Mm logo

Mm

CommunityPopular
alsk1992
mm

Market making - two-sided quoting with inventory management

Overview

Publisheralsk1992
RepositoryCloddsBot
Skill namemm
Stars
2.8K
Forks
336
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 alsk1992 on GitHub. Read the source before you install it.

Installation

Install the Mm 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.
  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/alsk1992/CloddsBot.git /tmp/CloddsBot
mkdir -p .claude/skills
cp -r /tmp/CloddsBot/src/skills/bundled/mm .claude/skills/mm
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mm 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 Mm 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 Mm 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.

Market Making Skill

Automated two-sided quoting on prediction markets with inventory skew, volatility-adjusted spreads, and risk controls.

Supported Platforms

  • Polymarket (post-only maker orders, zero taker fees)
  • Kalshi

Chat Commands

Lifecycle

/mm start <platform> <marketId> <tokenId> [flags]   Start market making
/mm stop <id>                                        Stop and cancel all orders
/mm list                                             List active market makers

Monitoring

/mm status                     Overview of all active MMs
/mm status <id>                Detailed state for one MM

Configuration

/mm config <id>                View current config as JSON
/mm config <id> --spread 3     Update config (takes effect next requote)

Start Flags

FlagDefaultDescription
--spread N2Base half-spread in cents
--min-spread N1Minimum spread floor (cents)
--max-spread N10Maximum spread cap (cents)
--size N50Order size per side (shares)
--max-inventory N500Max inventory before aggressive skew
--skew N0.5Inventory skew factor (0-1)
--vol-mult N10Volatility multiplier for spread widening
--alpha N0.3EMA alpha for fair value smoothing (0-1)
--fv-method Mweighted_midFair value method: mid_price, weighted_mid, vwap, ema
--interval N5000Requote interval in ms
--threshold N1Min price change (cents) to trigger requote
--max-pos N1000Max position value in USD
--max-loss N100Max loss before auto-halt (USD)
--max-orders N1Orders per side (levels)
--level-spacing N(=spread)Cents between price levels
--level-decay N0.5Size decay per level (0-1, e.g. 0.5 = each level half of previous)
--neg-risk truefalseEnable negative risk mode (Polymarket crypto)
--name "Name"autoDisplay name for the outcome

Examples

# Start with defaults
/mm start polymarket 0xabc123 98765

# Custom spread and sizing
/mm start polymarket 0xabc123 98765 --spread 3 --size 100 --max-inventory 1000

# Tight spread for liquid market
/mm start polymarket 0xabc123 98765 --spread 1 --min-spread 1 --max-spread 5 --interval 2000

# 3-level quoting: L1=50 shares, L2=25, L3=12 — spaced 2c apart
/mm start polymarket 0xabc123 98765 --max-orders 3 --level-spacing 2 --level-decay 0.5 --size 50

# Check all running MMs
/mm status

# Widen spread on the fly
/mm config polymarket_98765678 --spread 4

# Shut down
/mm stop polymarket_98765678

How It Works

  1. Fair value computed from orderbook (weighted mid, VWAP, or EMA)
  2. Spread adjusted by recent volatility (wider in volatile markets)
  3. Skew shifts quotes away from overweight side to manage inventory
  4. Quotes placed as post-only maker orders (bid and ask)
  5. Requote cycle: cancel all, recalculate, place new orders
  6. Auto-halt if realized P&L exceeds max loss threshold

API Usage

typescript
import { createMMStrategy, type MMConfig } from '../trading/market-making';

const config: MMConfig = {
  id: 'btc-yes',
  platform: 'polymarket',
  marketId: '0x...',
  tokenId: '12345',
  outcomeName: 'BTC > 100k',
  baseSpreadCents: 2,
  minSpreadCents: 1,
  maxSpreadCents: 10,
  orderSize: 50,
  maxInventory: 500,
  skewFactor: 0.5,
  volatilityMultiplier: 10,
  fairValueAlpha: 0.3,
  fairValueMethod: 'weighted_mid',
  requoteIntervalMs: 5000,
  requoteThresholdCents: 1,
  maxPositionValueUsd: 1000,
  maxLossUsd: 100,
  maxOrdersPerSide: 1,
};

const strategy = createMMStrategy(config, { execution, feeds });
botManager.registerStrategy(strategy);
await botManager.startBot(strategy.config.id);

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 Mm AI skill do?

Market making - two-sided quoting with inventory management

Why use Mm on TypingMind?

Because you install it once and use it with any model. Mm 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 Mm in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alsk1992/CloddsBot/tree/main/src/skills/bundled/mm. 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 Mm?

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 Mm?

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

Is the Mm AI skill free?

Yes. It is published on GitHub by alsk1992 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 👇