Finance Reconciliation logo

Finance Reconciliation

Organization
frumu-ai
finance-reconciliation

Reconcile GL balances to subledger, bank, or third-party balances

Overview

Publisherfrumu-ai
Repositorytandem
Skill namefinance-reconciliation
Stars
121
Forks
13
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by frumu-ai on GitHub. Read the source before you install it.

Installation

Install the Finance Reconciliation 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/frumu-ai/tandem.git /tmp/tandem
mkdir -p .claude/skills
cp -r /tmp/tandem/apps/tandem-desktop/src-tauri/resources/skill-templates/finance-reconciliation .claude/skills/finance-reconciliation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Finance Reconciliation 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 Finance Reconciliation 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 Finance Reconciliation 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.

Account Reconciliation

If you see unfamiliar placeholders or need to check which tools are connected, please ask about available integrations.

Important: This skill assists with reconciliation workflows but does not provide financial advice. All reconciliations should be reviewed by qualified financial professionals before sign-off.

Reconcile GL account balances to subledger, bank, or third-party balances. Identify and categorize reconciling items and generate a reconciliation workpaper.

Usage

You can ask to reconcile an account (e.g., "Reconcile the bank account" or "Prepare the AP recon").

Arguments

  • account — The account or account category to reconcile. Examples:
    • cash or bank — Bank reconciliation (GL cash to bank statement)
    • accounts-receivable or ar — AR subledger reconciliation
    • accounts-payable or ap — AP subledger reconciliation
    • fixed-assets or fa — Fixed asset subledger reconciliation
    • intercompany or ic — Intercompany balance reconciliation
    • prepaid — Prepaid expense schedule reconciliation
    • accrued-liabilities — Accrued liabilities detail reconciliation
    • Any specific GL account code (e.g., 1010, 2100)
  • period — The accounting period end date (e.g., 2024-12, 2024-12-31)

Workflow

1. Gather Both Sides of the Reconciliation

If an ERP or data warehouse is connected:

  • Pull the GL balance for the specified account(s) as of period end
  • Pull the subledger, bank statement, or third-party balance for comparison
  • Pull prior period reconciliation (if available) for outstanding item carryforward

If no data source is connected:

Connect an ERP or data warehouse to pull account balances automatically. To reconcile manually, provide:

  1. GL side: The general ledger balance for the account as of period end
  2. Other side: The subledger balance, bank statement balance, or third-party confirmation balance
  3. Prior period outstanding items (optional): Any reconciling items from the prior period reconciliation

2. Compare Balances

Calculate the difference between the two sides:

GL Balance:                    $XX,XXX.XX
Subledger/Bank/Other Balance:  $XX,XXX.XX
                               ----------
Difference:                    $XX,XXX.XX

3. Identify Reconciling Items

Analyze the difference and categorize reconciling items:

Timing Differences (items that will clear in subsequent periods):

  • Outstanding checks / payments issued but not yet cleared
  • Deposits in transit / receipts recorded but not yet credited
  • Invoices posted in one system but pending in the other
  • Accruals awaiting reversal

Permanent Differences (items requiring adjustment):

  • Errors in recording (wrong amount, wrong account, duplicate entries)
  • Missing entries (transactions in one system but not the other)
  • Bank fees or charges not yet recorded
  • Foreign currency translation differences

Prior Period Items (carryforward from prior reconciliation):

  • Items from prior period that have now cleared (remove from reconciliation)
  • Items from prior period still outstanding (carry forward with aging)

4. Generate Reconciliation Workpaper

ACCOUNT RECONCILIATION
Account: [Account code] — [Account name]
Period End: [Date]
Prepared by: [User]
Date Prepared: [Today]

RECONCILIATION SUMMARY
=======================

Balance per General Ledger:              $XX,XXX.XX

Add: Reconciling items increasing GL
  [Item description]                     $X,XXX.XX
  [Item description]                     $X,XXX.XX
                                         ---------
  Subtotal additions:                    $X,XXX.XX

Less: Reconciling items decreasing GL
  [Item description]                    ($X,XXX.XX)
  [Item description]                    ($X,XXX.XX)
                                         ---------
  Subtotal deductions:                  ($X,XXX.XX)

Adjusted GL Balance:                     $XX,XXX.XX

Balance per [Subledger/Bank/Other]:      $XX,XXX.XX

Add: Reconciling items
  [Item description]                     $X,XXX.XX

Less: Reconciling items
  [Item description]                    ($X,XXX.XX)

Adjusted [Other] Balance:                $XX,XXX.XX

DIFFERENCE:                              $0.00

5. Reconciling Items Detail

Present each reconciling item with:

#DescriptionAmountCategoryAge (Days)StatusAction Required
1[Detail]$X,XXXTiming5Expected to clearMonitor
2[Detail]$X,XXXErrorN/ARequires correctionPost adjusting JE

6. Review and Escalation

Flag items that require attention:

  • Aged items: Reconciling items outstanding more than 30/60/90 days
  • Large items: Individual items exceeding materiality thresholds
  • Growing balances: Reconciling item totals increasing period over period
  • Unresolved prior period items: Items carried forward without resolution
  • Unexplained differences: Amounts that cannot be tied to specific transactions

7. Output

Provide:

  1. The formatted reconciliation workpaper
  2. List of reconciling items with categorization and aging
  3. Required adjusting entries (if any permanent differences identified)
  4. Action items for items requiring follow-up
  5. Comparison to prior period reconciliation (if available)
  6. Sign-off section for preparer and reviewer

Frequently asked questions

What does the Finance Reconciliation AI skill do?

Reconcile GL balances to subledger, bank, or third-party balances

Why use Finance Reconciliation on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/frumu-ai/tandem/tree/main/apps/tandem-desktop/src-tauri/resources/skill-templates/finance-reconciliation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Finance Reconciliation?

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 Finance Reconciliation?

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

Is the Finance Reconciliation AI skill free?

It is published on GitHub by frumu-ai. 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 👇