LLMQuant Skills MCP server
Provides reusable finance agent skills for equity research, options, macro, crypto, and portfolio management grounded in LLMQuant Data.
Also known as LLMQuant/skills
- Stars
- 246
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- May 30, 2026
- License
- MIT
What is LLMQuant Skills MCP?
LLMQuant Skills provides reusable finance agent skills for equity research, options, macro, crypto, and portfolio management grounded in LLMQuant Data.
Summary generated from the project's README
About LLMQuant Skills MCP server
Providing specialized financial workflows for AI agents is what this skill catalog enables. Developers can equip agents like Claude Code, Cursor, Codex, and Antigravity with eighteen distinct category skills covering equities, options, macro, crypto, credit, and portfolio management. These skills act as routers that guide an agent through specific financial procedures while ensuring all claims remain grounded in LLMQuant Data.
Users install these capabilities using the npx skills add command, which can target specific agents or install all categories globally. While the skills function as reusable workflows that can request user-provided data, they are designed to work natively with the LLMQuant Data MCP server. This connection allows agents to access prices, filings, 13F holdings, and macro snapshots through a single configuration. By using natural language to describe data needs, the system ensures that agents can navigate complex financial research tasks without manual tool reconfiguration.
What you can do with it
- 1Perform equity research and valuationAn agent can conduct a five-lens analysis or create a research memo for specific stocks.
- 2Analyze options volatility and GreeksA developer can task an agent with building an options strategy or monitoring an IV rank.
- 3Simulate portfolio exposure and riskUsers can run what-if simulations or generate portfolio exposure maps to test different market states.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablellmquant/skills is public and reachablegithub.com/llmquant/skills ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-05-30github.com/llmquant/skills ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubnpx skills add LLMQuant/skills # Claude Code · Codex · Cursor · Antigravity · OpenClaw · Hermes · …
[!TIP] 18 category skills — equities, options, macro, crypto, credit, portfolio, risk, and more — that route an agent to the right finance workflow and keep every claim grounded in LLMQuant Data.
Contents
Overview
This repository is a skill catalog. The install/import unit is a category folder under skills/llmquant-* — each one a router SKILL.md that indexes workflows/*.md, tells the agent which workflow to load, and enforces the LLMQuant Data evidence contract. It is not an isolated SKILL.md and not a single workflow file.
skills/
├── llmquant-data/
│ ├── SKILL.md
│ ├── workflows/
│ ├── scripts/
│ └── assets/
├── llmquant-etfs/
│ ├── SKILL.md
│ └── workflows/
└── ...
.claude-plugin/ # Claude Code plugin + marketplace manifests
.codex-plugin/ # Codex plugin manifest
.cursor-plugin/ # Cursor plugin manifest
assets/
README.md
README.zh-CN.md
Category Skills
| Skill | Scope | Key workflows |
|---|---|---|
llmquant-data |
LLMQuant Data primitives and source-grounded research. | 10-K risk review, 13F holders, U.S. macro snapshot, macro brief |
llmquant-equities |
Equity research, comparison, valuation, catalysts, and sell discipline. | Five-lens analysis, equity compare, research memo, merger arb, take-profit lab |
llmquant-etfs |
ETF holdings, overlap, concentration, and exposure analysis. | ETF overlap report |
llmquant-options |
Options, volatility, Greeks, unusual activity, and option backtests. | IV rank, strategy builder, Greeks dashboard, P&L simulator, volatility surface |
llmquant-equity-derivatives |
Single-stock derivative and hybrid security research. | Single-stock derivative playbook, convertible and warrant lens |
llmquant-commodities |
Commodity spot, futures curve, inventory, and macro linkage work. | Commodity market lens, futures curve monitor |
llmquant-crypto |
Crypto regime, token research, perpetual funding, basis, and leverage monitoring. | Crypto market regime, token research, perp funding monitor |
llmquant-prediction-markets |
Event odds, prediction-market contracts, probability gaps, and cross-venue arb review. | Event probability brief, arb watch, probability vs options pricing |
llmquant-macro |
Macro dashboards, central-bank previews, liquidity, growth, inflation, and portfolio impact. | Global macro dashboard, Fed policy preview, macro-to-portfolio impact |
llmquant-credit |
Issuer credit, spread regimes, high-yield stress, refinancing, and default risk. | Issuer credit risk review, credit spread regime, high-yield stress monitor |
llmquant-rates-fx |
Rates, yield curves, central-bank divergence, FX carry, and currency risk. | Yield curve trade lens, central-bank divergence, FX carry dashboard |
llmquant-events |
Earnings, M&A, regulatory, legal, policy, and catalyst event monitoring. | Earnings event brief, M&A event tracker, regulatory risk monitor |
llmquant-portfolio |
Company profiles, thesis tracking, watchlists, alerts, and themes. | Company profile, thesis tracker, theme research, watchlist monitor, alert manager |
llmquant-portfolio-lab |
Portfolio exposure maps, what-if simulations, and virtual portfolio states. | Portfolio exposure map, portfolio what-if simulator |
llmquant-risk |
Risk regime, hedging, panic scoring, and research quality checks. | Fear score, VIX status, hedge advisor, research health check |
llmquant-strategies |
Hedge-fund and PM strategy playbooks. | Equity long/short, long-biased, event-driven, macro, quant, multi-strategy |
llmquant-market-intelligence |
Reusable market utilities and signal views. | Macro view, market sentiment, event probability signals |
llmquant-investor-lenses |
Investor-style reasoning overlays using LLMQuant Data evidence. | Buffett, Graham, Munger, Lynch, Fisher, Burry, Ackman, Damodaran, and more |
Install
Recommended: npx skills add
One command, and it works across Claude Code, Codex, Cursor, Antigravity, Gemini, and other agents.
[!TIP] Already inside an agent? Just run
npx skills add LLMQuant/skills— it auto-detects the host and installs to the right place.
# Pick skills interactively for the current agent
npx skills add LLMQuant/skills
# Install all category skills globally
npx skills add LLMQuant/skills -g --all
# Install specific skills
npx skills add LLMQuant/skills -g --skill llmquant-options llmquant-equities
# Target a specific agent
npx skills add LLMQuant/skills -a codex
Manage installed skills with npx skills list, npx skills update, and npx skills remove. Then ask the agent What skills are available?, or invoke one directly, e.g. /llmquant-options.
Native plugin install
The whole repository is also packaged as a single plugin that bundles every category skill, for agents with a native plugin system.
Claude Code — add this repo as a plugin marketplace, then install the bundle:
/plugin marketplace add LLMQuant/skills
/plugin install llmquant-skills@llmquant
Codex — the repo ships .codex-plugin/plugin.json, so it is plugin-ready. To install today, use the CLI above (npx skills add LLMQuant/skills -a codex), or install a single category skill via the skill installer:
$skill-installer install https://github.com/LLMQuant/skills/tree/main/skills/llmquant-options
Cursor · Antigravity · other agents — use the recommended CLI with the matching agent, e.g. npx skills add LLMQuant/skills -a cursor or -a antigravity.
LLMQuant Data
These skills are the workflow layer for LLMQuant Data — one MCP server that feeds prices, filings, 13F, macro, ETF holdings, crypto, and more to your agents. Configure once, and every agent in your stack gets the data.
Set it up the AI-native way — paste this to your agent:
Install the LLMQuant data-mcp server in this environment by following https://github.com/LLMQuant/data-mcp
Or add it by hand:
claude mcp add llmquant-data -e LLMQUANT_API_KEY=your_api_key -- npx -y @llmquant/data-mcp
[!NOTE] Grab an API key and the full multi-agent setup at docs.llmquantdata.com and
LLMQuant/data-mcp.
Skills describe the data they need in natural language and let the agent route to whatever LLMQuant Data exposes, so coverage can grow without editing any skill. Without llmquant-data connected, skills still run as reusable workflows — the agent asks for user-provided data and clearly labels anything missing. The full evidence contract is in CONTRIBUTING.md.
Contributing
Add or update workflows inside the relevant category (skills/llmquant-<category>/ → SKILL.md + workflows/ + scripts/ + assets/):
- Category folders must be named
llmquant-*, andSKILL.mdis the router that indexes every workflow. - Workflow files hold the repeatable procedure, output format, data contract, and guardrails.
- Describe data needs as natural-language capabilities, not exact MCP tool names.
- Update this README when a category or major workflow is added, removed, or renamed.
See CONTRIBUTING.md for the full contract and quality bar.
License
MIT — see LICENSE. Listing a project here does not change the license of any linked code or artifact.
Star History
LLMQuant Skills MCP questions
What kind of financial skills are available?
The catalog includes 18 categories such as equities, options, macro, crypto, credit, portfolio, risk, and more.
How do I install these skills for Claude Code or Cursor?
You can install them using the command npx skills add LLMQuant/skills, which auto-detects your host agent.
Do I need the LLMQuant Data MCP server for these skills to work?
While skills can run as reusable workflows by asking for user-provided data, they are designed to work with the LLMQuant Data MCP server for grounded research.