Dflow Phantom Connect

OrganizationPopular

internet-court

dflow-phantom-connect

Build Solana wallet-connected apps with Phantom Connect SDKs and DFlow spot trading. Use when user asks to connect a Phantom wallet, integrate Phantom in React, React Native, or vanilla JS, sign messages or transactions, build token-gated pages, mint NFTs, accept crypto payments, or swap/stream tokens with DFlow. Covers @phantom/react-sdk, @phantom/react-native-sdk, @phantom/browser-sdk, and DFlow spot trading and market-data streaming. Do NOT use for Ethereum or EVM wallet integrations, or non-DFlow DEX routing.

Overview

Publisher	internet-court
Repository	`internet-court-skill`
Skill name	`dflow-phantom-connect`
Stars	5.8K
Forks	106
Bundled files	9
License	MIT
Links	Skill source Repository

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.
9 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 Dflow Phantom Connect AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/internet-court/internet-court-skill/tree/main/vendored/dflow/dflow-phantom-connect

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/dflow/dflow-phantom-connect .claude/skills/dflow-phantom-connect

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dflow Phantom Connect 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 Dflow Phantom Connect 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 Dflow Phantom Connect 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.

Phantom Connect + DFlow Skill

Instructions

Step 1: Identify What the User Wants to Build

Determine the domain, then route to the right references.

Wallet connection and Solana interactions:

Connecting a Phantom wallet (React, React Native, vanilla JS)
Signing messages or transactions
Token-gated access
NFT minting
Crypto payments
Solana transfers (SOL or SPL tokens)

DFlow trading & market data:

Spot token swaps (quote, sign, submit, confirm)
Live prices, order-book depth, or priority-fee streaming

Many tasks combine both (for example, a swap UI needs wallet connection AND DFlow trading). Read all relevant references before writing code.

Step 2: Read the Relevant References

Phantom Connect SDKs (wallet connection, signing, auth):

references/react-sdk.md: React hooks, components, theming, PhantomProvider
references/react-native-sdk.md: Expo config, polyfills, deep links, mobile auth
references/browser-sdk.md: BrowserSDK init, events, wallet discovery, vanilla JS

Solana patterns (transactions, gating, minting, payments):

references/transactions.md: SOL/SPL transfers, signing, fee estimation
references/token-gating.md: client-side and server-side token-gated access
references/nft-minting.md: mint pages, Metaplex Core, compressed NFTs
references/payments.md: SOL/USDC payments, checkout with backend verification

DFlow (swaps, streaming):

references/dflow-crypto-trading.md: spot swaps via /order (atomic units, base58 mints, quote-without-wallet, priority/platform/sponsor fees)
references/dflow-websockets.md: real-time quote, order-book, and priority-fee streaming (browser proxies through the backend)

Step 3: Ask the Right Questions

Before implementing, ask questions based on the domain:

For Phantom Connect tasks:

Which platform? (React, React Native, vanilla JS)
Do they need social login (Google/Apple) or extension only?

For DFlow tasks:

Do you have a DFlow API key? (Yes: prod host with x-api-key. No: dev host, rate-limited. Prod key: pond.dflow.net/get-started/api-key.) It's one key for everything DFlow.
Client environment? (web, mobile, backend, CLI) Browser apps keep the key on the backend and proxy DFlow HTTP and WebSocket through it.
Platform fees? If yes, what bps and which builder-owned fee account (which must already exist)?

Step 4: Implement

Follow the patterns in the reference files. Key rules by domain:

Phantom Connect:

All SDK details (provider setup, hooks, components, auth providers) are in the SDK reference files. Read them before writing Phantom integration code.

DFlow:

Trades are synchronous: one /order call returns a signed-ready transaction that you sign, submit, and confirm.
As a security best practice, keep the DFlow API key on the backend, not in browser code. Browser apps proxy DFlow HTTP (/order serves no CORS) and the WebSocket streams through their backend.
Dev endpoints (dev-quote-api.dflow.net) work without a key but are rate-limited; production requires a key from pond.dflow.net/get-started/api-key. In production, quote and book stream access is granted per key.

Step 5: Handle Errors

Each reference file contains domain-specific error handling. Key cross-cutting concerns:

User rejects a transaction or signature request
Wallet not connected when a signed action is attempted
DFlow API returns 429 (rate limited): retry with backoff or get a production API key
route_not_found from DFlow: a likely cause is insufficient liquidity for the pair at that size; also check the mint addresses and that amount is in atomic units

Examples

Example 1: React wallet connection

User says: "Add Phantom wallet login to my Next.js app"

Actions:

Read references/react-sdk.md
Install @phantom/react-sdk
Wrap app in PhantomProvider with desired auth providers and appId
Use useModal hook for a connect button
Use useAccounts to display the connected wallet address

Result: Working wallet connection with social login and extension support

Example 2: Token-gated page

User says: "Build a page that only BONK holders can see"

Actions:

Read references/react-sdk.md and references/token-gating.md
Set up wallet connection
Query the BONK token balance for the connected wallet
Conditionally render content based on balance threshold
For production: add server-side signature verification

Result: Page that checks wallet token balance and gates content

Example 3: DFlow token swap

User says: "Add a swap feature using DFlow"

Actions:

Ask: API key? Client environment? Platform fees?
Read references/dflow-crypto-trading.md
Use the /order flow: request the order (proxy through the backend in a browser), deserialize the returned transaction, sign, submit, and confirm
In a browser, sign and send with the Phantom SDK (see references/transactions.md); server-side, sign with a keypair and submit through your RPC

Result: Working swap with DFlow routing

Example 4: Full swap page with wallet connection

User says: "Build a full swap page with wallet connect and DFlow"

Actions:

Ask: which platform? API key? Platform fees?
Read the relevant SDK reference AND references/dflow-crypto-trading.md
Set up wallet connection with the Phantom SDK
Build the swap form; proxy /order through the backend so the key stays server-side
Sign and send with the Phantom SDK, then confirm

Result: End-to-end swap page combining Phantom wallet and DFlow trading

Example 5: Live order book

User says: "Show a live order book for a token pair"

Actions:

Read references/dflow-websockets.md
Stand up a backend relay that holds the key, opens /book-stream with the x-api-key header, and relays frames to the browser
Subscribe with { op: "subscribe", base_mint, quote_mint }; render the batched per-slot updates[]
Reconnect and re-subscribe on drop

Result: Live streaming order book, key kept server-side

Resources

Phantom Portal: phantom.com/portal/login
Phantom Docs: docs.phantom.com/introduction
SDK Examples: github.com/phantom/phantom-connect-sdk/tree/main/examples
Phantom MCP Server: docs.phantom.com/resources/mcp-server
DFlow MCP Server: pond.dflow.net/mcp
DFlow MCP Docs: pond.dflow.net/ai/mcp
DFlow Docs: pond.dflow.net/introduction

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 Dflow Phantom Connect AI skill do?

Why use Dflow Phantom Connect on TypingMind?

Because you install it once and use it with any model. Dflow Phantom Connect 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 Dflow Phantom Connect in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/internet-court/internet-court-skill/tree/main/vendored/dflow/dflow-phantom-connect. 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 Dflow Phantom Connect?

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 Dflow Phantom Connect?

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

Is the Dflow Phantom Connect AI skill free?

Yes. It is published on GitHub by internet-court 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

Constraint Driven Development

addyosmani

CommunityPopular

Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no…

Spec Driven Development

addyosmani

CommunityPopular

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and…

Pod Sales

Run one tick of the sales business-pod (ADR-164 §4.1, Phase 2). Loads templates/sales.json, validates it against the pod-schema, resolves agents against ruflo's agent registry, reserves budget via the…

Cost Anomaly

MAD-based outlier detection on session spend. Robust to the very outliers it hunts (unlike mean+sigma). Surfaces specific anomalous sessions with modified-z scores; optional --alert-on-outliers exit…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Phantom Connect + DFlow Skill

Instructions

Step 1: Identify What the User Wants to Build

Step 2: Read the Relevant References

Step 3: Ask the Right Questions

Step 4: Implement

Step 5: Handle Errors

Examples

Example 1: React wallet connection

Example 2: Token-gated page

Example 3: DFlow token swap

Example 4: Full swap page with wallet connection

Example 5: Live order book

Resources

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now