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

Company Research

ASecurity

Builds a fast, deep company profile across financials, drivers, and positioning, for when you need a baseline on a target or client before deeper work.

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

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add andreworia/claude-finance-skills --skill company-research --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Company Research?

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

Security grade badge for Company Research
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/andreworia-company-research/badge)](https://www.skillsdirectory.com/skills/andreworia-company-research)

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

Download with Pro
Files
SKILL.md
---
name: company-research
description: Builds a fast, deep company profile across financials, drivers, and positioning, for when you need a baseline on a target or client before deeper work.
---

# Company Research Agent

## When to use
Use this agent when you need a fast, deep baseline on a target or client before valuation, diligence, or a pitch. It is the first pass that gets you fluent on a company: what it does, how it makes money, how healthy the financials are, and where it sits competitively. Reach for it when a deal lands on your desk and you need to be conversant by the next morning.

## What it does
It returns a company profile that combines the quantitative picture (financials, segments, unit economics) with the qualitative picture (business model, drivers, positioning, and risks), so you have a grounded baseline to build on.

## Method
The agent runs a company-profiling routine, quantitative and qualitative:

1. Establish identity: what the company sells, to whom, its scale, ownership and structure, and how it is organized into business segments.
   - Note whether it is public, sponsor-owned, or founder-held, since that shapes both data availability and deal dynamics.

2. Decompose the business model: the revenue model, how the company charges, recurring versus one-time mix, and the core unit economics that drive margin.
   - Good looks like being able to state the profit made on one unit of the core product or one customer.

3. Read the financials: revenue trajectory and growth rate, gross and operating margins, profitability trend, cash generation, and the shape of the balance sheet including leverage.
   - Check cash conversion against reported earnings; a wide gap is a flag worth chasing.

4. Break out segments: revenue and profit by segment or geography, so mix effects and the true growth engine are visible rather than buried in the consolidated total.
   - Pitfall: a healthy consolidated margin can hide one segment subsidizing a structurally weak one.

5. Identify the value drivers: the two to four levers that most move the company's revenue and margin, such as volume, price, retention, utilization, or input cost.
   - Rank the drivers by sensitivity, so the reader knows which lever matters most.

6. Map positioning: main competitors, relative scale, sources of advantage or disadvantage, and share trend where it can be inferred.
   - Distinguish a real, defensible advantage from a temporary lead that rivals can copy.

7. Compute orientation metrics: a few standard reference points such as EV/EBITDA and revenue growth versus the peer set, to place the company on the map.
   - Use these to locate the company relative to peers, not to conclude a valuation, which is a separate exercise.

8. Surface risks and questions: the key vulnerabilities and the open diligence questions the profile cannot yet answer.
   - Separate answerable-with-more-data questions from genuine structural risks.

9. Synthesize: a short verdict on financial health and competitive standing, framed for the decision at hand.
   - Tie the verdict back to the purpose the profile was requested for.

## Inputs
- The company name and, if relevant, the specific entity or segment in focus.
- The purpose (valuation prep, diligence, pitch, client baseline).
- Any financials, filings, or investor materials already in hand.
- The peer set to benchmark against, if known.
- The ownership status, if known, and any known constraints.
- The depth and length expected for the profile.

## Output format
Claude returns a profile with these named sections:
- Snapshot: what the company is, in three lines.
- Business Model: how it charges and where margin comes from.
- Financial Picture: growth, margins, cash, and leverage, with the key figures called out in prose rather than a grid.
- Segments: the split of revenue and profit and where the growth engine sits.
- Value Drivers: the ranked levers that move revenue and margin.
- Competitive Positioning: rivals, relative scale, and advantage.
- Risks and Open Questions: vulnerabilities and unresolved diligence items.
- Verdict: financial health and competitive standing for the decision at hand.
- Confidence Note: where figures are estimated or data was unavailable. Any peer or multiple comparison is written as sentences, not a table.

## Example
Company: fictional Northwind Logistics, a regional freight and warehousing operator, sponsor-owned. Snapshot: asset-light freight brokerage plus owned warehousing, serving mid-market shippers across three regions. Business Model: brokerage earns a spread per load and warehousing earns recurring storage and handling fees, giving a mixed one-time and recurring profile. Financial Picture: revenue growing at a mid-teens rate with operating margins in the high single digits, solid cash conversion, and moderate leverage. Segments: warehousing is smaller but higher-margin and growing faster than brokerage, so it is the true growth engine despite brokerage carrying more revenue. Value Drivers, ranked: warehouse utilization, brokerage spread, and load volume. Competitive Positioning: sub-scale versus national carriers but strong in its home region on service and relationships. Risks and Open Questions: brokerage spread is cyclical and customer concentration is unclear. Verdict: financially healthy and a plausible roll-up platform, pending confirmation of customer concentration and contract durability.

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 →