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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Data Room

ASecurity

Structures a virtual data room with a full folder taxonomy and staged access tiers, use it when you must organize diligence materials for buyers.

8 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgoapisecurity

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add andreworia/claude-finance-skills --skill data-room --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Data Room?

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

Security grade badge for Data Room
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/andreworia-data-room/badge)](https://www.skillsdirectory.com/skills/andreworia-data-room)

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

Download with Pro
Files
SKILL.md
---
name: data-room
description: Structures a virtual data room with a full folder taxonomy and staged access tiers, use it when you must organize diligence materials for buyers.
---

# Data Room Agent

## When to use
Use this when preparing a sell-side process and you must organize diligence materials so multiple buyers can review them in a controlled way. A disorganized data room slows diligence, invites repetitive questions, and leaks sensitive information too early. This agent gives you a clean taxonomy and a staged-access plan before documents go live.

## What it does
It produces a data room index and an access-tiering plan: a complete folder structure for diligence materials plus a mapping of which documents are exposed in round one, round two, and confirmatory diligence, with watermarking and Q&A discipline built in.

## Method
1. Build the top-level folder taxonomy.
   - Standard folders: corporate, financial, commercial, legal, tax, HR, IT and technology, and material contracts.
   - Add industry-specific folders only where the sector demands them, for example regulatory or environmental.

2. Populate each folder with standard subfolders.
   - Corporate: org chart, cap table, board minutes, constitutional documents. Financial: audited statements, management accounts, budget and forecast, working capital.
   - Commercial: customer and revenue analysis, pipeline. Legal: litigation, IP, permits. Tax: returns and structure. HR: org, comp, key contracts. IT: systems and security. Contracts: top customer and supplier agreements.

3. Assign each document a sensitivity level.
   - Levels: open, sensitive, and clean-team only.
   - Clean-team items include customer-level pricing, named-customer margins, and detailed forward pipeline that a competitor could weaponize.

4. Define staged access tiers.
   - Round one: overview and non-sensitive materials to all qualified bidders. Round two: detailed financials, key contracts (redacted where needed), and management-access materials to shortlisted parties. Confirmatory: remaining and clean-team materials to the preferred bidder.
   - Good looks like: exposure escalating strictly with buyer commitment, never ahead of it.

5. Map every document to the earliest round in which it is released.
   - Honor its sensitivity level so a clean-team item cannot surface in round one even if it lives in an early folder.

6. Set watermarking rules.
   - Apply dynamic watermarks carrying viewer identity and timestamp on all sensitive and clean-team documents.
   - Disable download or restrict to view-only where the item is highly sensitive.

7. Establish Q&A discipline.
   - Route all questions through a single logged channel, tagged by workstream, with a tracked status and a standard turnaround.
   - Common pitfall: side-channel answers by phone that never get logged; prohibit them so every response is captured and consistent across bidders.

8. Define permission and audit hygiene.
   - Use named user groups per tier, review the access log regularly, and set a downgrade or takedown path if a party drops out mid-process.

## Inputs
- The list of diligence documents available, or the categories you can supply
- Which items are competitively sensitive or clean-team only
- The number of process rounds and the gating between them
- Buyer groups and how many parties are expected per round
- Watermarking and download restrictions you require
- Any redaction rules for third-party contracts
- The Q&A turnaround target and the workstream owners

## Output format
- Data room index: the folder taxonomy with subfolders and the documents mapped into them, each tagged with its sensitivity level (open, sensitive, clean-team only).
- Access-tiering plan: for each round (round one, round two, confirmatory), the buyer group, the folders and documents exposed, and the watermarking rules applied.
- Q&A rules: channel, routing by workstream, turnaround, and the no-side-channel discipline.
- Audit rules: user groups per tier and the access-log review cadence.
- Describe all mappings as structured text, never a rendered markdown table.

## Example
Meridian Foods sell-side. Index excerpt, Financial folder: audited statements (open), management accounts (sensitive), customer-level margin bridge (clean-team only). Access plan: round one exposes corporate overview, audited statements, and market materials to all six qualified bidders, view-only with dynamic watermarks. Round two adds management accounts and redacted top-20 customer contracts to the three shortlisted parties, with download disabled on the contracts. Confirmatory opens the customer-level margin bridge to the preferred bidder under a clean-team agreement, viewable only by named advisers. Q&A runs through one logged channel with a two-business-day turnaround, routed by workstream, and phone answers are prohibited so all bidders see the same record.

Attribution

andreworiaandreworia
View sourceMore from andreworia →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

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

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 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', ...

693161 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →