars), Deadline Prep (davila7/claude-code-templates, 32k stars), Interview Prep (RightNow-AI/openfang, 18k stars) and Outlines Structured Generation (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deposition Prep?

anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-for-legal, which has 9,629 GitHub stars. The repository holds 147 skills in this directory. The repository was last updated on September 29, 2026.

Source: anthropics/claude-for-legal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.