A command-line tool and AI skill that instantly extracts and compares the SEC 10-K Risk Factors section (Item 1A) across different filing years for any US-listed company.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install edgar-risk-diff
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install edgar-risk-diff using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Edgar Risk Diff?
Edgar Risk Diff is an automated pipeline that pulls public regulatory filings directly from SEC EDGAR and provides a structured diff of Item 1A (Risk Factors). It calculates text churn, categorizes risk modifications under high-impact themes like AI, Geopolitics, and Cybersecurity, and isolates added or dropped paragraphs. By integrating this solution from the ecosystem of Openclaw Skills, financial analysts, developers, and investment teams can quickly parse thousands of words in SEC filings without relying on expensive external APIs or manual comparisons.
This utility operates locally with no required API keys, complying with SEC fair-access policies through smart rate-limiting and local caching. It empowers AI agents to understand shifts in corporate risk profiles over time, making it an essential addition to any developer's financial workflow.
Edgar Risk Diff Use Cases
- Track annual corporate adjustments: Instantly identify new disclosures or dropped risk factors in a company's yearly 10-K filing.
- Conduct multi-ticker market scans: Compare risk profiles across peer groups like AAPL, MSFT, and GOOGL for morning briefs or hedge fund research.
- Analyze thematic risk trends: Roll up additions and changes into topics such as Cybersecurity, AI/ML, Climate, and Regulatory modifications.
- Identify paraphrased risk language shifts: Evaluate how existing risks have been strategically reframed or updated using paragraph-matching similarity ratios.
- Integrate structured SEC intelligence into automated AI workflows via highly compatible Openclaw Skills.
How Edgar Risk Diff Works
- Query SEC EDGAR: The tool queries data.sec.gov and public archives to pull the 10-K filings for the requested US ticker symbol.
- Enforce Rate Limiting and Compliance: An SEC-compliant User-Agent header is sent, throttling requests to under 10 requests per second to protect access stability.
- Extract Item 1A: Using a regex-based parser, the tool isolates the Risk Factors section from the retrieved HTML filing structure.
- Diff Paragraphs and Calculate Churn: Paragraphs are tokenized and compared using fuzzy matching (SequenceMatcher) to identify added, removed, and modified text, calculating an overall churn percentage.
- Categorize and Theme: Added paragraphs are automatically scanned for keyword matches and tagged with high-level themes like AI, geopolitics, and litigation.
- Generate Local Cache: The extracted sections are saved inside the local environment directory, making subsequent requests for the same ticker instant.
Edgar Risk Diff Setup
To get started with Edgar Risk Diff, ensure you have Python 3 and the requests library installed. This tool runs directly via the CLI as one of the highly integrated Openclaw Skills.
# Clone or navigate to the skill directory and run the basic diff
python3 scripts/risk_diff.py diff AAPL
# Compare specific years for a ticker
python3 scripts/risk_diff.py diff TSLA --years 2024 2022
# Print the latest Risk Factors section without a comparison
python3 scripts/risk_diff.py latest NVDA
To customize the user-agent compliance header, export the following environment variable:
export EDGAR_USER_AGENT="Your Name [email protected]"
For premium usage (embedding-based novelty score), save your license key:
echo "YOUR_LICENSE_KEY" > ~/.edgar-risk-diff/license.txt
# Or set the environment variable
export EDGAR_RISK_LICENSE="YOUR_LICENSE_KEY"
Edgar Risk Diff Data Schema & Taxonomy
File Structure and Caching
Edgar Risk Diff processes all data locally to respect your privacy and speed up future execution. It structures cached information and configurations within the user's home directory:
| Path/File | Type | Description |
|---|---|---|
~/.edgar-risk-diff/cache/ |
Directory | Houses cached HTML and structured JSON extractions of Item 1A per ticker. |
~/.edgar-risk-diff/license.txt |
Text File | Optional file containing your premium tier license key. |
Parsed Document Metadata Schema
When a 10-K is parsed, the internal representation includes the following metadata taxonomy:
ticker: The equity symbol analyzed (e.g., AAPL).year: The calendar or fiscal year of the 10-K filing.churn_percentage: The calculated fraction of updated or modified paragraph blocks.themes: Tagged categories applied to newly identified risk paragraphs (e.g., Cybersecurity, Regulation).similarity_ratio: Fuzzy matching score between modified old/new paragraph pairs.
Edgar Risk Diff Advanced Features
- Premium Semantic Novelty Score: Leverages a local, deterministic hashed-bigram embedding algorithm to identify paraphrased or reframed risks that simple keyword diffs miss.
- Multi-Ticker Scan: Run batch assessments across an arbitrary list of tickers in a single command, ideal for generating automated market-wide daily risk digests.
- No-API Dependency: Eliminates third-party subscription costs by querying raw public SEC EDGAR endpoints directly while maintaining strict standard-compliant throttling.
- Local Zero-Telemetry Execution: Operates with strict data privacy, performing no analytical or telemetry tracking outside your self-hosted environment, making it a secure choice among Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
PDF to Structured JSON
A zero-configuration, intelligent document parsing skill powered by Laiye ADP that converts PDFs, images, and Office documents into structured JSON layouts.
WeChat Mini-Program Vibe Coding Starter
An AI agent skill designed to help non-engineers and product managers build, iterate, and launch WeChat Mini-Program MVPs from scratch using Vibe Coding methodologies.
Scientific Figure Analysis
An end-to-end multi-stage pipeline that extracts figures from scientific PDFs, analyzes them with Kimi K2.6 multimodal vision AI, and reverse-engineers their generation workflows.
CodeGraph Assistant
An automated wrapper for npm codegraph that simplifies codebase indexing, structural search, impact analysis, and context injection for AI programming.
Classical Chinese Commit Message Generator
An AI coding agent skill that translates staging area code changes into grammatically precise Classical Chinese git commit messages.
legal-verify
An advanced verification tool that extracts legal citations from draft texts and validates them against authoritative databases to eliminate LLM hallucinations.
Featured*
