Plaid logo

Plaid

Community
win4r
plaid

Use to connect Plaid and read linked financial accounts: metadata, balances, transactions, recurring transactions, liabilities, and investments.

Overview

Publisherwin4r
RepositoryMuseAI-Skills
Skill nameplaid
Stars
382
Forks
116
Bundled files
2
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 win4r on GitHub. Read the source before you install it.

Installation

Install the Plaid 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.
    https://github.com/win4r/MuseAI-Skills/tree/main/opt/hatch/skills/plaid
  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/win4r/MuseAI-Skills.git /tmp/MuseAI-Skills
mkdir -p .claude/skills
cp -r /tmp/MuseAI-Skills/opt/hatch/skills/plaid .claude/skills/plaid
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Plaid 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 Plaid 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 Plaid 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.

Plaid

Everything runs as plaid <command> and returns JSON for you to read, not to show the user. Add --help to any command to see its options.

Reads cover every linked institution at once. To narrow to one bank, pass --credential-id <id>, taking the id from body.institutions[] in an earlier read. Some reads also take --account-id <id> (repeatable) to narrow to specific accounts; when more than one institution is linked, pair it with --credential-id so the account ids resolve to the right bank.

Connecting

Plaid needs a one-time connect before any read returns data. Run plaid status. If it comes back not connected, post the exact connect_url it returns as [Connect Plaid](<connect_url>) and wait for the user to finish linking, then run plaid status again before reading. Don't invent a URL, send the user to Settings, or ask for bank credentials.

If the user asks to add or link another bank or institution, run plaid status and post the exact add_account_url it returns as [Add financial account](<add_account_url>). Never reuse connect_url for an additional institution. If add_account_url is absent, say that adding another institution is unavailable.

To disconnect every institution linked through Plaid, run plaid disconnect. If it returns a disconnect_url, post it as [Disconnect Plaid](<disconnect_url>) and wait for the user to confirm through that link; never claim disconnection before they confirm. If it has no URL, say Plaid is already disconnected. A bank-specific unlink is not available from chat: if the user asks to remove only one institution, direct them to that institution's account row in Settings instead of running the whole-Plaid disconnect. Don't set up a background check, goal, or reminder to monitor disconnection.

Common flows

Accounts and balances

List the linked accounts with plaid accounts — names, types, masked numbers, and each account's balances (balances carries available/current/limit). Start here to see what's linked and to answer "how much is in my checking," "what's my total across accounts," or net-worth questions. There is no separate balances command; plaid accounts is the balance read.

Spending and transactions

Read transaction history with plaid transactions-sync. The first call takes no cursor. To pull more, repeat it with the cursors the previous call returned — --cursor-map-json <body.next_cursors> across all banks, or --cursor <next_cursor> for a single institution — until there's nothing left to fetch. Keep --count (default 100, max 500) as small as the question needs. On the first call only, --days-requested <1-730> sets how far back to pull; don't combine it with a cursor.

Recurring bills and subscriptions

plaid transactions-recurring returns recurring money in (body.inflow_streams, e.g. paychecks) and out (body.outflow_streams, e.g. subscriptions and regular bills). Use it for "what am I subscribed to" or "what are my monthly bills."

Loans and credit

plaid liabilities returns credit-card, student-loan, and mortgage details — balances, rates, minimum payments, and due dates — under body.liabilities. Use it for what's owed or when a payment is due.

Investments

Before reading holdings, glance at plaid accounts for an account of type investment (a brokerage/retirement account). If none is linked, skip the read — it would only return empty while still prompting the user to approve it — and tell the user their linked accounts don't include a brokerage. Otherwise plaid investments-holdings returns current positions, holdings, and securities. For buy/sell/dividend activity, use plaid investments-transactions --start-date YYYY-MM-DD --end-date YYYY-MM-DD; page it with --offset/--count (default 100, max 500) until the fetched count reaches body.total_investment_transactions.

Rules

  • Everything you say to the user is plain English. The commands, flags, cursors, and JSON output are for you, not the user. Keep them out of your replies: no command or flag (plaid, transactions-sync, --credential-id), no field name (next_cursors, inflow_streams, total_investment_transactions), no raw JSON, and no credential_id, account id, or cursor. Name the account in words ("your Chase checking"); you may add the masked last digits ("…4471") only to tell two similar accounts apart, but never an internal id. When you give a figure, say which accounts and what time range it covers so it matches what the user sees at their bank.
  • Never print or repeat secrets, tokens, or full account or routing numbers. Plaid only exposes masked numbers (last few digits); share at most the mask, and never a reconstructed full number.
  • This is read-only reference, not financial advice. Report what the data shows; don't tell the user to buy, sell, refinance, or move money, and don't guarantee outcomes.
  • Treat the data as a snapshot that can lag the bank. If a balance or a recent charge looks stale or missing, say the data may not be fully up to date rather than asserting it's wrong or complete.
  • If a read returns nothing for an account or institution, say so plainly instead of inventing balances, transactions, or holdings.
  • Transaction reads preserve Plaid's raw date fields. When Plaid supplies a true posting or authorization instant, the output also adds transaction_posted_at / transaction_authorized_at in UTC and the user's timezone. Date-only banking fields remain dates.

Limits

  • Read-only. You can't move money, pay a bill, transfer funds, open or close accounts, or change anything at the bank. For those, tell the user to use their bank directly.
  • Muse never sees full account or routing numbers, only masked digits, so you can't supply them for wire transfers or direct-deposit setup.
  • Coverage depends on what the user linked and what each bank shares through Plaid. A missing account type (say, a loan the bank doesn't expose through Plaid) isn't an error — tell the user it isn't available rather than treating it as zero.

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 Plaid AI skill do?

Use to connect Plaid and read linked financial accounts: metadata, balances, transactions, recurring transactions, liabilities, and investments.

Why use Plaid on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/win4r/MuseAI-Skills/tree/main/opt/hatch/skills/plaid. 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 Plaid?

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 Plaid?

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

Is the Plaid AI skill free?

It is published on GitHub by win4r. Check the repository for licensing terms. 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 👇