GI ValueSider Superinvestor Data

Fetches Superinvestors' 13F portfolio holdings and buy/sell activity from ValueSider (valuesider.com). Use when the user asks for guru portfolio, 13F holding...

Security Scan

The skill's code, instructions, and requirements are coherent with its stated purpose (scraping and parsing ValueSider 13F pages); it requests no credentials or unusual installs and contains only straightforward parsing and optional HTTP fetch logic.

Purpose & Capability

The name/description (fetch ValueSider 13F holdings and activity) matches the included scripts and SKILL.md. The repo contains a parser and an optional fetcher; neither asks for unrelated credentials, unusual binaries, or unrelated platform access.

Instruction Scope

SKILL.md instructs the agent to fetch two ValueSider pages (portfolio and portfolio-activity) via web_fetch or to run the included fetch script, then parse the returned text with the provided parser. The instructions are focused on the task and only reference temporary files or stdin/stdout. Note: it explicitly advises using web_fetch to avoid 403 responses and expects full page text input — this is appropriate for scraping but means the agent will repeatedly retrieve external pages when invoked.

Install Mechanism

There is no platform install spec (instruction-only), which is low-risk. The package includes Python scripts and a requirements.txt (requests, beautifulsoup4) so dependencies must be installed manually or be present in the runtime. No downloads from untrusted URLs or archives, and no code obfuscation present.

Credentials

No environment variables, credentials, or config paths are required. The code sets a benign User-Agent header for HTTP requests and does not attempt to read secrets or unrelated files. The requested access is proportional to scraping/parsing web pages.

Persistence & Privilege

always is false, and the skill does not modify other skills or system-wide settings. It does not persist credentials or change agent configuration. Autonomous invocation is allowed by default (platform default) but not combined with other privileged behavior.

Assessment

What to consider before installing: - This skill scrapes valuesider.com and parses the returned page text. It requires no API keys or secrets. - If invoked, the agent will make outbound HTTP requests to valuesider.com (either via the platform's web_fetch or by running the included fetch script). If you have network or privacy policies, verify that such scraping is acceptable. - The skill provides a local test mode (scripts/run_test.sh with sample files) so you can validate parsing without hitting the network — try that first. - The included scripts are small and readable (no obfuscated code). If you require extra assurance, review scripts/fetch_valuesider.py and scripts/parse_fetched_content.py (they only request and parse HTML). - Consider ValueSider's terms of service and rate limits before heavy use; the parser is brittle by nature of scraping and may mis-parse if the site HTML changes. - If you do not want the agent to autonomously fetch pages, you can restrict the skill (disable autonomous invocation in your agent settings) or require manual fetch-and-paste into the parser.

ValueSider Superinvestor Data

Dynamically fetches portfolio and trading activity for value investors (Superinvestors) from ValueSider, based on SEC 13F filings. Real-time flow: fetch page with web_fetch → parse with script → return JSON.

When to use

• User asks for a Superinvestor / guru portfolio (e.g. Warren Buffett, Mason Hawkins, Longleaf Partners).
• User asks for 13F holdings or what stocks does [manager/fund] own.
• User asks for buy/sell activity (what is [guru] buying or selling).
• User mentions ValueSider or valuesider.com in the context of portfolio data.

Real-time flow (recommended)

ValueSider often returns 403 for direct HTTP requests. Use web fetch to get page content, then parse with the script.

Step 1: Resolve guru slug

• If the user gave a name (e.g. "Mason Hawkins"), use a known slug such as mason-hawkins-longleaf-partners, or fetch https://valuesider.com/value-investors with web_fetch and find the matching link (slug is the path between /guru/ and /portfolio).
• Common slugs: warren-buffett-berkshire-hathaway, mason-hawkins-longleaf-partners, seth-klarman-baupost-group, bill-ackman-pershing-square-capital-management.

Step 2: Fetch both pages with web_fetch

• Portfolio: https://valuesider.com/guru/{guru_slug}/portfolio
• Activity: https://valuesider.com/guru/{guru_slug}/portfolio-activity

Call web_fetch (or equivalent) for each URL and keep the returned text content.

Step 3: Parse content to JSON

Save the portfolio response to a temp file (e.g. _portfolio.txt), activity to _activity.txt. Then run:

# From the skill directory (gi-valuesider-superinvestor-data/)
python scripts/parse_fetched_content.py --type portfolio --file _portfolio.txt --guru-slug <guru_slug> --source-url "https://valuesider.com/guru/<guru_slug>/portfolio"
python scripts/parse_fetched_content.py --type activity --file _activity.txt --guru-slug <guru_slug> --source-url "https://valuesider.com/guru/<guru_slug>/portfolio-activity"

Or pipe content from stdin (no --file):

python scripts/parse_fetched_content.py --type portfolio --guru-slug mason-hawkins-longleaf-partners < _portfolio.txt

Output is JSON: portfolio has summary + holdings; activity has activities (quarter, ticker, stock_name, activity_type, share_change, pct_change_to_portfolio, reported_price, pct_of_portfolio).

Step 4: Present results

Summarize summary (period, portfolio value, number of holdings), list top holdings or recent buys/sells from the parsed JSON. Data is from ValueSider; do not present as financial advice.

---

Alternative: direct fetch script (when not 403)

If the environment allows (e.g. no 403), you can use the request-based script:

# List gurus (may 403)
python scripts/fetch_valuesider.py --list-gurus --limit 100

# Fetch one guru (may 403)
python scripts/fetch_valuesider.py <guru_slug>
python scripts/fetch_valuesider.py <guru_slug> --portfolio-only
python scripts/fetch_valuesider.py <guru_slug> --activity-only

Requires: pip install -r requirements.txt (requests, beautifulsoup4). On 403, use the real-time flow above instead.

Data source

• Portfolio: https://valuesider.com/guru/{guru_slug}/portfolio
• Activity: https://valuesider.com/guru/{guru_slug}/portfolio-activity
• Guru list: https://valuesider.com/value-investors