Wallet Analysis logo

Wallet Analysis

Organization
sendaifun
wallet-analysis

Analyze Solana wallets and multichain portfolios with Zerion API. Use for Solana portfolio value, token positions, transaction history, wallet charts, and PnL. Prefer direct REST API integration, with hosted MCP and x402 on Solana as no-key alternatives for agent workflows.

Overview

Publishersendaifun
Repositoryskills
Skill namewallet-analysis
Stars
128
Forks
81
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Wallet Analysis 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/sendaifun/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/wallet-analysis .claude/skills/wallet-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wallet Analysis 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 Wallet Analysis 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 Wallet Analysis 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.

Wallet Analysis with Zerion API

Build Solana-first wallet analysis features with Zerion's normalized wallet API. Use this skill when the user wants portfolio views, token balances, interpreted transactions, charts, or wallet-level PnL for Solana addresses, while still supporting the same flows across Zerion's broader multichain surface.

Overview

Zerion is especially useful when you need:

  • Solana wallet portfolio summaries without building your own indexer
  • Solana token holdings and wallet activity in a normalized schema
  • Wallet PnL and historical chart views for portfolio apps and agents
  • API-first implementation guidance, with MCP available for agent-native environments

Authentication

Prefer these auth modes in this order:

1. API key for app integrations

Use Zerion API directly when the user is building a product integration.

bash
export ZERION_API_KEY="zk_dev_..."

curl -u "$ZERION_API_KEY:" \
  "https://api.zerion.io/v1/wallets/8BH9pjtgyZDC4iAQH5ZiYDZ1MDWC98xki2V8NzqqKW3K/portfolio"

For explicit headers, use HTTP Basic auth with base64("${ZERION_API_KEY}:").

2. x402 for no-key agent workflows, including Solana

If the user does not want to provision an API key, Zerion documents x402 as a pay-per-request path for AI workflows. Zerion's official agent repo also documents Solana-backed x402, so a Solana wallet can be used instead of an API key when the runtime supports x402 payment handshakes.

bash
export SOLANA_PRIVATE_KEY="5C1y..."
export ZERION_X402_PREFER_SOLANA=true

Use x402 when:

  • the user explicitly wants no API key
  • the environment already supports x402
  • the workflow is agentic and Solana-funded

3. Hosted MCP for agent-native environments

If the user is in Claude Code, Cursor, or another MCP-native client, Zerion API provides a hosted MCP endpoint:

text
https://developers.zerion.io/mcp

Treat MCP as an alternate interface, not a different product. The same wallet-analysis surface is available there, and Zerion's official AI docs/repo describe API key and x402 auth paths for AI workflows. Prefer direct REST API examples when the user is asking for app code.

Routing

Start with Solana unless the user asks for another chain. Zerion's wallet-analysis endpoints support Solana addresses and the same normalized object model used across the rest of the API.

User intentEndpoint / Tool
Solana wallet overviewGET /v1/wallets/{address}/portfolio or MCP wallet-portfolio
Solana token balancesGET /v1/wallets/{address}/positions/ or MCP wallet-positions
Solana recent activityGET /v1/wallets/{address}/transactions/ or MCP wallet-transactions
Solana wallet PnLGET /v1/wallets/{address}/pnl or MCP wallet-pnl
Solana portfolio chartGET /v1/wallets/{address}/charts/{period}
Supported chainsGET /v1/chains/ or MCP chains-list

Solana-First Workflow

  1. Confirm the wallet address is Solana if the user is building for Solana.
  2. Fetch portfolio first to get total value and high-level composition.
  3. Fetch positions next for token-level breakdown.
  4. Fetch transactions for interpreted wallet activity.
  5. Fetch pnl when the user needs performance, realized gains, or net invested amounts.
  6. Add charts when the user needs historical portfolio value in the UI.
  7. Only expand to EVM or multichain filters if the user's request actually needs them.

API Patterns

Portfolio

bash
curl -u "$ZERION_API_KEY:" \
  "https://api.zerion.io/v1/wallets/${ADDRESS}/portfolio?currency=usd"

Use this first for Solana wallet dashboards, watchlists, and summary cards.

Positions

bash
curl -u "$ZERION_API_KEY:" \
  "https://api.zerion.io/v1/wallets/${ADDRESS}/positions/?filter[positions]=no_filter"

Use filter[positions]=only_simple when the user only wants token balances.

Transactions

bash
curl -u "$ZERION_API_KEY:" \
  "https://api.zerion.io/v1/wallets/${ADDRESS}/transactions/?page[size]=10&currency=usd"

Use this for interpreted Solana activity such as swaps, transfers, and approvals.

PnL

bash
curl -u "$ZERION_API_KEY:" \
  "https://api.zerion.io/v1/wallets/${ADDRESS}/pnl?currency=usd"

Use this when the user asks for realized gain, unrealized gain, net invested, or cost basis.

Charts

bash
curl -u "$ZERION_API_KEY:" \
  "https://api.zerion.io/v1/wallets/${ADDRESS}/charts/month?currency=usd"

Use this for portfolio trend charts and timeline visualizations.

Guidelines

  • Prefer Zerion API for implementation examples in app code.
  • Use Solana wallet examples in prompts, code, and explanations whenever possible.
  • Use Zerion MCP when the user wants agent-native querying in Claude Code, Cursor, or VS Code.
  • Make x402 a first-class fallback, especially when the user wants a Solana-funded no-key setup.
  • Keep Basic auth examples accurate: API key as username, empty password.
  • Do not tell the user to build chain-specific parsers when Zerion already normalizes Solana wallet data.
  • Do not invent x402 headers or payment flows; use Zerion's documented path when the runtime supports x402.

Common Errors

401 Unauthorized

Cause: Missing or invalid API key in Basic auth. Fix: Use curl -u "$ZERION_API_KEY:" ... or encode ZERION_API_KEY: into the Authorization: Basic ... header.

402 Payment Required

Cause: x402 path selected but the runtime has not completed the payment handshake. Fix: Use a client/runtime that supports x402 and fund the Solana wallet with the required balance.

Empty Solana positions on first request

Cause: Zerion docs note some Solana assets can need a short bootstrap period. Fix: Retry with bounded polling instead of assuming the wallet is empty.

Missing protocol positions on Solana

Cause: Zerion's current docs still list protocol-position support on Solana as a temporary limitation for the wallet positions surface. Fix: Be explicit that token balances are available, but DeFi protocol position coverage may be incomplete for Solana right now.

References

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 Wallet Analysis AI skill do?

Analyze Solana wallets and multichain portfolios with Zerion API. Use for Solana portfolio value, token positions, transaction history, wallet charts, and PnL. Prefer direct REST API integration, with hosted MCP and x402 on Solana as no-key alternatives for agent workflows.

Why use Wallet Analysis on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sendaifun/skills/tree/main/skills/wallet-analysis. 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 Wallet Analysis?

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 Wallet Analysis?

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

Is the Wallet Analysis AI skill free?

Yes. It is published on GitHub by sendaifun 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 👇