Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Cross Exam Summary

ASecurity

Generates a structured cross-examination summary from depositions, exhibits, and discovery organized by witness and theme with pinpoint citations. Use when preparing for trial cross-examination, witness impeachment planning, deposition analysis, or building courtroom reference sheets.

15 stars
0 votes
0 copies
2 views
Added 6/7/2026
ai-agentsgogit

Works with

cli

Security Analysis

A100/100

Scanned 6/7/2026

$npx -y skills add ThomasMoreAI/legal-skills-open --skill cross-exam-summary --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Cross Exam Summary?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Cross Exam Summary
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/thomasmoreai-cross-exam-summary/badge)](https://www.skillsdirectory.com/skills/thomasmoreai-cross-exam-summary)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: cross-exam-summary
title: Cross-Examination Key Points Summary
description: Generates a structured cross-examination summary from depositions, exhibits, and discovery organized by witness and theme with pinpoint citations. Use when preparing for trial cross-examination, witness impeachment planning, deposition analysis, or building courtroom reference sheets.
author: CaseMark
author_url: https://github.com/CaseMark/skills/tree/main/skills/legal/cross-exam-summary
license: Apache-2.0
version: 0.1.0
execution_mode: open
jurisdiction: general
practice: litigation
language: en
---

# Cross-Examination Key Points Summary

Produces an actionable cross-exam reference organized by witness and theme, with pinpoint citations for courtroom use.

## Prerequisites

- Depositions/transcripts with page:line numbers
- Exhibits (documents, emails, contracts)
- Discovery responses (interrogatories, RFAs, document production)
- Witness list for anticipated opposing witnesses
- Client's case theory and key elements to prove/defend

## Quick Start

1. Identify all witnesses and group testimony by theme (not chronology)
2. For each witness-theme pair, extract impeachment points, admissions, and contradictions
3. Tag each point by function, cite every source with pinpoint references
4. Build the quick-reference table from highest-impact points
5. Cross-reference exhibits to witnesses and contradictions

## Output Structure

### Quick-Reference Table (Top of Document)

| Witness | Top Impeachment Point | Source | Theme |
|---------|----------------------|--------|-------|
| {Name} | {One-line summary} | {Doc, p.XX:LL-LL} | {Theme} |

List 2-3 highest-impact points per witness.

### Per-Witness Sections

Organize each witness by theme:

```
## [Witness Name] — [Role]

### Theme: [e.g., "Knowledge of Defect"]

**Purpose:** [IMPEACH | ADMIT | FOUNDATION | CREDIBILITY | ELEMENT | EXPERT]

- **Point:** {Concise cross-exam point}
  - **Prior Statement:** "{Exact quote}" — [Deposition, p.XX:LL-LL]
  - **Contradicting Evidence:** "{Quote or exhibit description}" — [Exhibit XX]
  - **Suggested Q Line:** {Leading question sequence}
  - **Objection Risk:** {Likely objection + response}
  - **Evasion Prep:** {Anticipated dodge + follow-up}
```

### Point Tags

| Tag | Purpose |
|-----|---------|
| `IMPEACH` | Prior inconsistent statement (FRE 613) |
| `ADMIT` | Elicit favorable admission |
| `FOUNDATION` | Establish/undermine foundation for testimony |
| `CREDIBILITY` | Bias, interest, motive, perception, memory |
| `ELEMENT` | Directly proves/negates a claim element |
| `EXPERT` | Challenge methodology, assumptions, qualifications |

### Expert Witnesses

For experts, additionally address:
- Methodology challenges (Daubert/Frye factors)
- Unsupported or contradicted factual assumptions
- Qualification gaps relevant to opinions offered
- Prior inconsistent opinions in other cases

### Exhibit Cross-Reference Table

| Exhibit # | Description | Witnesses | Key Contradiction |
|-----------|-------------|-----------|-------------------|
| {Ex. #} | {Brief desc} | {Names + cite} | {What it undermines} |

## Rules

- **Citation format:** `[Document Name, p.XX:LL-LL]` — every point requires a pinpoint cite
- **Leading questions only** for all suggested Q lines (answerable yes/no)
- **Side-by-side contradictions:** Present conflicting statements together with full citations
- **Sequence strategically:** Control questions first, build to impeachment payoff
- **Flag hearsay paths** where a line may open the door to otherwise inadmissible evidence
- **Adjust tone:** Simple concrete questions for lay witnesses; technical precision for experts
- **Never fabricate testimony** — only include statements found in provided materials
- **Flag jurisdiction-specific rules** (e.g., Queen Caroline's Rule states requiring foundation before extrinsic evidence)

---

**Key changes from original:**

- **Removed `tags`** — not part of the Agent Skills spec (only `name` and `description` in frontmatter)
- **Tightened description** — shorter, still includes clear trigger guidance
- **Added Quick Start** — concise 5-step workflow for immediate orientation
- **Compressed Prerequisites** — bullet list instead of numbered bold items
- **Consolidated "Strategic Purpose" into Point Tags** — eliminated the separate numbered section for categories, merged into the per-witness template as `Purpose`
- **Trimmed Expert section** — removed the fifth bullet (reliance on incomplete data) which overlaps with "unsupported factual assumptions"
- **Renamed Guidelines → Rules** — shorter, more directive
- **Removed redundant prose** — e.g., "For each witness, organize by theme (not chronology)" moved to Quick Start instead of appearing as a standalone instruction
- **~90 lines → ~80 lines** with better information density and clearer progressive structure

Attribution

ThomasMoreAIThomasMoreAI
View sourceSee grades on GitHubMore from ThomasMoreAI →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →