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

Proprietary Angle Assessment

ASecurity

Tests a claimed proprietary angle against evidence, grades it real, partial or none and prices what it actually buys -- when you need to know whether there is a reason to win a deal outside a broad auction.

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

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add andreworia/claude-finance-skills --skill proprietary-angle-assessment --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Proprietary Angle Assessment?

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

Security grade badge for Proprietary Angle Assessment
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/andreworia-proprietary-angle-assessment/badge)](https://www.skillsdirectory.com/skills/andreworia-proprietary-angle-assessment)

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

Download with Pro
Files
SKILL.md
---
name: Proprietary Angle Assessment
description: Tests a claimed proprietary angle against evidence, grades it real, partial or none and prices what it actually buys -- when you need to know whether there is a reason to win a deal outside a broad auction.
---

# Proprietary Angle Assessment

## When to use

Use this skill the moment someone calls a deal proprietary, and always before a pre-emptive bid is underwritten -- the premium usually arrives attached to the claim. Start from the assumption that there is no angle; most do not survive step two.

## What it does

Produces a short assessment: the claim written plainly with its holder named, the result of each evidence test, a grade of real, partial or none, what the angle mechanically buys, and the premium it must justify against the expected clearing range.

## Method

### Step 1 -- Write the claim and name the person who holds it

Firms do not have relationships; individuals do. If the claim cannot be attached to a named partner and a named counterparty, it is an institutional attribute, not an angle -- and "we know this sector" is marketing until tested.

### Step 2 -- Apply the substitution test

Substitute each of the ten most likely bidders into the claim. If it stays true for three or more, it is a table stake. Sector focus, a vertical team, a buy-and-build record and "we move quickly" all fail this test in most mid-market processes.

### Step 3 -- Test relationship with dates, not adjectives

Record when the principal last spoke with the owner, who initiated it, and what the owner asked for. An unprompted inbound is evidence; three meetings the fund arranged are hospitality. Coverage without reciprocity is a mailing list.

### Step 4 -- Test credibility with a reference the owner would call

Credibility means a named chief executive in the same sub-sector who will take the owner's call and say something specific about how the fund behaved after closing, ideally when the plan went wrong. A portfolio page and two panels are not credibility.

### Step 5 -- Test speed, certainty and structure against your own record

Certainty is measurable: across the last five processes, median days from exclusivity to signing, re-trades, deals abandoned post-IOI. Structure is something the fund owns and a generalist cannot replicate: an adjacent portfolio asset, an operating partner who has run the business, a longer-hold vehicle. Price is not structure.

### Step 6 -- Grade it, and default to none

Real requires evidence in two categories plus a mechanism the seller will act on. Partial buys a look, not a process. None is the default, and the honest answer in most cases -- including many where the fund has met the owner repeatedly.

### Step 7 -- Price what the angle buys

State what it mechanically delivers -- exclusivity, a bilateral negotiation, a pre-emptive window, a first call before the bank's mailing -- and the premium over the expected range that acting costs. In a broad auction the clearing price is set by the most optimistic underwriter in the room, and a partial angle is worth nothing against that bidder.

## Inputs

- The claimed angle as stated by the deal team, verbatim
- Contact history with the owner: dates, initiator, substance
- The fund's process record: exclusivity-to-signing days, re-trades, drops
- The likely bidder list, sponsors and strategics
- Expected valuation range from comparable processes

## Output format

- The claim in one sentence, with the individual holding it named
- Substitution test result, naming the bidders it also holds for
- Evidence by category: relationship, credibility, certainty, structure
- Grade: real, partial or none, with the reasoning
- What the angle mechanically buys, in process terms
- The premium it must justify against the expected clearing range
- Recommended posture: pre-empt, participate, or decline

## Example

**Fictional worked example -- Halden Packaging.**

Claim: "proprietary, because our operating partner sat on a competitor's board." Relationship: two calls in 14 months, both initiated by us. Substitution: four of the ten likely bidders field a packaging operating partner, so this is a table stake. Certainty: the last five deals signed a median 31 days from exclusivity with no re-trades -- real, and verifiable by the seller's adviser. Grade: partial; it buys a three-week pre-emptive window, not exclusivity.

Price: on EBITDA of GBP 16M, a range of 8.5-9.5x is GBP 136M to GBP 152M. Pre-empting at the 9.0x mid, GBP 144M, would be topped in a competitive process, so a serious pre-empt costs GBP 152M -- GBP 8M above the mid, which a partial angle does not buy.

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 →