DeFi Protocol Templates
wshobson/agents
Solidity templates for DeFi building blocks: staking with reward distribution, an automated market maker, governance tokens and flash loans.
Build with the ChainGPT Web3 AI developer platform. An agent skill from internet-court/internet-court-skill.
$ npx skills add internet-court/internet-court-skill --skill chaingpt -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install internet-court/internet-court-skill chaingpt --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/internet-court/internet-court-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/vendored/chaingpt/chaingpt .claude/skills/chaingpt && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "chaingpt" agent skill from https://github.com/internet-court/internet-court-skill/tree/main/vendored/chaingpt/chaingpt into .claude/skills/chaingpt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chaingpt", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/internet-court/internet-court-skill/tree/main/vendored/chaingpt/chaingptType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add internet-court/internet-court-skill --skill chaingpt -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install internet-court/internet-court-skill chaingpt --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/internet-court/internet-court-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/vendored/chaingpt/chaingpt .agents/skills/chaingpt && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "chaingpt" agent skill from https://github.com/internet-court/internet-court-skill/tree/main/vendored/chaingpt/chaingpt into .agents/skills/chaingpt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chaingpt", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add internet-court/internet-court-skill --skill chaingpt -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install internet-court/internet-court-skill chaingpt --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/internet-court/internet-court-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/vendored/chaingpt/chaingpt .cursor/skills/chaingpt && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "chaingpt" agent skill from https://github.com/internet-court/internet-court-skill/tree/main/vendored/chaingpt/chaingpt into .cursor/skills/chaingpt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chaingpt", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/internet-court/internet-court-skill.git --path vendored/chaingpt/chaingpt--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add internet-court/internet-court-skill --skill chaingpt -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install internet-court/internet-court-skill chaingpt --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/internet-court/internet-court-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/vendored/chaingpt/chaingpt .gemini/skills/chaingpt && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "chaingpt" agent skill from https://github.com/internet-court/internet-court-skill/tree/main/vendored/chaingpt/chaingpt into .gemini/skills/chaingpt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chaingpt", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install internet-court/internet-court-skill chaingptInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add internet-court/internet-court-skill --skill chaingpt -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/internet-court/internet-court-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/vendored/chaingpt/chaingpt .github/skills/chaingpt && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "chaingpt" agent skill from https://github.com/internet-court/internet-court-skill/tree/main/vendored/chaingpt/chaingpt into .github/skills/chaingpt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chaingpt", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add internet-court/internet-court-skill --skill chaingpt -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install internet-court/internet-court-skill chaingpt --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/internet-court/internet-court-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/vendored/chaingpt/chaingpt .opencode/skills/chaingpt && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "chaingpt" agent skill from https://github.com/internet-court/internet-court-skill/tree/main/vendored/chaingpt/chaingpt into .opencode/skills/chaingpt/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chaingpt", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
chaingptBuild with the ChainGPT Web3 AI developer platform. An agent skill from internet-court/internet-court-skill.
Chaingpt is an agent skill from internet-court/internet-court-skill. Build with the ChainGPT Web3 AI developer platform. Full API/SDK reference and project scaffolding for: Web3 AI Chatbot & LLM, AI NFT Generator, Smart Contract Generator, Smart Contract Auditor, AI Crypto News, AgenticOS Twitter agents, and Solidity LLM. Use when building blockchain apps, Web3 chatbots, NFT tools, smart contract tools, crypto news feeds, AI agents, or integrating any ChainGPT API. Triggers: chaingpt, web3 ai, nft generator, smart contract audit, crypto news api, agenticos, solidity llm, cgpt…
Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.
It sits in Backend & APIs, covering Crypto and DeFi analysis and Smart contracts. It works with Solidity and X (Twitter). The repository describes itself as: The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all… The licence is MIT.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit fa89195. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
buncurlgitpipFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
api.chaingpt.orggithub.comAlso links to:
chaingpt.orgdocs.chaingpt.orghuggingface.cocalendly.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
CHAINGPT_API_KEYAPI_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Chaingpt loads about 4k tokens when it runs. Until then it costs about 139 tokens; SKILL.md has 1,305 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from internet-court/internet-court-skill at commit fa89195, republished under its MIT licence (© internet-court). 1,305 words, ~4,025 tokens.
.claude/skills/chaingpt/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.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.
ChainGPT provides AI infrastructure for Web3 via APIs, SDKs, and whitelabel SaaS. All API products share:
https://api.chaingpt.orgAuthorization: Bearer <API_KEY> header| Product | NPM Package | Model ID / Endpoint | Cost per Request |
|---|---|---|---|
| Web3 AI Chatbot & LLM | @chaingpt/generalchat | general_assistant via POST /chat/stream | 0.5 credits (+0.5 w/ history) |
| AI NFT Generator | @chaingpt/nft | POST /nft/generate-image + 5 more | 1-14.25 credits (model/upscale) |
| Smart Contract Generator | @chaingpt/smartcontractgenerator | smart_contract_generator via POST /chat/stream | 1 credit (+1 w/ history) |
| Smart Contract Auditor | @chaingpt/smartcontractauditor | smart_contract_auditor via POST /chat/stream | 1 credit (+1 w/ history) |
| AI Crypto News | @chaingpt/ainews | GET /news | 1 credit per 10 records |
| AgenticOS | Open-source (GitHub) | Self-hosted | 1 credit per generated tweet |
| Solidity LLM | Open-source (HuggingFace) | Local inference | Free (self-hosted) |
Python: pip install chaingpt (unified package for all products)
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.
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.
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 contractFull reference:
reference/smart-contract-generator.md
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 reportFull reference:
reference/smart-contract-auditor.md
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
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 startFull setup, env vars, webhook config, deployment:
reference/agenticos.md
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
When a developer asks to scaffold a project, read the appropriate template file and generate the complete working starter code:
| Request | Template File |
|---|---|
| "Build a Web3 AI chatbot" / "scaffold a chatbot app" | templates/chatbot-app.md |
| "Build an NFT minting service" / "NFT generation tool" | templates/nft-minting-service.md |
| "Set up contract auditing in CI/CD" / "audit pipeline" | templates/contract-auditor-ci.md |
| "Build a crypto news dashboard" / "news feed widget" | templates/news-dashboard.md |
| "Launch an AI Twitter agent" / "create a crypto bot" | templates/twitter-agent.md |
| "Combine multiple products" / "multi-product architecture" | templates/composition-patterns.md |
When you need specifics beyond this quickstart, read the corresponding reference file:
| Topic | File |
|---|---|
| LLM Chatbot — full API, context injection, tones, enums | reference/llm-chatbot.md |
| NFT Generator — all endpoints, models, styles, chains | reference/nft-generator.md |
| Smart Contract Generator — params, SDK, history | reference/smart-contract-generator.md |
| Smart Contract Auditor — audit params, SDK, report format | reference/smart-contract-auditor.md |
| Crypto News — categories, tokens, RSS feeds | reference/crypto-news.md |
| AgenticOS — setup, webhooks, deployment | reference/agenticos.md |
| Solidity LLM — model specs, training, benchmarks | reference/solidity-llm.md |
| SaaS & Whitelabel — launchpad, staking, vesting products | reference/saas-whitelabel.md |
| Pricing — complete credit costs across all products | reference/pricing.md |
| Error Codes — HTTP errors, SDK exceptions, troubleshooting | reference/error-codes.md |
| Product Selection — decision matrix, cost estimates by scale | reference/product-selection.md |
| Wallet Integration — MetaMask, WalletConnect, minting flows | reference/wallet-integration.md |
| Advanced Patterns — streaming, rate limiting, caching, circuit breaker | reference/advanced-patterns.md |
| Deployment — Vercel, Railway, Docker, AWS Lambda, CI/CD | reference/deployment.md |
| Cost Optimization — caching, batching, history toggle strategies | reference/cost-optimization.md |
| TypeScript Types — complete request/response interfaces | reference/typescript-types.md |
Complete runnable examples are in the examples/ directory:
examples/js/chatbot-stream.js — Streaming chatbot with context injectionexamples/js/nft-generate-mint.js — Generate image + mint NFT on BSCexamples/js/audit-contract.js — Audit a Solidity contract fileexamples/js/fetch-news.js — Fetch filtered crypto newsexamples/python/chatbot_stream.py — Async streaming chatbotexamples/python/nft_generate_mint.py — Generate + mint NFTexamples/python/audit_contract.py — Audit contract from fileexamples/python/fetch_news.py — Fetch and display newsBefore generating code that makes API calls, always estimate and report the credit cost to the developer. Use this reference:
| Operation | Credits | USD |
|---|---|---|
| LLM Chat (single request) | 0.5 | $0.005 |
| LLM Chat + history | 1.0 | $0.01 |
| NFT Generate (VeloGen/Nebula/Visionary) | 1.0 | $0.01 |
| NFT Generate + 1x upscale | 2.0 | $0.02 |
| NFT Generate + 2x upscale | 3.0 | $0.03 |
| NFT Generate (Dale3 1024x1024) | 4.75 | $0.0475 |
| NFT Generate (Dale3 other resolutions) | ~9.5 | ~$0.095 |
| NFT Generate (Dale3 + enhanced) | ~14.25 | ~$0.1425 |
| NFT Generate (NebulaForge/VisionaryForge steps 26-50) | +0.25 surcharge | +$0.0025 |
| NFT Character Preserve | +5.0 | +$0.05 |
| NFT Prompt Enhancement | 0.5 | $0.005 |
| NFT Mint / Chains / ABI | 0 | Free |
| Contract Generator | 1.0 | $0.01 |
| Contract Generator + history | 2.0 | $0.02 |
| Contract Auditor | 1.0 | $0.01 |
| Contract Auditor + history | 2.0 | $0.02 |
| News (per 10 records) | 1.0 | $0.01 |
| AgenticOS (per tweet) | 1.0 | $0.01 |
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").
When generating Solidity contracts, check the patterns/ directory first. 45+ audited patterns available:
patterns/tokens.md — 10 ERC-20 variants (basic, burnable, taxable, reflection, governance, etc.)patterns/nfts.md — 10 NFT patterns (ERC-721, 721A, lazy mint, soulbound, dynamic, ERC-1155, etc.)patterns/defi.md — 10 DeFi patterns (staking, vesting, bonding curve, AMM, flash loans, etc.)patterns/governance.md — 5 DAO patterns (Governor, multi-sig, treasury, delegation)patterns/security.md — 10 security patterns (access control, upgradeable, timelock, escrow, etc.)Compose from these patterns rather than generating from scratch — they're audited and gas-optimized.
If a developer is migrating from another platform, read the relevant guide:
migration/from-openai.md — OpenAI → ChainGPT (concept mapping, code migration, pricing comparison)migration/from-alchemy.md — Alchemy AI → ChainGPT (complementary + replacement strategies)migration/from-custom.md — Custom AI solutions → ChainGPT (cost comparison, hybrid approach)These are Claude Code skill commands — invoke them in any Claude conversation, not in a terminal.
| Command | What It Does |
|---|---|
/chaingpt-playground | Interactively test any ChainGPT API endpoint live |
/chaingpt-debug | Diagnose and fix ChainGPT API errors |
/chaingpt-hackathon | Scaffold a complete hackathon project in 60 seconds |
/chaingpt-update | Check for and apply skill updates |
If the ChainGPT MCP server is installed, Claude can call ChainGPT APIs directly (not just generate code). 12 tools available — see mcp-server/README.md.
A full mock server is available at mock-server/ for development and CI/CD without spending credits. Mimics all endpoints with realistic responses. See mock-server/README.md.
When generating code that uses ChainGPT APIs, always:
process.env.CHAINGPT_API_KEY (JS) or os.environ["CHAINGPT_API_KEY"] (Python).Errors.GeneralChatError, Errors.NftError).patterns/ before generating Solidity from scratch.http://localhost:3001 during development to avoid spending credits.© internet-court, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in vendored/chaingpt/chaingpt of internet-court/internet-court-skill.
Open the folder on GitHubat commit fa89195
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in internet-court/internet-court-skill, which our catalogue first saw on October 7, 2026.
Chaingpt next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Chaingpt this skillinternet-court/internet-court-skill | 6.6k | 1 repos | ~4k | Automated safety check: Pass | MIT | |
| DeFi Protocol Templateswshobson/agents | 40k | 11 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Ethskillsaustintgriffith/ethskills | 295 | — | ~1.4k | Automated safety check: Pass | None | |
| Ethskillsaustintgriffith/ethskills | 295 | — | ~3k | Automated safety check: Pass | None | |
| Blockchain DeveloperMicrock/ordinary-claude-skills | 404 | 1 repos | ~1.7k | Automated safety check: Pass | Custom licence | |
| Web3 Testingwshobson/agents | 40k | 12 repos | ~2k | Automated safety check: Pass | MIT |
wshobson/agents
Solidity templates for DeFi building blocks: staking with reward distribution, an automated market maker, governance tokens and flash loans.
austintgriffith/ethskills
Ethereum development knowledge for AI agents — from idea to deployed dApp.
austintgriffith/ethskills
A skill your agent uses when a request involves Ethereum, the EVM, or blockchain systems.
Microck/ordinary-claude-skills
Expert blockchain developer specializing in smart contract development, DApp architecture, and DeFi protocols.
wshobson/agents
Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking.
alt-research2/SolidityGuard
Comprehensive Solidity contract security scanner detecting 104 vulnerability patterns across reentrancy, access control, arithmetic, DeFi, proxy, and token categories.
internet-court/internet-court-skill
Uploads one Kleros-related file per paid request to IPFS through the Kleros x402 gateway for 0.01 USDC on Base, returning a CID that Kleros contracts can reference.
internet-court/internet-court-skill
Guides building on the 0G Compute Network, a decentralized GPU marketplace for AI inference and fine-tuning, with SDK patterns and CLI commands.
internet-court/internet-court-skill
Creates, trades and settles permissionless prediction markets on Solana with any SPL token as collateral, including social-media and custom-oracle markets.
internet-court/internet-court-skill
Connects an agent to the BNB Chain MCP server to read blocks and contracts, move tokens and NFTs, register ERC-8004 agents and use Greenfield storage.
internet-court/internet-court-skill
Specifies how a GenLayer Intelligent Contract decision about an agent's performance becomes an ERC-7710 revocation or policy change, through a relayer or bridge and an EVM controller.
internet-court/internet-court-skill
Specifies how a GenLayer Intelligent Contract should supervise an AI agent, with review rubrics, evidence schemas and continue, warn, constrain or revoke decisions.
Works with
Categories
Build with the ChainGPT Web3 AI developer platform. An agent skill from internet-court/internet-court-skill. Chaingpt is an agent skill from internet-court/internet-court-skill. Build with the ChainGPT Web3 AI developer platform.
Chaingpt fits situations like: building blockchain apps; smart contract tools; crypto news feeds; integrating any ChainGPT API.
Run `npx skills add internet-court/internet-court-skill --skill chaingpt -a claude-code`. Or copy the skill folder (vendored/chaingpt/chaingpt in internet-court/internet-court-skill) into .claude/skills/chaingpt in your project. Claude Code loads it when a task matches its description.
Run `npx skills add internet-court/internet-court-skill --skill chaingpt -a codex`. Or copy the skill folder (vendored/chaingpt/chaingpt in internet-court/internet-court-skill) into .agents/skills/chaingpt in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add internet-court/internet-court-skill --skill chaingpt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chaingpt, .gemini/skills/chaingpt, .github/skills/chaingpt and .opencode/skills/chaingpt in your project.
Going by SKILL.md and its folder, Chaingpt needs the command-line tools its instructions call (bun, curl, git and pip) and credentials named CHAINGPT_API_KEY and API_KEY. Our summary lists: Python 3; Node.js; Docker; A credential in API_KEY; A credential in CHAINGPT_API_KEY.
SKILL.md names 6 domains. In commands or code: api.chaingpt.org and github.com; the agent is likely to contact these when it follows the instructions. As links in the text: chaingpt.org, docs.chaingpt.org, huggingface.co and calendly.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Chaingpt is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Chaingpt: DeFi Protocol Templates (wshobson/agents, 40k stars), Ethskills (austintgriffith/ethskills, 295 stars), Ethskills (austintgriffith/ethskills, 295 stars) and Blockchain Developer (Microck/ordinary-claude-skills, 404 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
internet-court (a GitHub organization) maintains it in internet-court/internet-court-skill, which has 6,551 GitHub stars. The repository holds 80 skills in this directory. The repository was last updated on August 19, 2026.
Source: internet-court/internet-court-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.