Public Company First Pass logo

Public Company First Pass

Community
latour-ai
public-company-first-pass

Create a first-pass tear sheet on a US-listed public company from public sources. Trigger on: "tear sheet", "first pass", "company overview", "equity research", "stock analysis", "company profile", "investment overview", "what does [company] do", "tell me about [ticker]", "quick look at [company]", "pull up [ticker]", "company summary", "how does [company] make money", "who competes with [company]", "bull/bear case for [ticker]", "break down [company]", "is [ticker] interesting", "run me through [company]", or any request to understand a US-listed public company's business, financials, valuation, or competitive landscape. Also trigger when the user provides a ticker and expects research, or uploads SEC filings for synthesis. NOT for private companies, crypto, mutual funds, ETFs, or non-US securities.

Overview

Publisherlatour-ai
Repositoryskills
Skill namepublic-company-first-pass
Stars
69
Forks
4
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by latour-ai on GitHub. Read the source before you install it.

Installation

Install the Public Company First Pass AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/latour-ai/skills/tree/main/public-company-first-pass
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/latour-ai/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/public-company-first-pass .claude/skills/public-company-first-pass
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Public Company First Pass in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Public Company First Pass on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Public Company First Pass is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Public Company First Pass

Generate a concise (~3 page) first-pass tear sheet on a US-listed public company. The output is a .md file covering 11 sections: TL;DR, business overview, revenue breakdown, financials, valuation context, competitive landscape, recent developments, bull/bear cases, and an initial investment view with sources.

This is NOT a full initiation report, financial model, price target, or buy/sell/hold recommendation. It is a structured first look — the kind of thing an analyst prepares before deciding whether to dig deeper.

Workflow

  1. Identify the company. Confirm name, ticker, and exchange. If the user only gives a name or ticker, confirm the right entity before proceeding.
  2. Research using WebSearch. Pull data from public sources following the Source Rules below. Search for SEC filings (10-K, 10-Q), latest earnings results, investor presentations, and reputable financial data.
  3. Build the tear sheet following the 11-section output format below.
  4. Save as [TICKER]-first-pass.md (e.g., CRM-first-pass.md) and share with the user.

Source Rules (priority order)

Use the best available public information in this order:

  1. Latest Form 10-K or annual report
  2. Latest Form 10-Q
  3. Latest earnings release
  4. Latest earnings call transcript
  5. Investor presentation
  6. Company website
  7. Reputable financial data sources (SEC EDGAR, Yahoo Finance, Bloomberg, FactSet)
  8. Reputable news sources (WSJ, FT, Reuters, Bloomberg News)
  9. Public competitor information

Do NOT use blogs, anonymous commentary, message boards, promotional stock-picking sites, social media posts, or unsourced claims. If data is unavailable, say so clearly — never fabricate numbers, market share, competitors, or valuation metrics.

Time Period

Use latest fiscal year and LTM (last twelve months) where available. Reference the latest quarter when relevant. Only use older history to explain the current state.

Core Principles

These matter because the tear sheet needs to be trustworthy enough for a professional to act on — even if that action is just "worth more work."

  • Be neutral and concise. Separate facts from interpretation.
  • Prefer specific numbers over vague descriptions ("revenue grew 12% YoY" not "revenue grew nicely").
  • Do not invent financials, market share, competitors, or valuation metrics.
  • No buy/sell/hold recommendation. No price target. Do not overstate precision in valuation.
  • Include a balanced bull and bear case — don't softball either one.
  • Flag missing, stale, or inconsistent information explicitly.
  • Use bullets and tables to keep it scannable.

Output Format — 11 Sections

Section 1: TL;DR

3-5 bullets: what it does, why it matters now, financial profile, valuation context, bull/bear tension.

Example:

markdown
## TL;DR

- **What it does:** Leading cloud-based CRM platform serving enterprises across sales, service, marketing, and commerce.
- **Why it matters:** Dominant CRM market share (~23%) with expanding platform play into data/AI via recent acquisitions.
- **Financial profile:** $34.9B revenue (FY24), 11% YoY growth, 30.5% non-GAAP operating margin, $12.2B FCF.
- **Valuation context:** Trading at ~26x NTM EV/EBITDA vs. 5-year average of ~35x; FCF yield ~4.5%.
- **Bull/bear tension:** Bulls see margin expansion + AI monetization; bears worry about decelerating organic growth and acquisition integration risk.

Section 2: Business Overview

What the company does, core products/services, primary customers, end markets, geographic exposure, and business model. Keep it concise — avoid corporate history. Focus on what someone needs to understand the business today.

Section 3: How the Company Makes Money

Table format breaking down revenue streams. This answers "where do the dollars actually come from?"

Example:

markdown
| Revenue Stream / Segment | What It Includes | Key Drivers | Notes |
|---|---|---|---|
| Subscription & Support | Cloud CRM licenses, premium support | Seat expansion, upsell to higher tiers | ~94% of revenue, highly recurring |
| Professional Services | Implementation, consulting, training | New deployments, platform migrations | ~6% of revenue, lower margin |

Section 4: Key Financial Snapshot

Table of core financial metrics. Only include what's actually available — do not estimate or fabricate.

Example:

markdown
| Metric | Latest FY (FY24) | LTM / Latest Available | Notes |
|---|---|---|---|
| Revenue | $34.9B | $35.6B (LTM) | FY ends Jan 31 |
| Revenue Growth (YoY) | 11% | 10% (LTM) | Decelerating from 18% two years prior |
| Gross Margin | 76.1% | 76.4% | Stable; subscription mix supports margin |
| Operating Income (non-GAAP) | $10.6B | $11.0B | 30.5% margin, up from 22% prior year |
| Net Income (GAAP) | $4.1B | $4.5B | Includes SBC of ~$3.8B |
| Free Cash Flow | $12.2B | $12.8B | FCF margin ~35%, strong conversion |
| Cash & Equivalents | $14.2B | — | Net debt ~$4B after long-term debt |
| Total Debt | $18.3B | — | Primarily acquisition financing |

Include relevant items like segment revenue (if not in Section 3), capex, R&D, dividends/buybacks, or anything material. Caveat stale or estimated figures.

Section 5: Basic Valuation Context

Current valuation metrics with caveats. These are context, not conclusions.

Example:

markdown
| Valuation Metric | Value | Notes |
|---|---|---|
| Market Cap | $265B | As of [date] |
| Enterprise Value | $269B | Includes net debt of ~$4B |
| P/E (NTM) | ~28x | Based on consensus NTM EPS |
| EV / Revenue (NTM) | ~7.0x | vs. large-cap SaaS median of ~8x |
| EV / EBITDA (NTM) | ~26x | vs. 5-year average of ~35x |
| FCF Yield | ~4.5% | Based on LTM FCF / market cap |
| 52-Week Performance | -8% | Underperforming S&P 500 by ~15pp |

If data is stale or unavailable, say so (e.g., "Consensus estimates not available; using trailing metrics only").

Section 6: Competitive Landscape

Table mapping competitors — direct, adjacent, and substitutes.

Example:

markdown
| Competitor | Relationship to Company | Relevant Difference |
|---|---|---|
| Microsoft Dynamics 365 | Direct competitor in CRM/ERP | Bundled with Office 365; enterprise integration advantage |
| HubSpot | Direct competitor in SMB CRM | Freemium model, stronger in inbound marketing |
| SAP | Adjacent (ERP with CRM module) | Stronger in manufacturing/supply chain verticals |
| ServiceNow | Adjacent (ITSM expanding into CX) | Competing in service/workflow automation |
| Freshworks | Substitute (lower-cost CRM) | Price-competitive for SMB segment |

Section 7: Recent Developments

Last 6-12 months. Use bullets. Be specific with dates and numbers. Cover:

  • Latest earnings results and guidance changes
  • Product launches or strategic pivots
  • M&A activity (completed, announced, rumored)
  • Management changes
  • Regulatory developments
  • Major customer wins/losses or market developments
  • Capital allocation changes (buybacks, dividends, debt paydown)

Section 8: Bull Case

What needs to go right? Growth drivers, margin expansion, competitive advantages, market structure, capital allocation upside, valuation re-rating catalysts.

Ground every point in evidence. "Revenue could accelerate" is weak. "Revenue could accelerate as the $2B AI/Data Cloud segment (growing 35% YoY) scales and drives platform upsell" is useful.

No recommendation — this is "here's why an optimist would be interested."

Section 9: Bear Case

What could go wrong? Growth deceleration, margin pressure, competitive threats, customer concentration, cyclicality, balance sheet risk, regulatory risk, valuation downside.

Don't exaggerate for false balance, but don't softball either. A useful bear case identifies scenarios that would actually cause losses, not just "competition could increase."

Section 10: Initial Investment View

Synthesize Sections 8 and 9 into a framework for further work:

  • Central investment debate: The one question that most determines outcome (e.g., "Can the company sustain 10%+ organic growth while expanding margins, or is this a maturing platform?")
  • What needs to be true for the bull case: 2-3 specific, falsifiable conditions
  • What needs to be true for the bear case: 2-3 specific, falsifiable conditions
  • Key variables to diligence next: What would you study before forming a stronger view?

No price target. No rating. No recommendation. Just a clear-eyed framing of what matters.

Section 11: Sources Used

List every source referenced with title, publisher/filing type, and date.

Example:

markdown
| Source | Publisher / Filing Type | Date |
|---|---|---|
| Salesforce FY24 10-K | SEC Filing (Annual Report) | March 2024 |
| Q4 FY24 Earnings Release | Company Press Release | February 2024 |
| Q4 FY24 Earnings Call Transcript | Company / Seeking Alpha | February 2024 |
| "Salesforce Raises Full-Year Outlook" | Reuters | November 2023 |

Handling Missing Information

If information isn't available, say so directly:

  • "Not available in the reviewed public sources"
  • "Not disclosed in the reviewed filings"
  • "Consensus estimates not available; using trailing metrics only"

If the source set is incomplete (e.g., couldn't access the 10-K or latest transcript), add a note at the end explaining what's missing and how it affects the analysis.

Quality Checklist

Before delivering, verify:

  • Total length ~3 pages (rendered markdown)
  • Neutral, professional tone throughout
  • Every financial figure is sourced or caveated
  • Valuation metrics are current or explicitly flagged as stale
  • Bull and bear cases are balanced and grounded
  • No buy/sell/hold recommendation or price target anywhere
  • Missing information is flagged, not fabricated
  • Sources section is complete
  • Tables are properly formatted

Output

Save as [TICKER]-first-pass.md and share with the user.

Frequently asked questions

What does the Public Company First Pass AI skill do?

Create a first-pass tear sheet on a US-listed public company from public sources. Trigger on: "tear sheet", "first pass", "company overview", "equity research", "stock analysis", "company profile", "investment overview", "what does [company] do", "tell me about [ticker]", "quick look at [company]", "pull up [ticker]", "company summary", "how does [company] make money", "who competes with [company]", "bull/bear case for [ticker]", "break down [company]", "is [ticker] interesting", "run me through [company]", or any request to understand a US-listed public company's business, financials, valu...

Why use Public Company First Pass on TypingMind?

Because you install it once and use it with any model. Public Company First Pass is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Public Company First Pass in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/latour-ai/skills/tree/main/public-company-first-pass. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Public Company First Pass?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Public Company First Pass?

As many as you like. As long as a model supports skills, you can use Public Company First Pass with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Public Company First Pass AI skill free?

It is published on GitHub by latour-ai. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇