edgar-sec-filings
This skill extracts and analyzes key information from SEC EDGAR filings including 10-K annual reports, 10-Q quarterly reports, 8-K current events, proxy statements, and Form 4 insider transactions. Use it to identify financial trends, risk factors, management analysis, and investment signals from US public company disclosures by parsing filing documents directly or accessing structured financial data through yfinance.
git clone --depth 1 https://github.com/HKUDS/Vibe-Trading /tmp/edgar-sec-filings && cp -r /tmp/edgar-sec-filings/agent/src/skills/edgar-sec-filings ~/.claude/skills/edgar-sec-filingsSKILL.md
# SEC EDGAR Filing Analysis
## Overview
Analyze US public company filings from SEC EDGAR to extract fundamental insights, risk signals, and investment-relevant information. Covers annual reports (10-K), quarterly reports (10-Q), current events (8-K), proxy statements (DEF 14A), and insider transactions (Form 4).
This skill provides the analytical framework for interpreting SEC filings. Data retrieval uses `read_url` tool with EDGAR URLs or `yfinance` Ticker objects for structured financial data.
## Filing Types and Investment Relevance
| Filing | Frequency | Key Content | Signal Value |
|--------|-----------|-------------|--------------|
| 10-K | Annual | Full-year financials, risk factors, MD&A, segment data | Comprehensive fundamental view |
| 10-Q | Quarterly | Quarterly financials, interim MD&A, legal updates | Trend confirmation / inflection detection |
| 8-K | Event-driven | Material events: M&A, CEO change, restatement, guidance | Catalyst / risk trigger |
| DEF 14A | Annual (proxy) | Executive comp, board composition, shareholder proposals | Governance quality signal |
| Form 4 | Within 2 days | Insider buys / sells | Insider conviction signal |
| 13F | Quarterly | Institutional holdings >$100M AUM | Smart money positioning |
| SC 13D/G | Event-driven | >5% ownership stake disclosure | Activist / strategic investor signal |
## EDGAR Data Access
### Direct EDGAR URLs
```python
# Company filings search
# https://www.sec.gov/cgi-bin/browse-edgar?action=getcompany&CIK={ticker}&type={filing_type}
# Example: Apple 10-K filings
url = "https://www.sec.gov/cgi-bin/browse-edgar?action=getcompany&CIK=AAPL&type=10-K&dateb=&owner=include&count=10"
# EDGAR full-text search (EFTS)
# https://efts.sec.gov/LATEST/search-index?q={query}&dateRange=custom&startdt={start}&enddt={end}
```
### Via yfinance (structured data)
```python
import yfinance as yf
ticker = yf.Ticker("AAPL")
# Financial statements (derived from 10-K/10-Q)
income = ticker.financials # Annual income statement
income_q = ticker.quarterly_financials # Quarterly
balance = ticker.balance_sheet # Balance sheet
cashflow = ticker.cashflow # Cash flow statement
# Insider transactions (derived from Form 4)
insider = ticker.insider_transactions
# Institutional holders (derived from 13F)
institutions = ticker.institutional_holders
major = ticker.major_holders
```
## 10-K / 10-Q Analysis Framework
### I. Financial Statement Deep Dive
**Income Statement Focus:**
- Revenue growth rate: YoY and QoQ acceleration / deceleration
- Gross margin trend: expanding (pricing power) vs compressing (cost pressure)
- Operating leverage: SG&A as % of revenue declining = positive operating leverage
- R&D intensity: R&D / revenue ratio vs peers
- Non-recurring items: restructuring charges, impairments, one-time gains
**Balance Sheet Focus:**
- Cash & equivalents vs total debt: net cash / net debt position
- Current ratio and quick ratio: liquidity health
- Goodwill / intangibles as % of total assets: acquisition-driven growth risk
- Inventory days (for manufacturers / retailers): rising = demand weakness signal
- Accounts receivable days: rising = collection risk or channel stuffing
**Cash Flow Focus:**
- FCF = Operating CF - CapEx: true cash generation power
- FCF conversion = FCF / Net Income: >80% = high earnings quality
- CapEx intensity = CapEx / Revenue: rising = growth investment or maintenance burden
- Stock-based compensation: add back to get true cash earnings
- Buyback vs dividend: capital return strategy signal
### II. MD&A (Management Discussion & Analysis)
The MD&A section is the most qualitative and forward-looking part of the filing.
**Key extraction targets:**
1. **Revenue drivers**: which segments / geographies are growing, which are declining
2. **Margin commentary**: management explanation for margin changes
3. **Forward guidance language**: "expect", "anticipate", "believe" — tone shift detection
4. **Risk factor changes**: compare risk factors vs prior filing; NEW risks added = material change
5. **Liquidity and capital resources**: debt maturity schedule, credit facility availability
**Tone analysis signals:**
```python
# Simplified tone scoring
positive_words = ["growth", "improvement", "strong", "exceeded", "momentum", "opportunity"]
negative_words = ["challenging", "decline", "uncertainty", "headwind", "pressure", "risk"]
cautious_words = ["moderate", "cautious", "prudent", "measured", "selective"]
# Count frequency change vs prior filing
# Rising negative word count = deteriorating outlook
# Rising cautious words = management hedging
```
### III. Risk Factor Analysis
**Risk factor change detection (10-K vs prior 10-K):**
| Change Type | Signal | Action |
|-------------|--------|--------|
| New risk factor added | Material new risk identified | Deep dive on the specific risk |
| Risk factor removed | Risk resolved or deemed immaterial | Positive signal if genuine resolution |
| Language intensified | Risk escalating | Review exposure and hedging |
| Order changed (moved higher) | Risk priority elevated | Assess potential impact magnitude |
**Common risk categories for US equities:**
- Regulatory / legal risk (antitrust, FDA, patent expiry)
- Customer concentration (>10% revenue from single customer must be disclosed)
- Geographic concentration (China exposure, emerging market risk)
- Technology disruption risk
- Cybersecurity risk (new SEC mandate: material cybersecurity incidents must be disclosed in 8-K)
- Climate / ESG risk (increasingly required)
## 8-K Event Analysis
### Material Event Classification
| Event Type | 8-K Item | Typical Price Impact | Time Sensitivity |
|------------|----------|---------------------|------------------|
| Earnings pre-release | 2.02 | High | Immediate |
| M&A announcement | 1.01 | Very high | Immediate |
| CEO / CFO departure | 5.02 | Medium-high | Same day |
| Restatement | 4.02 | Very high (negative) | Immediate |
| Guidance revision | 7.01/Professional finance research toolkit — backtesting (7 engines + benchmark comparison panel), factor analysis, Alpha Zoo (452 pre-built alphas across qlib158/alpha101/gtja191/academic), options pricing, 77 finance skills, 29 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 7 data sources (tushare, yfinance, okx, akshare, mootdx, ccxt, futu).
ADR/H-share/A-share cross-listing premium analysis — track pricing gaps between US-listed ADRs, HK-listed H-shares, and A-shares for arbitrage signals, dual-listing valuation, and delisting risk assessment.
AKShare financial data aggregator (18k+ stars). Free, no API key. Covers A-shares, US, HK, futures, macro, forex. Primary fallback for tushare and yfinance.
Browse and bench the bundled alpha zoos — prebuilt cross-sectional factor libraries (Kakushadze 101, GTJA 191, Qlib 158, Fama-French / Carhart). Use when the user asks "which alphas exist", wants metadata on a named alpha, or wants to run IC/IR on a whole zoo over a universe.
A 股 ST/*ST 风险预测框架 — 基于最新中报/三季报或业绩预告/快报,预测下一财年是否会因营收、利润、净资产、分红不达标而被风险警示,并将新浪监管处罚记录作为独立证据面纳入风险等级。仅适用于 A 股,不预测财务造假。
Asset allocation theory and optimizer usage — MPT / Black-Litterman / risk budgeting / all-weather strategy, including guides for 4 optimizers and rebalancing rules.
Diagnose failed or underperforming backtests, locate the root cause, and fix the issue
Behavioral finance applications: theories of overreaction and underreaction, behavioral explanations for momentum and reversal, investor sentiment cycles, cognitive-bias checklists, and debiasing quantitative strategies.