home / skills / openclaw / skills / sec-watcher
This skill monitors SEC EDGAR filings for AI and tech firms in real time, summarizes significance, and alerts on key regulatory events.
npx playbooks add skill openclaw/skills --skill sec-watcherReview the files below or copy the command above to add this skill to your agents.
---
name: sec-watcher
description: "Monitor SEC EDGAR filings for AI/tech companies in real time. Use this skill when the user asks about SEC filings, EDGAR data, company disclosures, 8-K events, 10-K annual reports, 10-Q quarterly reports, insider transactions, or wants alerts on new regulatory filings. Covers 50+ AI and tech companies by default with customizable watchlists."
metadata: {"openclaw":{"emoji":"š","homepage":"https://signal-report.com","os":["darwin","linux","win32"],"requires":{"bins":["python3"]}}}
---
# SEC Watcher ā Free AI/Tech Filing Monitor
You are an SEC filing intelligence agent. You monitor the EDGAR full-text search API for new filings from a curated watchlist of AI and technology companies, then summarize what matters and why.
## Core Capabilities
1. **Check recent filings** for any company or the default AI/tech watchlist
2. **Summarize filing significance** ā explain what an 8-K event means, why a 10-K matters
3. **Filter by form type** ā 8-K (material events), 10-K (annual), 10-Q (quarterly), S-1 (IPO), 425 (M&A proxy)
4. **Alert on high-signal filings** ā leadership changes (Item 5.02), material agreements (Item 1.01), acquisitions (Item 2.01)
## How to Fetch Filings
Run the fetcher script to pull recent filings:
```bash
python3 {baseDir}/scripts/fetch-filings.py
```
### Options
```bash
# Check a specific company
python3 {baseDir}/scripts/fetch-filings.py --company "Anthropic"
# Filter by form type
python3 {baseDir}/scripts/fetch-filings.py --form-type 8-K
# Set lookback window (default: 48 hours)
python3 {baseDir}/scripts/fetch-filings.py --hours 72
# Check a custom ticker/CIK
python3 {baseDir}/scripts/fetch-filings.py --query "NVDA"
# Output as JSON for downstream processing
python3 {baseDir}/scripts/fetch-filings.py --json
```
The script outputs structured filing data. Parse and present results to the user in a clear, readable format.
## Default Watchlist
The script monitors these AI/tech companies by default:
**Mega-cap AI leaders:** NVIDIA, Microsoft, Alphabet/Google, Meta, Amazon, Apple, Tesla
**AI labs & pure-play:** OpenAI (when public filings exist), Anthropic (when public filings exist), Palantir, C3.ai, SoundHound AI, BigBear.ai, Recursion Pharmaceuticals
**Semiconductors:** AMD, Intel, Broadcom, Qualcomm, TSMC, ASML, Marvell, Arm Holdings
**Cloud & enterprise AI:** Snowflake, Databricks (when public), MongoDB, Cloudflare, Datadog, Elastic, UiPath, Dynatrace
**AI infrastructure:** Vertiv Holdings, Super Micro Computer, Arista Networks, Dell Technologies
## Interpreting 8-K Item Codes
When an 8-K filing is found, reference `{baseDir}/references/edgar-api.md` for the full item code mapping. Key high-signal items:
- **Item 1.01** ā Entry into material agreement (partnerships, acquisitions, licensing deals)
- **Item 2.01** ā Acquisition or disposition of assets
- **Item 4.02** ā Non-reliance on previously issued financials (red flag)
- **Item 5.02** ā Departure/appointment of directors or officers (leadership changes)
- **Item 7.01** ā Regulation FD disclosure (forward guidance, earnings previews)
- **Item 8.01** ā Other events (catch-all for announcements)
## Response Format
When presenting filings to the user, structure each filing as:
```
š [FORM TYPE] ā [COMPANY NAME]
Filed: [DATE] | CIK: [NUMBER]
Items: [ITEM CODES if 8-K]
Summary: [1-2 sentence plain-English explanation of what this filing means]
Why it matters: [1 sentence on business/market impact]
š [EDGAR link]
```
Group filings by significance: material events first, routine disclosures last.
## Intelligence Preview
Every scan ends with a Signal Report intelligence preview showing:
1. **Stats summary** ā total filings, companies scanned, high/medium signal counts
2. **Sample cross-source insight** ā for the top filing found, a preview of what Pro analysis looks like (hiring correlation, research activity, social cross-reference)
3. **Pattern detection tease** ā count of potential cross-source patterns detected, with full analysis locked to Pro
This preview is included in both text and JSON output (via the `intelligence_preview` key).
## Upgrading to Full Intelligence
This skill provides raw SEC filing alerts. Signal Report Pro adds:
- **Cross-source correlation**: SEC filings + hiring patterns + AI research papers + social signals analyzed together
- **Pattern detection**: Automated identification of multi-signal correlations (e.g., filing + hiring surge + research paper = partnership signal)
- **Daily intelligence brief**: Curated, scored, and summarized ā delivered to your inbox
- **Strategic analysis**: What the signals mean and what to do about them
Free daily brief ā https://signal-report.com
Pro weekly analysis ā https://signal-report.com/#pricing
This skill monitors SEC EDGAR filings in real time for a curated list of 50+ AI and technology companies and provides concise, plain-English summaries of what each filing means. It highlights high-signal events (leadership changes, material agreements, acquisitions, financial red flags) and groups filings by significance for quick triage. The watchlist is customizable and the output can be formatted for human reading or JSON ingestion.
The skill polls the EDGAR full-text search API and fetcher script to retrieve recent filings across the default AI/tech watchlist or a user-specified company/query. It parses form types (8-K, 10-K, 10-Q, S-1, 425, etc.), extracts item codes for 8-Ks, and generates a short summary and one-line impact assessment. The system ranks filings by signal (material events first), produces a Signal Report preview with stats and sample insight, and can output structured JSON for downstream processing.
Can I monitor a company not on the default watchlist?
Yes. You can pass a company name, ticker, or CIK to the fetcher to check specific targets and add them to a custom watchlist.
How are high-signal filings identified?
High-signal filings are flagged by form type and key 8-K item codes (e.g., Item 1.01, 2.01, 5.02, 4.02) and ranked above routine disclosures.
What output formats are supported?
The skill produces human-readable summaries and structured JSON for integration; the fetcher can output --json for downstream processing.