agentleFS
tellmefrankietellmefrankie/ai-investment-skills/llms.txt

ai-investment-skills

llms.txt14 starsChanged 6 months agoMITView on GitHub

Open-source Claude Code skills for investment analysis — options flow scanner, price monitoring, multi-agent debate system.

The file

We split this llms.txt into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Stop-loss and take-profit alerts via Telegram.

    line 12
  2. Distinctive:

    Test fixtures: /test/fixtures/ (RXRX noisy chain, CEL clean chain)

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 3,806 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# AI Investment Skills

> Open-source Claude Code skills for investment analysis — options flow scanner, price monitoring, multi-agent debate system.

## Skills

### Options Flow Analyzer
Analyzes options chain data with real vs lottery call separation. Raw P/C ratios are misleading — 84% of RXRX calls were $0.01 lottery tickets, making raw P/C 0.38 (bullish) when adjusted P/C was 2.38 (bearish). Uses Polygon.io API.
- Path: /options-flow-analyzer/SKILL.md

### Price Monitor Alert
Stop-loss and take-profit alerts via Telegram. Market hours aware — only fires during US market hours (9:30 AM - 4:00 PM ET). Uses Yahoo Finance.
- Path: /price-monitor-alert/SKILL.md

### News Sentiment Engine
RSS news collection → Claude AI analysis → Telegram delivery. Covers TechCrunch, The Verge, Ars Technica, Hacker News, Korean sources. Sentiment scoring, industry tagging, impact rating.
- Path: /news-sentiment-engine/SKILL.md

### Investment Briefing Agent
9-wave daily briefing: Macro → Sector → Technical → News → Finder → Critic → Simulator → DeepConnections → Meta. Produces actionable signals with cross-validation.
- Path: /investment-briefing-agent/SKILL.md

### Multi-Agent Orchestrator
9 specialized agents (Scanner, Critic, Analyst, Strategist, Cross-Validator) debating stock positions via threaded discussions. Anti-Narrative Harness enforces numbers over stories.
- Path: /multi-agent-orchestrator/SKILL.md

### EV Calculator
Expected value calculator for stock positions. Factors in probability-weighted upside/downside scenarios.
- Path: /ev-calculator/SKILL.md

## Key Concepts

### Lottery Filter
Options priced at $0.01-$0.05 (deep OTM) inflate raw P/C ratios. Filtering these reveals the actual institutional signal. Example: RXRX raw P/C 0.38 → adjusted 2.38 after removing 84% lottery calls.

### Anti-Narrative Harness
Rules that prevent AI agents from constructing misleading market narratives: cross-validate earnings dates, never attribute past events to current dates, numbers over stories.

### Signal-Side Context vs Reasoning-Side Outcome
Eval fixtures capture both what data the Critic saw (raw composition + cleaned ratio) and what conclusion it reached (debate transcript + decision). Enables retuning signal cleaning without losing reasoning quality data.

## Links

- GitHub: https://github.com/tellmefrankie/ai-investment-skills
- Test fixtures: /test/fixtures/ (RXRX noisy chain, CEL clean chain)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.