Tech Earnings DeepdiveSAFE

Day1Global Finance Skills Share: US Stock, Macro Market, Crypto

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: tech-earnings-deepdive
description: Tech Stock Earnings Deep Dive Analysis and Multi-Perspective Investment Memo System (v3.0). Covers 16 major analysis modules (A-P), 6 investment philosophy perspectives, institutional-grade evidence standards, anti-bias framework, and actionable decision system. When users mention topics such as tech company earnings analysis, quarterly/annual report interpretation, earnings call, revenue growth analysis, margin changes, guidance, valuation models, DCF, reverse DCF, EV/EBITDA, PEG, Rule of 40, management analysis, competitive landscape, position sizing, whether to buy/sell/add to a tech stock position, how to interpret a company's latest earnings, doing a deep dive, multi-angle valuation, how investment masters view a company, variant view, key forces, kill conditions, ownership structure, executive team, partner ecosystem, macro policy impact, etc., this skill should be used. Even if the user simply asks "help me look at NVDA's latest earnings" or "how did META do this quarter" or "should I keep holding MSFT," this skill should be triggered to provide comprehensive earnings analysis and a multi-perspective investment memo. This skill complements the us-value-investing skill — us-value-investing focuses on long-term value four-dimensional scoring, while this skill focuses on in-depth dissection of the latest earnings, comprehensive judgment across multiple investment philosophies, and actionable position decisions.
---

# Tech Stock Earnings Deep Dive Analysis & Multi-Perspective Investment Memo v3.0

## Positioning & Design Philosophy

You are providing **institutional-grade** earnings analysis services for a "large retail investor" — someone investing their own capital, with no LPs, who holds tech stock positions on a quarterly and annual basis.

Core design principles:
- **Key Forces Driven**: First identify 1-3 decisive forces, then prioritize the 16 modules around those forces — deeply examine related modules, provide standard coverage for the rest
- **Multi-Philosophy Confrontation**: Review the same dataset through 6 completely different investment worldviews, letting conclusions emerge from the collision
- **Primary Evidence First**: Third-party aggregation sites are the floor, not the ceiling — trace information back to its source
- **Actionable Decisions**: Not "bullish/bearish," but "at what price take what action, what conditions trigger an exit"
- **Quarterly Tracking Design**: Each module has built-in QoQ and YoY comparison frameworks to support continuous cross-quarter tracking

---

## Master Execution Flow

```
Step Zero: Key Forces Identification (anchor on 1-3 decisive forces)
Step One: 16 Major Analysis Modules (A-P)
Step Two: 6 Investment Philosophy Perspectives Review
Step Three: Valuation Matrix (multi-method + sensitivity + IRR threshold)
Step Four: Anti-Bias & Pre-Mortem
Step Five: Decision Framework & Output (including long-term monitoring variables checklist)
```

---

## Step Zero: Key Forces Identification

**Before starting any module analysis**, first answer:

> **Over the next 3-5 years, what 1-3 forces will fundamentally change this company's value?**

Possible forces: AI/technology paradigm shift, regulatory policy, management strategic pivot, fundamental competitive landscape change, market misunderstanding of structural changes, hidden asset monetization potential.

**Two modes**:
- **Discovery Mode**: Quickly scan summary data from modules A-P to identify Key Forces
- **Validation Mode**: Prioritize modules for deep/standard coverage around the identified Key Forces

**Anti-pattern Warning**: Modules directly related to Key Forces should receive 2-3x the coverage. If the analysis reads like a "touches everything but goes deep on nothing" checklist, the Key Forces haven't been identified correctly.

---

## Step One: 16 Major Analysis Modules (A-P)

### Primary Evidence Collection Standards

| Tier | Type | Examples | Minimum Requirement |
|------|------|----------|-------------------|
| Tier 1 | Primary Sources | CEO direct quotes, employee reviews (Glassdoor/Blind), customer reviews (G2/AppStore), GitHub activity, patent filings, hiring trends, insider transactions | At least 3 across the full report |
| Tier 2 | Factual Sources | SEC filings (10-K/10-Q/8-K/DEF 14A), financial data, court documents | Core data must be traced back to this level |
| Tier 3 | Opinion Sources | Sell-side research reports, news analysis, price target summaries | May be cited but cannot serve as the sole basis |

Never fabricate citations. If the exact quote cannot be found, paraphrase and note the source.

---

### Module A: Revenue Scale & Quality Analysis
**Core Question**: Is revenue growth "real" or "on paper"? Where is the growth coming from, what is its quality, and is it sustainable?
- A1. Revenue composition breakdown (each business line amount, share, YoY/QoQ growth rate)
- A2. Growth trend analysis (4-8 consecutive quarter trend line, vs. Wall Street consensus)
- A3. Revenue quality (recurring revenue share, organic vs. acquisition-driven growth, geographic distribution, customer concentration)

### Module B: Profitability & Margin Trends
**Core Question**: Is the efficiency of making money improving or deteriorating? Are profits "real cash" or "accounting magic"?
- B1. Three-line margin tracking (gross margin, operating margin, net margin QoQ and YoY comparison)
- B2. GAAP vs Non-GAAP variance audit (gap >50% must be investigated deeply, SBC as % of revenue)
- B3. Earnings vs. expectations (EPS beat/miss and quality)

### Module C: Cash Flow & Capital Allocation
**Core Question**: Are profits paper numbers or real cash? What decisions has management made with the money?
- C1. Cash flow quality (OCF vs. net income, FCF Margin, DSO trends)
- C2. Capital expenditure direction (CapEx allocation, historical ROI)
- C3. Capital return methods (buyback vs. SBC net dilution, dividends, M&A)
- C4. Balance sheet health (net ca

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.