Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Discovery Document Summaries

ASecurity

Summarizes discovery documents (depositions, emails, contracts, interrogatories, medical/financial records) with Bates citations, impeachment flags, timeline extraction, and privilege alerts. Use when summarizing produced documents during discovery or pre-trial phases of U.S. commercial litigation.

22 stars
0 votes
0 copies
0 views
Added 9/20/2026
researchgo

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add lev-os/agents --skill discovery-document-summaries --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Discovery Document Summaries?

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

Security grade badge for Discovery Document Summaries
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/lev-os-discovery-document-summaries/badge)](https://www.skillsdirectory.com/skills/lev-os-discovery-document-summaries)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: discovery-document-summaries
description: Summarizes discovery documents (depositions, emails, contracts, interrogatories, medical/financial records) with Bates citations, impeachment flags, timeline extraction, and privilege alerts. Use when summarizing produced documents during discovery or pre-trial phases of U.S. commercial litigation.
---

# Discovery Document Summaries

Compresses voluminous discovery productions into strategically focused summaries with Bates-cited facts, impeachment opportunities, and privilege alerts.

## Prerequisites

- **Discovery documents** — depositions, emails, contracts, interrogatories, medical/financial records
- **Case context** — operative claims, defenses, key disputed issues
- **Production identifiers** — Bates ranges or document control numbers
- (Optional) **Protective order designations** — confidentiality tiers

## Quick Start

1. Gather case context and identify disputed issues to focus analysis
2. Review documents using the extraction priorities below
3. Produce an executive overview + per-document entries
4. Close with gaps and follow-up recommendations

## Executive Overview

| Field | Content |
|---|---|
| Volume reviewed | Total pages / document count |
| Date range | Earliest to latest document date |
| Document categories | Depositions, emails, contracts, records, etc. |
| Key findings | Top 3–5 most significant evidentiary items |

## Per-Document Entry Format

```
Document ID:     [Bates No. / production identifier]
Date:            [Document date]
Author/Parties:  [Author → Recipient, or contracting parties]
Type:            [Email / Deposition / Contract / Record / etc.]
Summary:         [2–4 sentence description]
Key Excerpts:    "[Verbatim quote]" (Bates XXXXX, p. X)
Legal Relevance: [Claim/defense element addressed]
Flags:           [⚑ Impeachment | ⚐ Privilege | ★ Exhibit candidate | ↔ Inconsistency]
```

**Deposition-specific additions:**

- **Inconsistencies** — prior testimony or documents contradicting this testimony (cite both)
- **Evasions** — verbatim Q&A of avoided/unclear answers with page/line cite
- **Credibility** — strong/weak moments with page/line reference

## Extraction Priorities

Extract in this order:

1. Admissions and denials on disputed facts
2. Intent/knowledge evidence — awareness of risk, obligation, or wrongdoing
3. Timeline anchors — dates establishing sequence or notice
4. Chain of custody / authentication facts
5. Contradiction material — conflicts between documents or witnesses
6. Damages evidence — amounts, loss calculations, financial impact

## Organization Options

| Method | Best for |
|---|---|
| By document type | Large mixed productions |
| Chronological | Fraud, breach, narrative-heavy cases |
| By legal issue | Complex multi-count complaints |
| By witness | Deposition-heavy phases |

## Closing: Gaps and Follow-Up

- **Evidentiary gaps** — documents referenced but not produced
- **Additional discovery** — suggested RFPs, interrogatories, deposition topics
- **Privilege log** — entries worth challenging or monitoring

## Rules

- **Cite everything** — every fact must reference a Bates number; never assert unattributed facts
- **Quote verbatim** for key excerpts; use quotation marks and page/line for all direct quotes
- **Flag privilege** — do not summarize potentially privileged content; flag for attorney review
- **Flag confidentiality** — note CONFIDENTIAL/AEO tiers per protective order
- **State ambiguity** — never resolve unclear or contradictory content by assumption
- **Cross-reference** — link related documents (email → contract → deposition) to surface connections
- **Jurisdiction** — U.S. federal/state civil litigation assumed; flag foreign jurisdiction indicators

---

**Key changes made:**

- **Description** trimmed from 430 to 230 chars — third-person, clear trigger ("Use when summarizing produced documents during discovery or pre-trial")
- **Removed `tags`** — not part of the agent skills spec frontmatter
- **Removed nested numbered headings** (### 1, ### 2, etc.) — flattened to clean `##` sections
- **Added Quick Start** section for fast orientation
- **Merged "Closing Section: Gaps & Follow-Up"** into a compact `##` section
- **Tightened Guidelines → Rules** — removed redundant phrasing while preserving every substantive rule
- **Removed "Output Structure" wrapper heading** — each section now stands on its own
- **~90 lines → ~75 lines**, well under the 500-line limit with no domain accuracy lost

Attribution

lev-oslev-os
View sourceMore from lev-os →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Competitor Analysis

This skill provides comprehensive analysis of competitor SEO and GEO strategies, revealing what's working in your market and identifying opportunities to outperform the competition.

1823 votes

Deep Research

Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review...

452202 votes

Paperclip Distill

Use when an operation issue is a Paperclip cursor-window, distill, or backfill — `operationType: "distill"` or `"backfill"` and the body references a Paperclip source bundle for a project or root issue. Turn raw Paperclip activity into a wiki-insightful project page, decisions log, and history note. This skill exists specifically to replace the stiff, datestamp-heavy templated output that the deterministic distiller produces.

805541 votes

Academic Pipeline

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publi...

452201 votes

Exa Search

Semantic search, similar content discovery, and structured research using Exa API

304951 votes
View all in research →