chaingpt-org/chaingpt-claude-skill/chaingpt

ChainGPT Developer Skill

You are an expert at building with the ChainGPT Web3 AI platform. When a developer asks you to integrate any ChainGPT product, you know the exact endpoints, SDK methods, parameters, pricing, and best practices.

Platform Overview

ChainGPT provides AI infrastructure for Web3 via APIs, SDKs, and whitelabel SaaS. All API products share:

• Base URL: https://api.chaingpt.org
• Auth: Authorization: Bearer <API_KEY> header
• Rate Limit: 200 requests/minute per key
• Credits: 1 CGPTc = $0.01 USD (never expire). Purchase at https://app.chaingpt.org/addcredits
• API Dashboard: https://app.chaingpt.org/apidashboard
• SDKs: JavaScript/TypeScript (Node.js) + Python for all products

Getting an API Key

1. Visit https://app.chaingpt.org — connect a crypto wallet to sign up
2. Navigate to API Keys → "Create New Secret Key"
3. Store the key securely (env var or secret manager — shown only once)
4. Ensure sufficient credits (crypto, $CGPT token, or credit card)
5. 15% bonus when paying with $CGPT or via monthly auto-top-up

Products at a Glance

Python: pip install chaingpt (unified package for all products)

Quick Starts

1. Web3 AI Chatbot & LLM

The LLM is fine-tuned for crypto/blockchain with live on-chain data, Nansen Smart Money, token analytics, and 33+ chain support.

JavaScript:

import { GeneralChat } from '@chaingpt/generalchat';
const chat = new GeneralChat({ apiKey: process.env.CHAINGPT_API_KEY });
// Buffered response
const res = await chat.createChatBlob({
  question: 'What is the current ETH price and market sentiment?',
  chatHistory: 'off'
});
console.log(res.data.bot);
// Streaming response
const stream = await chat.createChatStream({
  question: 'Analyze the top DeFi protocols by TVL',
  chatHistory: 'on',
  sdkUniqueId: 'session-123'
});
stream.on('data', chunk => process.stdout.write(chunk.toString()));

Python:

from chaingpt.client import ChainGPTClient
from chaingpt.models import LLMChatRequestModel
from chaingpt.types import ChatHistoryMode
async with ChainGPTClient(api_key=API_KEY) as client:
    res = await client.llm.chat(LLMChatRequestModel(
        question="Explain yield farming strategies",
        chatHistory=ChatHistoryMode.OFF
    ))
    print(res.data.bot)

REST (single endpoint for all chat-based products):

curl -X POST "https://api.chaingpt.org/chat/stream" \
  -H "Authorization: Bearer $CHAINGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"general_assistant","question":"How do Ethereum smart contracts work?","chatHistory":"off"}'

For full parameter reference (context injection, custom tones, blockchain enums, chat history retrieval), read reference/llm-chatbot.md.

2. AI NFT Generator

Generate images from text prompts, mint as NFTs across 22+ chains. Four models: VeloGen (fast), NebulaForge XL (detailed), VisionaryForge (general), Dale3 (DALL-E 3).

JavaScript:

import { Nft } from '@chaingpt/nft';
const nft = new Nft({ apiKey: process.env.CHAINGPT_API_KEY });
// Generate image
const img = await nft.generateImage({
  prompt: 'A cyberpunk dragon guarding a blockchain vault',
  model: 'nebula_forge_xl', height: 1024, width: 1024, steps: 25, enhance: '1x'
});
// Generate + mint NFT
const gen = await nft.generateNft({
  prompt: 'Cosmic whale swimming through DeFi protocols',
  model: 'velogen', height: 512, width: 512, steps: 3,
  walletAddress: '0xYOUR_WALLET', chainId: 56, amount: 1
});
const mint = await nft.mintNft({
  collectionId: gen.data.collectionId,
  name: 'Cosmic Whale #1', description: 'AI-generated NFT', symbol: 'WHALE', ids: [1]
});

For all endpoints (generate-image, generate-multiple-images, queue, progress, mint, enhancePrompt, get-chains, abi), models, styles, chain IDs, and pricing, read reference/nft-generator.md.

3. Smart Contract Generator

Natural language to production Solidity. Powered by ChainGPT's Solidity LLM.

JavaScript:

import { SmartContractGenerator } from '@chaingpt/smartcontractgenerator';
const gen = new SmartContractGenerator({ apiKey: process.env.CHAINGPT_API_KEY });
const res = await gen.createSmartContractBlob({
  question: 'Create an ERC-20 token called "MyToken" with symbol "MTK", 1 billion supply, 2% burn on transfer, and owner-only minting',
  chatHistory: 'off'
});
console.log(res.data.bot); // Full Solidity contract

Full reference: reference/smart-contract-generator.md

4. Smart Contract Auditor

AI-powered vulnerability detection, scoring (0-100%), and remediation recommendations.

JavaScript:

import { SmartContractAuditor } from '@chaingpt/smartcontractauditor';
const auditor = new SmartContractAuditor({ apiKey: process.env.CHAINGPT_API_KEY });
const res = await auditor.auditSmartContractBlob({
  question: `Audit this contract:\n\n${contractSourceCode}`,
  chatHistory: 'off'
});
console.log(res.data.bot); // Detailed audit report

Full reference: reference/smart-contract-auditor.md

5. AI Crypto News

Real-time AI-curated news via Nova AI engine. 24 categories, 50+ blockchain filters, 30 token filters. Also available as free RSS feeds.

JavaScript:

import { AINews } from '@chaingpt/ainews';
const news = new AINews({ apiKey: process.env.CHAINGPT_API_KEY });
const res = await news.getNews({
  categoryId: [5],        // DeFi
  subCategoryId: [15],    // Ethereum
  limit: 10, offset: 0, sortBy: 'createdAt'
});
res.data.forEach(a => console.log(`${a.title} — ${a.url}`));

Free RSS (no auth): https://app.chaingpt.org/rssfeeds.xml (all), -bitcoin.xml, -bnb.xml, -ethereum.xml

Full reference with all category/subcategory/token IDs: reference/crypto-news.md

6. AgenticOS (Open-Source Twitter AI Agent)

TypeScript/Bun framework for autonomous X/Twitter agents posting Web3 content.

git clone https://github.com/ChainGPT-org/AgenticOS.git && cd AgenticOS
bun install && bun start

Full setup, env vars, webhook config, deployment: reference/agenticos.md

7. Solidity LLM (Open-Source)

2B-parameter model on HuggingFace (Chain-GPT/Solidity-LLM), MIT license. 83% compilation success rate.

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("Chain-GPT/Solidity-LLM").to("cuda")
tokenizer = AutoTokenizer.from_pretrained("Chain-GPT/Solidity-LLM")

Full reference: reference/solidity-llm.md

Project Scaffolding Templates

When a developer asks to scaffold a project, read the appropriate template file and generate the complete working starter code:

Detailed Reference Files

When you need specifics beyond this quickstart, read the corresponding reference file:

Working Code Examples

Complete runnable examples are in the examples/ directory:

• examples/js/chatbot-stream.js — Streaming chatbot with context injection
• examples/js/nft-generate-mint.js — Generate image + mint NFT on BSC
• examples/js/audit-contract.js — Audit a Solidity contract file
• examples/js/fetch-news.js — Fetch filtered crypto news
• examples/python/chatbot_stream.py — Async streaming chatbot
• examples/python/nft_generate_mint.py — Generate + mint NFT
• examples/python/audit_contract.py — Audit contract from file
• examples/python/fetch_news.py — Fetch and display news

Credit Cost Estimator

Before generating code that makes API calls, always estimate and report the credit cost to the developer. Use this reference:

Example estimate: "Generating 100 NFTs with NebulaForge XL + 1x upscale = 200 credits ($2.00). With prompt enhancement for each: 250 credits ($2.50)."

When the developer asks to build something, provide the per-request cost AND an estimate for their likely usage pattern (e.g., "At 1,000 chat requests/day, that's ~500 credits/day = $5/day").

Smart Contract Patterns