Account Reconciliation logo

Account Reconciliation

Organization
vm0-ai
account-reconciliation

Reconcile accounts, ledgers, bank statements, subledgers, variances, and supporting schedules.

Overview

Publishervm0-ai
Repositoryvm0-skills
Skill nameaccount-reconciliation
Stars
76
Forks
18
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 vm0-ai on GitHub. Read the source before you install it.

Installation

Install the Account 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/vm0-ai/vm0-skills.git /tmp/vm0-skills
mkdir -p .claude/skills
cp -r /tmp/vm0-skills/account-reconciliation .claude/skills/account-reconciliation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Account 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 Account 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 Account 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.

Reconciliation Categories

General Ledger vs. Subledger

Verify that each control account in the GL agrees with the sum of its underlying detail ledger.

Accounts typically reconciled this way:

  • Trade receivables (GL control vs. AR aging schedule)
  • Trade payables (GL control vs. AP aging schedule)
  • Property, plant & equipment (GL control vs. asset register)
  • Inventory (GL control vs. stock valuation report)
  • Prepaid assets (GL control vs. amortization schedule)
  • Accrued liabilities (GL control vs. accrual supporting schedules)

Workflow:

  1. Extract the GL control account balance at the period cut-off
  2. Generate the subledger detail or trial balance as of the identical date
  3. Match the two totals — under real-time posting they should be identical
  4. Research any gap (manual GL postings, pending interface batches, failed data transfers, reclassifications without subledger mirror)

Typical root causes of discrepancy:

  • Journal entries booked directly to the control account without a subledger transaction
  • Subledger batches queued but not yet transmitted to the GL
  • Lag between batch processing windows
  • GL reclassifications with no subledger counterpart
  • Integration failures or rejected interface records

Cash / Bank Reconciliation

Align the book cash balance with the financial institution's reported position.

Workflow:

  1. Obtain the institution's closing statement balance
  2. Pull the corresponding GL cash account balance at the same date
  3. List checks written but not yet presented for payment
  4. List deposits recorded in the books but not yet credited by the bank
  5. Identify bank-initiated entries (fees, interest, returned items) absent from the GL
  6. Derive an adjusted balance on each side; the two must agree

Presentation template:

Institution statement balance:          $XX,XXX
  Plus: Deposits not yet credited        $X,XXX
  Less: Unpresented checks             ($X,XXX)
  Plus/Less: Institution errors          $X,XXX
Adjusted institution balance:           $XX,XXX

Book (GL) balance:                      $XX,XXX
  Plus: Interest & credits unrecorded    $X,XXX
  Less: Fees & charges unrecorded      ($X,XXX)
  Plus/Less: Book errors                 $X,XXX
Adjusted book balance:                  $XX,XXX

Remaining variance:                     $0.00

Intercompany Reconciliation

Confirm that receivables and payables between affiliated entities offset to zero for consolidation purposes.

Workflow:

  1. Collect intercompany receivable and payable balances for every entity pair
  2. Match Entity A's claim on Entity B against Entity B's corresponding obligation to Entity A
  3. Investigate and resolve discrepancies
  4. Verify that both sides have captured every intra-group transaction
  5. Validate that consolidation elimination entries will net these balances cleanly

Typical root causes of discrepancy:

  • One entity recorded the transaction while the other has not yet done so
  • Entities applied different foreign exchange rates on the same transaction
  • Amounts classified as intercompany by one party but as third-party by the other
  • Contested charges or unapplied cash receipts
  • Differing period-end cut-off conventions across subsidiaries

Classifying Open Reconciling Items

Class 1 — Timing Lags

Items arising from normal processing sequences that will self-clear without intervention:

  • Checks issued and booked but awaiting bank presentment
  • Deposits journalized but pending bank value-date credit
  • Transactions posted in one system awaiting batch interface to the other
  • Items sitting in an approval queue prior to final posting

Expected outcome: Resolution within the standard processing window (generally 1-5 business days). No corrective entry required.

Class 2 — Corrective Action Needed

Items that demand a journal entry or other ledger adjustment:

  • Bank-originated charges not yet reflected on the books (service fees, wire costs, NSF penalties)
  • Interest income or expense recognized by the institution but absent from the GL
  • Posting mistakes — wrong dollar amount, wrong account, or duplicate recording
  • Transactions present in one system with no counterpart in the other
  • Properly recorded amounts sitting in an incorrect GL account

Expected outcome: Prepare and post a correcting entry during the current or next available period.

Class 3 — Investigation Required

Items lacking a clear explanation:

  • Variances with no identifiable source
  • Amounts in dispute between internal parties or with external counterparties
  • Stale items that have exceeded their expected clearance window
  • Persistent differences of the same type reappearing period after period

Expected outcome: Perform root-cause analysis, document findings, and escalate when resolution is not straightforward.

Aging and Monitoring of Open Items

Track every unresolved reconciling item by age to surface those requiring management attention:

Age BandClassificationRequired Response
0-30 daysCurrentRoutine monitoring — within normal processing window
31-60 daysMaturingActive follow-up — determine why the item has not cleared
61-90 daysPast dueSupervisor notification with documented investigation
Over 90 daysStaleManagement escalation — evaluate write-off or forced adjustment

Item-Level Tracking Register

SeqDescriptionAmountOrigination DateDays OpenClassResolution StatusAssigned To
1[Detail]$X,XXX[Date]XX[Type][Status][Name]

Trend Monitoring

Evaluate the reconciling-item population across periods to detect deterioration:

  • Compare the aggregate dollar value of open items to the prior period
  • Flag when total open items exceed the account's materiality benchmark
  • Flag when the count of open items grows for two or more consecutive periods
  • Investigate chronic items that appear in every reconciliation (signal of a systemic process gap)

Escalation Governance

Establish triggers proportional to organizational risk appetite:

ConditionIllustrative ThresholdEscalation Path
Single-item dollar valueAbove $10,000Supervisor review
Single-item dollar valueAbove $50,000Controller review
Aggregate open itemsAbove $100,000Controller review
Item ageOver 60 daysSupervisor follow-up
Item ageOver 90 daysController / senior management review
Unresolved net differenceAny amountPeriod cannot close — must resolve or formally document
Worsening trendThree or more consecutive periodsInitiate process-improvement project

Calibrate thresholds to match the entity's materiality level and control environment.

Operating Principles

  1. Cadence discipline: Finish every reconciliation within the close calendar window (commonly T+3 to T+5 after period end)
  2. Coverage: Reconcile every balance sheet account on a defined cycle — monthly for material balances, quarterly for immaterial ones
  3. Audit trail: Each reconciliation must identify the preparer, reviewer, completion date, and a narrative for every open item
  4. Separation of duties: The reconciler should not be the person who initiates or approves transactions in the same account
  5. Closure rigor: Carry open items forward only with active follow-up; never allow perpetual rollover without investigation
  6. Systemic fixes: When the same reconciling item type recurs, address the upstream process rather than repeatedly clearing symptoms
  7. Uniform format: Employ standardized templates and naming conventions across all accounts and business units
  8. Record keeping: Retain completed reconciliations and all supporting evidence in accordance with the organization's document-retention policy

Frequently asked questions

What does the Account Reconciliation AI skill do?

Reconcile accounts, ledgers, bank statements, subledgers, variances, and supporting schedules.

Why use Account Reconciliation on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vm0-ai/vm0-skills/tree/main/account-reconciliation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Account 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 Account Reconciliation?

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

Is the Account Reconciliation AI skill free?

It is published on GitHub by vm0-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 👇