# options-analytics-agent-langgraph

Builds a LangGraph agent that pulls options data from Polygon.io, caches it in ChromaDB and keeps memory across sessions. Useful when you want your own trading assistant.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2000 installs · ★ 5
- Author: reason-machines
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/data-skills/tree/HEAD/skills/options-analytics-agent-langgraph/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/options-analytics-agent-langgraph

## What it does

The skill scaffolds a project where LangGraph wires several tools into one workflow. Options search goes through Polygon.io, results land in a ChromaDB cache, and semantic search runs over that cache — you can ask about heavy volume or near-the-money contracts in plain words. Conversation history sits in SQLite, so the agent remembers earlier sessions.

Separate tools handle batch lookups across tickers, Greeks and sentiment analysis, anomaly detection, CSV export and chart generation. A FastAPI microservice wraps the whole thing if you want to run the agent as a standalone service.

You need Python 3.10 and both `OPENAI_API_KEY` and `POLYGON_API_KEY` in a `.env` file. Without the Polygon.io key options search simply fails, since that is the only data source here. `TAVILY_API_KEY` and `LANGCHAIN_API_KEY` matter only for web search and tracing. Dependencies come from `requirements.txt` and include langgraph, chromadb, fastapi and pandas.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill options-analytics-agent-langgraph -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/options-analytics-agent-langgraph/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/options-analytics-agent-langgraph/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill options-analytics-agent-langgraph -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/options-analytics-agent-langgraph/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill options-analytics-agent-langgraph -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/options-analytics-agent-langgraph/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/data-skills options-analytics-agent-langgraph
```

2. **Manually: put the files in place**
- File: `.github/skills/options-analytics-agent-langgraph/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill options-analytics-agent-langgraph -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/data-skills --path skills/options-analytics-agent-langgraph
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/options-analytics-agent-langgraph/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/data-skills --skill options-analytics-agent-langgraph -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/data-skills/tree/HEAD/skills/options-analytics-agent-langgraph/SKILL.md

## When to use it
- scaffold an agent that reads an options chain for a ticker
- cache Polygon.io responses instead of hitting the API twice
- query stored options data with a plain-language phrase
- compute Greeks and flag volume anomalies per contract
- export selected contracts to CSV or a chart

## Example prompts
- Build a LangGraph agent for analyzing AAPL options
- Set up ChromaDB as a cache for Polygon.io data
- Add Greeks analysis and anomaly detection to the agent

## Similar
- [langgraph-persistence](https://affpapa.org/en/nevibecode/skills/langgraph-persistence.md) — skill · 18000 installs
- [langgraph-fundamentals](https://affpapa.org/en/nevibecode/skills/langgraph-fundamentals.md) — skill · 18000 installs
- [langgraph](https://affpapa.org/en/nevibecode/skills/sickn33-langgraph.md) — skill · 1300 installs
- [langgraph-code-review](https://affpapa.org/en/nevibecode/skills/langgraph-code-review.md) — skill · 884 installs
- [langchain-development](https://affpapa.org/en/nevibecode/skills/langchain-development.md) — skill · 681 installs
- [options-strategy-advisor](https://affpapa.org/en/nevibecode/skills/options-strategy-advisor.md) — skill · 3700 installs

From the same set: [reason-machines/data-skills](https://affpapa.org/en/nevibecode/by/reason-machines/data-skills.md) — 22 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md