TypingMindTypingMindThe best frontend for AI
Noraz Swarm Trading logo

Noraz Swarm Trading

Community
mogons
noraz-swarm-trading

Autonomous multi-agent crypto trading skill for Robinhood Chain EVM DEX tokens and NFTs using 3-layer Swarm Consensus, Discord Command Center, and Position Management.

Overview

Publishermogons
Repositorynoraz-agent
Skill namenoraz-swarm-trading
Stars
169
Forks
167
Bundled files
Instructions only
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Noraz Swarm Trading 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/mogons/noraz-agent/tree/master/.agents/skills/noraz-swarm-trading
  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/mogons/noraz-agent.git /tmp/noraz-agent
mkdir -p .claude/skills
cp -r /tmp/noraz-agent/.agents/skills/noraz-swarm-trading .claude/skills/noraz-swarm-trading
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Noraz Swarm Trading 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 Noraz Swarm Trading 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 Noraz Swarm Trading 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.

Noraz Swarm Trading & Intelligence Skill

This skill defines the operational standards, decision pipelines, and multi-agent coordination rules for the Noraz AI (Robinhood Chain Edition) ecosystem.

1. Robinhood Chain Meme Signal Categories

Screening agents scan across 3 high-potential token opportunities:

  1. 🐣 Established Launches & CTO Tokens: Robinhood DEX tokens with active DEX liquidity and a Community Takeover (CTO) or dev-closed profile (no age gate — minAgeHours=0 in both presets).
  2. 🧟 Revival & CTO Tokens (Dead Tokens Waking Up): Established tokens (>= 4h age) with a sudden 1H price move > +50%, 2+ GMGN Smart Wallet accumulation, and dev 0% / CTO (Community Takeover).
  3. 🚀 Volume Surge & Trend Breakouts: Tokens breaking key resistance levels confirmed by 1H GMGN Smart Money Net Inflows.

Configurable thresholds: thresholds below are the LOOSENED defaults (2x) configured at onboarding; users can switch to Standard, edit numbers, or supply a custom strategy prompt (compiled by Noraz after deploy). All gates fail-closed; swarm >= 80% floor unchanged.

Layer 1: Quant & Liquidity Audit

  • Timeframe: 24H (24-hour rolling volume, liquidity, and trend evaluation).
  • Minimum Token Age: loosened default minAgeHours=0 — degen early access (new tokens pass immediately — smart money/CTO/KOL decide); the age gate is only enforced when minAgeHours > 0 is configured (e.g. via set_screening_config in the control room). Standard preset: minAgeHours=0 too — the age gate is off in both presets; the Revival signal type still requires tokens >= 4h old.
  • Minimum Volume: loosened default 24h volume ≥ $25,000 (Standard: 24h volume ≥ $50,000). Both are plain 24h gates — no hourly-volume or surge-ratio gate exists.
  • Minimum Liquidity: loosened default $5,000 USD (Standard: $10,000 USD).
  • Minimum Fees: loosened default total fees ≥ $250 (Standard: total fees ≥ $500; the gate only enforces when configured > 0).
  • Transaction Ratio: Buy vs Sell transaction ratio evaluation (momentum requires buy dominance).

Layer 2: Catalyst & Social Hype Audit

  • GMGN Social Data: Uses GMGN social fields (smart-money wallet counts, KOL counts, square mentions, visiting count, X/twitter activity flags — rename/delete/post counts) to score hype deterministically with local rules.
  • LLM Sentiment: LLM reasoning is reserved for high-value tasks only — interpreting social sentiment for the final AI Thesis and answering user chat queries in the command room (token & API cost optimization). Screening passes themselves are deterministic.
  • Narrative Match: Viral meme topic & community engagement scoring.

Layer 3: Security & Runner Token Audit Checklist (GMGN /token/security)

Flexible thresholds designed to capture high-potential RUNNER tokens while avoiding scams. These map to GMGN security fields available for the robinhood chain; where a field is unavailable, the audit is fail-closed (unverified = rejected):

  1. 👥 Top 10 Holders Control: MUST be <= 25% (allows healthy community & cabal backing).
  2. 👨‍💻 Dev Holding %: MUST be <= 10% (allows marketing/airdrop reserve).
  3. 🐋 Snipers %: MUST be <= 20% (realistic sniper threshold for runner tokens).
  4. 🕵️ Insiders %: MUST be <= 20% (realistic team/insider allocation).
  5. 🤖 Bundler %: MUST be <= 25% (allows early bundler momentum for runner launches).
  6. 🎣 Phishing Risk %: MUST be <= 3%.
  7. 💳 Dex Paid Status: MUST be DexScreener Paid (Paid status is mandatory to filter out low-effort rugs).
  8. 🚫 NoMint: Mint Authority MUST be disabled.
  9. 🛡️ No Blacklist: Blacklist Authority MUST be disabled.
  10. 🔥 Burnt LP %: 100% LP Burned / Permanent Lock.
  11. ⚠️ Rug Risk Score %: Overall calculated Rug Risk MUST be <= 5% (Runner Safe Zone).
  12. 📊 Holder Count Growth: Unique holders count verification.
  • Fail-Closed Note: every Layer 3 audit gate runs through GMGN /v1/token/security (per-token audit endpoint) + GMGN rank security fields. A missing/unavailable audit field or failed audit = REJECT — tokens are never passed on missing data.
  • Global Risk Limit: Verify daily portfolio drawdown < 5%.

2. Discord Call & Execution Standards

  • Informational Calls: Deliver to dedicated channels (#call-meme-robinhood, #call-lp-robinhood, #call-nft-robinhood, #call-alpha-robinhood, #call-whale-eth).
  • Interactive Action Links & Buttons: Provide [VIEW ON DEXSCREENER], [TRADE ON UNISWAP], and [PAUSE SCREENING].
  • Command Execution: User buys are executed securely via Noraz Core Hub in #noraz-control-room.

3. Position Management (Auto TP / SL)

Upon trade execution:

  • Take Profit (TP): Scale out 50% at +100% (2x), 25% at +200% (3x).
  • Stop Loss (SL): Hard stop loss execution if token drops by configured limit (default -20%).
  • Trailing Stop: Adjust stop loss upwards dynamically as high-water mark increases.

4. Trade Audit & Diagnostic Logging

  • Log every signal, thesis, entry price, execution time, and exit PnL in the database.
  • Support natural language trade diagnostics when queried in Discord.

Frequently asked questions

What does the Noraz Swarm Trading AI skill do?

Autonomous multi-agent crypto trading skill for Robinhood Chain EVM DEX tokens and NFTs using 3-layer Swarm Consensus, Discord Command Center, and Position Management.

Why use Noraz Swarm Trading on TypingMind?

Because you install it once and use it with any model. Noraz Swarm Trading 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 Noraz Swarm Trading in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mogons/noraz-agent/tree/master/.agents/skills/noraz-swarm-trading. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Noraz Swarm Trading?

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 Noraz Swarm Trading?

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

Is the Noraz Swarm Trading AI skill free?

Yes. It is published on GitHub by mogons 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.

Related AI Skills

View all
bytedance logo

Github Deep Research

bytedance
OrganizationPopular

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces…

11.4K
82.6K
2 files
View
ComposioHQ logo

Changelog Generator

ComposioHQ
OrganizationPopular

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns…

8.7K
75.2K
Instructions
View
thedaviddias logo

Ai Content

thedaviddias
CommunityPopular

Use when auditing metadata, crawlability, structured data, or indexability related to Audit and refine AI-generated content. Verify the rendered HTML and HTTP response rather than relying only on…

6.7K
74.2K
1 files
View
coreyhaines31 logo

Ab Testing

coreyhaines31
CommunityPopular

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test…

7.7K
50.7K
3 files
View

Set up your own AI workspace now

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