/diligence-issue-extraction

name: diligence-issue-extraction
description: >
  Read VDR documents and extract issues per house categories and materiality
  thresholds, producing findings in house memo format. Use when user says
  "review the data room", "extract issues from [folder]", "diligence review",
  "what's in the VDR", or points at VDR documents.
argument-hint: "[VDR folder path or category name]"

/diligence-issue-extraction

1. Load `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md` + `~/.claude/plugins/config/claude-for-legal/corporate-legal/deals/[code]/deal-context.md`. 2. Use the workflow below. 3. Check `ai-tool-handoff` — if category is bulk and tool is configured, hand off first. 4. Read docs, apply materiality filter, extract per category. 5. Findings in house memo format. Hand off consents to closing checklist.

---

Matter context

**Matter context.** Check `## Matter workspaces` in the practice-level CLAUDE.md. If `Enabled` is `✗` (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: "Which matter is this for? Run `/corporate-legal:matter-workspace switch <slug>` or say `practice-level`." Load the active matter's `matter.md` for matter-specific context and overrides. Write outputs to the matter folder at `~/.claude/plugins/config/claude-for-legal/corporate-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

Purpose

The VDR has 2,000 documents. Somewhere in there are the 30 that matter for the deal. This skill reads documents against the diligence categories and materiality thresholds from `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md`, extracts issues, and writes them in house memo format.

Load context

• `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md` → Diligence structure (categories, materiality thresholds)
• `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md` → Issues memo format (how findings are stated)
• `~/.claude/plugins/config/claude-for-legal/corporate-legal/deals/[code]/deal-context.md` → deal-specific thresholds, VDR location

If deal-context.md doesn't exist, ask which deal this is for.

Workflow

Step 1: Inventory the VDR

If VDR MCP (Box/Intralinks/Datasite) is connected, pull the index. Map VDR folders to diligence request list categories. Note gaps — request list categories with no corresponding VDR content.

## VDR Inventory: [Deal code]

| Request category | VDR folder | Docs | Status |
|---|---|---|---|
| Corporate & Organizational | /01-Corporate | 45 | Reviewed |
| Material Contracts | /02-Contracts | 312 | In progress |
| IP | /03-IP | 89 | Not started |
| [etc.] | | | |

**Gaps:** [Request categories with no VDR content — follow-up request needed]

Step 2: Apply materiality filter

Per `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md` / deal-context thresholds. Don't review everything if the threshold says contracts >$X.

For contracts specifically: sort by stated value (if in filename/metadata) or by counterparty significance. Review top-down until you hit the threshold or the category is exhausted.

Step 3: Extract issues

For each document read, check against the standard diligence concerns for its category:

**Material contracts — standard extraction set:**

• Change of control provision (triggered by this deal? consent required?)
• Assignment restriction (can the contract move to buyer?)
• Exclusivity / non-compete (restricts buyer's business?)
• MFN (most favored nation — pricing constraints)
• Termination rights (can counterparty walk because of the deal?)
• Unusual indemnities or liability exposure

**Corporate — standard extraction set:**

• Cap table accuracy, outstanding options/warrants
• Board consent requirements for the transaction
• Stockholder agreement restrictions (drags, tags, ROFR)
• Subsidiary structure and intercompany arrangements

**IP — standard extraction set:**

• Ownership chain (assignments from founders/employees in place?)
• Open source in the product (copyleft risk)
• Key IP licensed vs. owned
• Pending or threatened IP litigation

**Employment — standard extraction set:**

• Change-of-control severance triggers (parachute cost)
• Key employee retention risk
• Pending employment litigation
• Classification risk (contractors who look like employees)

**Litigation — standard extraction set:**

• Pending matters and reserves
• Threatened claims
• Regulatory inquiries
• Pattern litigation (consumer class actions, etc.)

Step 4: State each finding

> **Source attribution.** Where a finding references a statute, regulation, case, or regulator action — e.g., a change-of-control provision analyzed under an applicable law, an IP ownership gap cited against a specific doctrine, a pending litigation matter with a case citation — tag the citation with where it came from: `[Westlaw]`, `[CourtListener]`, 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 from the VDR, deal-team memos, or outside-counsel feedback. Document-source citations (VDR path, Bates, filename) retain their native reference. Citations tagged `verify` carry higher fabrication risk and should be checked first. Never strip or collapse the tags. > > **When disagreeing with a user's cited statute, quote the text or decline to characterize it.** If the user (or a deal-team note, or a sell-side disclosure) cites a statute for a proposition you don't think is correct, and you don't have the statute text available from a connected research tool or the VDR, do not invent a description of what the statute says. Say instead: "That section doesn't match what I'd expect a [bulk-