Trader Pelosi logo

Trader Pelosi

Community
Jakeschincariol
trader-pelosi

The Pelosi Tracker. Watches the stock trades members of Congress must disclose under the STOCK Act: reads the House Clerk's public Periodic Transaction Reports (PTRs) as soon as they are posted, alerts once per new filing, and turns each PDF into clean rows (who, owner, stock, ticker, buy or sell, options strike and expiry, trade date, amount range, how many days it took to disclose). Flags trades in stocks you hold. Senate reports are covered by a documented manual route. Use when the user says "what is Pelosi buying", "track Nancy Pelosi", "Congress trades", "politician stock trades", "did any congressman buy X", "alert me when Pelosi files", or "run the Pelosi skill".

Overview

PublisherJakeschincariol
Repositoryday-trader-skill
Skill nametrader-pelosi
Stars
617
Forks
119
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Jakeschincariol on GitHub. Read the source before you install it.

Installation

Install the Trader Pelosi AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Jakeschincariol/day-trader-skill/tree/main/trader-pelosi
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Jakeschincariol/day-trader-skill.git /tmp/day-trader-skill
mkdir -p .claude/skills
cp -r /tmp/day-trader-skill/trader-pelosi .claude/skills/trader-pelosi
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Trader Pelosi in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Trader Pelosi on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Trader Pelosi is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

trader-pelosi

Members of Congress have to report their trades, their spouse's and their dependent children's. The House Clerk posts every report as a PDF and lists them all in one index file per year. This skill reads that index, notices the moment a new report appears, and reads the report for you.

It is fast. It is not early. A PTR is due within 30 days of the member learning of the trade and never more than 45 days after it, so by the time anyone can read it the trade is days or weeks old. There is no inside information here: only public filings, read quickly. Say that every time.

Tool in this folder (standard library Python; pdftotext from poppler is optional, to read the PDFs locally):

bash
python3 "${CLAUDE_SKILL_DIR}/ptr.py" --help

What it reads and writes

  • Reads https://disclosures-clerk.house.gov/public_disc/financial-pdfs/<YEAR>FD.zip (one <Member> per filing: name, district, FilingType, FilingDate, DocID) and each PTR at .../public_disc/ptr-pdfs/<YEAR>/<DocID>.pdf.
  • Writes trader/state/pelosi.json (the DocIDs already shown, so each PTR alerts once) and keeps downloaded PDFs in trader/state/ptr-pdfs/.
  • Reads trader/portfolio.json (if it exists) to flag trades in what you hold.

The rules

  • Quote the filing, not a tracker. Every row comes from the PTR PDF on the Clerk's site, with its DocID and link. Third-party trackers are fine for browsing but can be off (Capitol Trades showed Pelosi's trade dates one day earlier than her PTRs). The PTR wins.
  • Amounts are ranges. "$1,000,001 - $5,000,000", never "$3 million".
  • Owner matters. SP is the spouse, JT joint, DC a dependent child, blank the member. Pelosi's 2026 trades are all SP: Paul Pelosi.
  • Say the delay. Each row shows how many days passed between the trade and the filing; over 45 is flagged as late.
  • Options are options. A call bought with a strike and an expiry is not a share purchase. The tool reads contracts, strike and expiry from the description and marks exercises.

Step 1: what has been filed

bash
python3 "${CLAUDE_SKILL_DIR}/ptr.py" index --member pelosi
python3 "${CLAUDE_SKILL_DIR}/ptr.py" index --since 2026-10-01        # every member
python3 "${CLAUDE_SKILL_DIR}/ptr.py" index --member "Josh Gottheimer" --year 2025

--member takes a last name, "First Last" or "Last, First", and repeats. --type '' lists every filing type (annual reports are type O).

Step 2: watch for new ones

bash
python3 "${CLAUDE_SKILL_DIR}/ptr.py" new --member pelosi --read

Shows only PTRs not seen at the last check (the first run shows the last 45 days), downloads and reads them with --read, and records them in the state file. Exit code 1 means nothing new. In January it also checks last year's index. The Clerk rebuilds the index file about once a day (the copy read on 2026-10-13 was stamped 09:00 that morning), so checking every hour on weekdays is plenty: run it with /loop 1h or a scheduled task.

Step 3: read a report

bash
python3 "${CLAUDE_SKILL_DIR}/ptr.py" fetch 20035143
python3 "${CLAUDE_SKILL_DIR}/ptr.py" parse ptr.txt --filed 2026-08-21 --json

fetch saves the PDF and, if pdftotext is installed, prints the rows. If it is not installed, open the saved PDF and read it directly: you can read PDFs. parse turns pdftotext -layout text into rows. Check the row count against the PDF when a report runs over several pages.

Example: a real alert

NEW Periodic Transaction Report: Hon. Nancy Pelosi (CA11) filed 2026-08-21, doc 20035143
  - spouse purchase, Bloom Energy Corporation Class A Common Stock (BE): 100 call
    options, $100 strike, expires 2027-06-17, $1,000,001 - $5,000,000, traded
    2026-07-24, disclosed 28 days later

The same PTR also shows 10,000 and 5,000 BE shares, a second block of 100 BE calls on 07/28, Intel shares and 50 Intel calls ($50 strike, 6/17/27), and a private real estate LLC with no ticker. Her other 2026 PTRs: 20033725 (01/23), 20034836 (06/23, Intel and Uber calls) and 20035553 (10/02, a real estate LLC). Then: "This is a public disclosure filed 28 days after the trade. It says what Paul Pelosi bought in July, not what anyone will buy next."

If the user wants to act on it, it goes the long way: a disclosure is weeks old, so it is a reason to look at a chart, not a setup. /trader-scanner and /trader-entry decide if there is a trade today; then shares only (the config has allow_options: false), sized by /trader-budget, checked by /trader-risk, placed by /trader-broker only after their yes.

The Senate: the manual route

Senate reports live at https://efdsearch.senate.gov. Before searching, the site asks you to tick a box agreeing to the legal limits on how the reports may be used. That is an agreement for the person to accept, so this skill does not click it or automate it. The route:

  1. The user opens https://efdsearch.senate.gov/search/ in their browser and accepts the agreement themselves.
  2. They pick the report type "Periodic Transactions", type the senator's last name, set the date range and search.
  3. They open the report: electronic filings show a table of transactions, paper filings are scanned images.
  4. They paste the table (or a screenshot, or the saved page) into the chat, and you write it up in the same shape as the House rows, with the report link, and the same 45-day caveat.

What it never does

  • Never says or implies a member has inside information, or that copying a politician beats the market. No return claims.
  • Never presents a range as an exact dollar figure or a tracker's date as the trade date.
  • Never places an order, and never copies options trades.
  • Never automates the Senate agreement or any login.

Safety

  • Education and tooling, not financial advice. Nothing in this pack is a recommendation to buy or sell anything.
  • Paper trading by default ("paper": true in trader/config.json).
  • Nothing places an order except /trader-broker, and only after /trader-risk passes AND the user types an explicit yes for that order in the chat, AND the brokerage tool is set to "Needs approval" in Claude (Customize > Connectors > tool permissions) so Claude's own "Allow once / Deny" card appears too. Never "Always allow" an order tool.
  • No options, margin, shorting or leverage unless the config allows it and the user confirms.
  • Congressional trades are PUBLIC disclosures filed up to 45 days after the trade (STOCK Act). This skill reads them fast; it has no inside information, and it says so.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Trader Pelosi AI skill do?

The Pelosi Tracker. Watches the stock trades members of Congress must disclose under the STOCK Act: reads the House Clerk's public Periodic Transaction Reports (PTRs) as soon as they are posted, alerts once per new filing, and turns each PDF into clean rows (who, owner, stock, ticker, buy or sell, options strike and expiry, trade date, amount range, how many days it took to disclose). Flags trades in stocks you hold. Senate reports are covered by a documented manual route. Use when the user says "what is Pelosi buying", "track Nancy Pelosi", "Congress trades", "politician stock trades", "di...

Why use Trader Pelosi on TypingMind?

Because you install it once and use it with any model. Trader Pelosi is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Trader Pelosi in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Jakeschincariol/day-trader-skill/tree/main/trader-pelosi. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Trader Pelosi?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Trader Pelosi?

As many as you like. As long as a model supports skills, you can use Trader Pelosi with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Trader Pelosi AI skill free?

Yes. It is published on GitHub by Jakeschincariol under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇