Metaplex logo

Metaplex

OrganizationPopular
internet-court
metaplex

Metaplex development on Solana — NFTs, tokens, compressed NFTs, candy machines, token launches, autonomous agents. Use when working with Token Metadata, Core, Bubblegum, Candy Machine, Genesis, Agent Registry, or the mplx CLI.

Overview

Publisherinternet-court
Repositoryinternet-court-skill
Skill namemetaplex
Stars
5.8K
Forks
106
Bundled files
21
LicenseApache-2.0
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.

  • 21 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by internet-court on GitHub. Read the source before you install it.

Installation

Install the Metaplex 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/internet-court/internet-court-skill.git /tmp/internet-court-skill
mkdir -p .claude/skills
cp -r /tmp/internet-court-skill/vendored/metaplex/metaplex .claude/skills/metaplex
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Metaplex 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 Metaplex 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 Metaplex 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.

Metaplex Development Skill

Overview

Metaplex provides the standard infrastructure for NFTs and tokens on Solana:

  • Agent Registry: On-chain agent identity, wallets, and execution delegation for MPL Core assets
  • Genesis: Token launch protocol with fair distribution + liquidity graduation
  • Core: Next-gen NFT standard (recommended for new NFT projects)
  • Token Metadata: Fungible tokens + legacy NFTs/pNFTs
  • Bubblegum: Compressed NFTs (cNFTs) using Merkle trees — massive scale at minimal cost
  • Candy Machine: NFT drops with configurable minting rules

Tool Selection

Prefer CLI over SDK for direct execution. Use SDK only when user specifically needs code.

ApproachWhen to Use
CLI (mplx)Default choice - direct execution, no code needed
Umi SDKUser needs code — default SDK choice. Covers all programs (TM, Core, Bubblegum, Genesis)
Kit SDKUser specifically uses @solana/kit, or asks for minimal dependencies. Token Metadata only — no Core/Bubblegum/Genesis support

Task Router

IMPORTANT: You MUST read the detail file for your task BEFORE executing any command or writing any code. The command syntax, required flags, setup steps, and batching rules are ONLY in the detail files. Do NOT guess commands from memory.

Task TypeRead This File
Any CLI operation (agent guidelines, batching, explorer links)./references/cli.md
CLI: Agent Registry (identity, delegation, revocation, token linking)./references/cli.md + ./references/cli-agent.md
CLI: Core NFTs/Collections./references/cli.md + ./references/cli-core.md + ./references/metadata-json.md
CLI: Token Metadata NFTs./references/cli.md + ./references/cli-token-metadata.md + ./references/metadata-json.md
CLI: Compressed NFTs (Bubblegum)./references/cli.md + ./references/cli-bubblegum.md + ./references/metadata-json.md
CLI: Candy Machine (NFT drops)./references/cli.md + ./references/cli-candy-machine.md + ./references/metadata-json.md
CLI: Token launch / bonding curve (Genesis)./references/cli.md + ./references/cli-genesis.md
CLI: Execute / asset-signer wallets / agent vault./references/cli.md + ./references/cli-core.md (execute section)
SDK: Execute / asset-signer PDA / agent vault./references/sdk-umi.md + ./references/sdk-core.md (execute section)
CLI: Fungible tokens./references/cli.md + ./references/cli-toolbox.md
SDK setup (Umi)./references/sdk-umi.md
SDK: Core NFTs./references/sdk-umi.md + ./references/sdk-core.md + ./references/metadata-json.md
SDK: Token Metadata./references/sdk-umi.md + ./references/sdk-token-metadata.md + ./references/metadata-json.md
SDK: Compressed NFTs (Bubblegum)./references/sdk-umi.md + ./references/sdk-bubblegum.md + ./references/metadata-json.md
SDK: Token Metadata with Kit./references/sdk-token-metadata-kit.md + ./references/metadata-json.md
SDK: Agent Registry (identity, wallets, delegation)./references/sdk-umi.md + ./references/sdk-agent.md
SDK: Token launch + bonding curve swaps (Genesis)./references/sdk-umi.md + ./references/sdk-genesis.md
SDK: Low-level Genesis (custom buckets, presale, vesting)./references/sdk-umi.md + ./references/sdk-genesis-low-level.md
Off-chain metadata JSON format/schema (NFT or token)./references/metadata-json.md
Account structures, PDAs, concepts./references/concepts.md
CLI errors, localnet issues./references/cli-troubleshooting.md

CLI Capabilities

The mplx CLI can handle most Metaplex operations directly. Read ./references/cli.md for agent guidelines (batching, JSON output, explorer links), then the program-specific file.

CLI v0.1.0 breaking changes (for agents/scripts migrating from older versions):

  • --json <file> (used to pass an offchain metadata file path) is now --offchain <file>. --json is now the standard OCLIF flag for machine-readable output.
  • All commands now return structured JSON when --json is passed — use this for programmatic/agent use.
TaskCLI Support
Register agent identity
Fetch agent data
Revoke execution delegation
Set agent token (Genesis link)✅ (requires asset-signer mode)
Create fungible token
Create Core NFT/Collection
Create TM NFT/pNFT
Transfer TM NFTs
Transfer fungible tokens
Transfer Core NFTs
Upload to Irys
Candy Machine drop✅ (setup/config/insert — minting requires SDK)
Compressed NFTs (cNFTs)✅ (batch limit ~100, use SDK for larger)
Execute (asset-signer wallets)
Check SOL balance / Airdrop
Query assets by owner/collection❌ SDK only (DAS API)
Token launch (Genesis)
Bonding curve swap (Genesis)

Program IDs

Agent Identity:  1DREGFgysWYxLnRnKQnwrxnJQeSMk2HmGaC6whw2B2p
Agent Tools:     TLREGni9ZEyGC3vnPZtqUh95xQ8oPqJSvNjvB7FGK8S
Genesis:         GNS1S5J5AspKXgpjz6SvKL66kPaKWAhaGRhCqPRxii2B
Core:            CoREENxT6tW1HoK8ypY1SxRMZTcVPm7R94rH4PZNhX7d
Token Metadata:  metaqbxxUerdq28cj1RbAWkYQm3ybzjb6a8bt518x1s
Bubblegum V1:    BGUMAp9SX3uS4efGcFjPjkAQZ4cUNZhtHaMq64nrGf9D
Bubblegum V2:    BGUMAp9Gq7iTEuizy4pqaxsTyUCBK68MDfK752saRPUY
Core Candy:      CMACYFENjoBMHzapRXyo1JZkVS6EtaDDzkjMrmQLvr4J

Quick Decision Guide

Autonomous Agents

Use Agent Registry to register on-chain identity and execution delegation for MPL Core assets. The Mint Agent API (mintAndSubmitAgent) is the recommended path — it creates the Core asset and registers identity in a single transaction. For existing assets, use registerIdentityV1 directly. Any Core asset already has a built-in wallet (Asset Signer PDA) via Core's Execute hook — the registry adds discoverable identity records and lets owners delegate an off-chain executive to operate the agent. Agents can optionally link a Genesis token via setAgentTokenV1. Read ./references/cli-agent.md (CLI) or ./references/sdk-umi.md + ./references/sdk-agent.md (SDK).

Token Launches (Token Generation Event / Fair Launch / Bonding Curve)

Use Genesis. The Launch API (genesis launch create / createAndRegisterLaunch) is recommended — it handles everything in one step. Two launch types:

  • launchpool (default): Configurable allocations, 48h deposit, team vesting support
  • bonding-curve: Instant bonding curve (constant product AMM) — no deposit window, trading starts immediately, auto-graduates to Raydium CPMM on sell-out. Supports creator fees, first buy, and agent mode.

Read ./references/cli.md + ./references/cli-genesis.md (CLI) or ./references/sdk-genesis.md (SDK launch flow). For custom buckets/presale/vesting, use ./references/sdk-genesis-low-level.md.

NFTs: Core vs Token Metadata

ChooseWhen
CoreNew NFT projects, lower cost (87% cheaper), plugins, royalty enforcement
Token MetadataExisting TM collections, need editions, pNFTs for legacy compatibility

Compressed NFTs (Massive Scale)

Use Bubblegum when minting thousands+ of NFTs at minimal cost. See ./references/cli-bubblegum.md (CLI) or ./references/sdk-bubblegum.md (SDK).

Fungible Tokens

Always use Token Metadata. Read ./references/cli-toolbox.md for CLI commands.

NFT Drops

Use Core Candy Machine. Read ./references/cli.md + ./references/cli-candy-machine.md.

App Mints into a Core Collection WITHOUT Candy Machine

Creating an asset into a Core collection requires the collection's update authority (or an UpdateDelegate) to sign — a user's wallet can't, and the authority key must never be in a frontend. The app needs either a custom on-chain program (PDA granted UpdateDelegate, mint logic in the program) or a backend/API holding a delegate keypair that signs mints. Read the "Minting into a Collection from an App" section in ./references/sdk-core.md before designing the minting flow.

Asset as Agent / Vault / Wallet (Execute)

Use Core Execute when an asset (NFT, agent, vault) needs to hold SOL/tokens, transfer funds, sign transactions, or own other assets. Every Core asset has a signer PDA that can act as an autonomous wallet. Read ./references/cli-core.md (CLI) or ./references/sdk-core.md (SDK), execute section.

For more info

When a task needs deeper detail than the skill references provide (edge cases, full API surfaces, guides), consult the Metaplex docs:

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 Metaplex AI skill do?

Metaplex development on Solana — NFTs, tokens, compressed NFTs, candy machines, token launches, autonomous agents. Use when working with Token Metadata, Core, Bubblegum, Candy Machine, Genesis, Agent Registry, or the mplx CLI.

Why use Metaplex on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/internet-court/internet-court-skill/tree/main/vendored/metaplex/metaplex. 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 Metaplex?

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 Metaplex?

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

Is the Metaplex AI skill free?

Yes. It is published on GitHub by internet-court under the Apache-2.0 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 👇