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

Third Party Advisor Brief

ASecurity

Produces the scope document for an external diligence provider -- the questions to answer, the deliverable format, the materiality threshold and the explicit exclusions -- for when you need the output to change a decision rather than describe a market.

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

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add andreworia/claude-finance-skills --skill third-party-advisor-brief --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Third Party Advisor Brief?

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

Security grade badge for Third Party Advisor Brief
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/andreworia-third-party-advisor-brief/badge)](https://www.skillsdirectory.com/skills/andreworia-third-party-advisor-brief)

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

Download with Pro
Files
SKILL.md
---
name: Third-Party Advisor Brief
description: Produces the scope document for an external diligence provider -- the questions to answer, the deliverable format, the materiality threshold and the explicit exclusions -- for when you need the output to change a decision rather than describe a market.
---

# Third Party Advisor Brief

## When to use

Use this skill before engaging any external provider on a live deal: commercial diligence, QoE, technology, insurance, ESG, or an operational specialist. Providers write to the scope they are given. A scope framed as topics -- "assess the competitive landscape" -- produces a competent report that changes nothing, billed in full. A scope framed as questions with decisions attached produces findings you can price.

## What it does

Produces an engagement brief covering the decision the work informs, the numbered questions to answer, the materiality and de-minimis thresholds, the deliverable format and interim read-out dates, the explicit exclusions, the fee structure with phasing and change control, and the reliance position.

## Method

### Step 1 -- State the decision and its date

Open the brief with the decision the work feeds and when it is taken -- the bid, the leverage quantum, an SPA protection, the 100-day plan -- plus the model freeze date. **A provider who knows the decision writes to it; one who knows only the topic writes to their template.**

### Step 2 -- Convert every scope line into a question

Number each question, make it answerable, and attach the consequence. Not "review customer churn" but "of the 14% gross revenue churn in FY25, how much sits in the cohorts renewing before completion, and what would a repeat of that rate do to the FY27 EBITDA bridge?" Order the questions by the EBITDA they bear on and say so -- providers put their best people on what the client clearly cares about.

### Step 3 -- Set the materiality and de-minimis thresholds

State the level below which you do not want to hear about something, expressed in EBITDA and in turns of the entry multiple. Without a de-minimis, a red-flag report arrives with sixty findings of which four matter, and the deal team spends the last week of exclusivity sorting them. **Thresholds are a quality instruction, not a cost-saving.**

### Step 4 -- Specify the deliverable and the interim cadence

Ask for a red-flag report in prose with a supporting databook, not a deck. Require a fixed interim read-out -- typically at the halfway point -- listing every finding above threshold to date, and state that findings above threshold are reported within 48 hours of being formed, not held for the report. Name the individuals who must attend the read-out.

### Step 5 -- Write the exclusions down

List what you will not pay for: market overviews you already have from the teardown, restatements of the CIM, benchmarking against the provider's proprietary index where it bears on no question, and any recommendation to transact. Exclusions are where fee is recovered and redeployed into interview volume, which is what moves confidence.

### Step 6 -- Phase the fee and control change

Split into a Phase 1 red-flag scope with a go/no-go, and a Phase 2 deep scope released only on your instruction. Fix Phase 1. Require written approval for any out-of-scope work above a stated amount, and make the interim read-out the moment scope changes are raised.

### Step 7 -- Settle reliance before signature

Confirm who may rely on the report -- the fund, the acquiring entity, lenders, a W&I insurer -- and whether reliance carries a fee or a liability cap. Reliance bought after a finding is uncomfortable is bought at a worse price.

## Inputs

- CIM teardown risk list and information gap log
- Thesis lines the workstream must support, with their EBITDA
- QoE EBITDA, entry multiple, materiality threshold
- Deal calendar: interim read-out, model freeze, IC, signing
- Provider proposal and fee quote, if already received

## Output format

- Decision statement, date, and model freeze
- Numbered questions, ordered by EBITDA at stake
- Materiality and de-minimis thresholds in EBITDA and turns
- Deliverable format, read-out dates, attendees, 48-hour rule
- Exclusions, stated as a list
- Fee: Phase 1 fixed, Phase 2 conditional, change-control threshold
- Reliance parties and liability cap

## Example

**Fictional target: Ravensdale Speciality Chemicals.** QoE EBITDA GBP 26.0m, proposed entry 8.5x, implied EV GBP 221.0m. De-minimis set at GBP 250k of annualised EBITDA -- just under 1% of QoE, and GBP 2.1m of EV at the 8.5x entry.

The commercial provider proposed GBP 225k across four modules. The market-sizing module at GBP 40k was struck, the teardown having already sized the market from the same third-party source the provider intended to cite. GBP 25k of the saving was redirected into raising customer interviews from 12 to 20, weighted to the two accounts that between them carry GBP 4.6m of EBITDA. Net engagement GBP 210k.

The judgement call is that interviews are the only part of a commercial scope that produces evidence you cannot get from your own desk. Cut the desk research, buy the calls, and hold the provider to a read-out date early enough that a bad answer still leaves room to re-bid.

Attribution

andreworiaandreworia
View sourceMore from andreworia →
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

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', ...

693621 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 →