Reconciliation logo

Reconciliation

OrganizationPopular
anthropics
reconciliation

Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.

Overview

Publisheranthropics
Repositoryknowledge-work-plugins
Skill namereconciliation
Stars
24.9K
Forks
3K
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

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

Installation

Install the 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/anthropics/knowledge-work-plugins.git /tmp/knowledge-work-plugins
mkdir -p .claude/skills
cp -r /tmp/knowledge-work-plugins/finance/skills/reconciliation .claude/skills/reconciliation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 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 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 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

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.

Methodology and best practices for account reconciliation, including GL-to-subledger, bank reconciliations, and intercompany. Covers reconciling item categorization, aging analysis, and escalation.

Reconciliation Types

GL to Subledger Reconciliation

Compare the general ledger control account balance to the detailed subledger balance.

Common accounts:

  • Accounts receivable (GL control vs AR subledger aging)
  • Accounts payable (GL control vs AP subledger aging)
  • Fixed assets (GL control vs fixed asset register)
  • Inventory (GL control vs inventory valuation report)
  • Prepaid expenses (GL control vs prepaid amortization schedule)
  • Accrued liabilities (GL control vs accrual detail schedules)

Process:

  1. Pull GL balance for the control account as of period end
  2. Pull subledger trial balance or detail report as of the same date
  3. Compare totals — they should match if posting is real-time
  4. Investigate any differences (timing of posting, manual entries not reflected, interface errors)

Common causes of differences:

  • Manual journal entries posted to the control account but not reflected in the subledger
  • Subledger transactions not yet interfaced to the GL
  • Timing differences in batch posting
  • Reclassification entries in the GL without subledger adjustment
  • System interface errors or failed postings

Bank Reconciliation

Compare the GL cash balance to the bank statement balance.

Process:

  1. Obtain the bank statement balance as of period end
  2. Pull the GL cash account balance as of the same date
  3. Identify outstanding checks (issued but not cleared at the bank)
  4. Identify deposits in transit (recorded in GL but not yet credited by bank)
  5. Identify bank charges, interest, or adjustments not yet recorded in GL
  6. Reconcile both sides to an adjusted balance

Standard format:

Balance per bank statement:         $XX,XXX
Add: Deposits in transit            $X,XXX
Less: Outstanding checks           ($X,XXX)
Add/Less: Bank errors               $X,XXX
Adjusted bank balance:              $XX,XXX

Balance per general ledger:         $XX,XXX
Add: Interest/credits not recorded  $X,XXX
Less: Bank fees not recorded       ($X,XXX)
Add/Less: GL errors                 $X,XXX
Adjusted GL balance:                $XX,XXX

Difference:                         $0.00

Intercompany Reconciliation

Reconcile balances between related entities to ensure they net to zero on consolidation.

Process:

  1. Pull intercompany receivable/payable balances for each entity pair
  2. Compare Entity A's receivable from Entity B to Entity B's payable to Entity A
  3. Identify and resolve differences
  4. Confirm all intercompany transactions have been recorded on both sides
  5. Verify elimination entries are correct for consolidation

Common causes of differences:

  • Transactions recorded by one entity but not the other (timing)
  • Different FX rates used by each entity
  • Misclassification (intercompany vs third-party)
  • Disputed amounts or unapplied payments
  • Different period-end cut-off practices across entities

Reconciling Item Categorization

Category 1: Timing Differences

Items that exist because of normal processing timing and will clear without action:

  • Outstanding checks: Checks issued and recorded in GL, pending bank clearance
  • Deposits in transit: Deposits made and recorded in GL, pending bank credit
  • In-transit transactions: Items posted in one system but pending interface to the other
  • Pending approvals: Transactions awaiting approval to post in one system

Expected resolution: These items should clear within the normal processing cycle (typically 1-5 business days). No adjusting entry needed.

Category 2: Adjustments Required

Items that require a journal entry to correct:

  • Unrecorded bank charges: Bank fees, wire charges, returned item fees
  • Unrecorded interest: Interest income or expense from bank/lender
  • Recording errors: Wrong amount, wrong account, duplicates
  • Missing entries: Transactions in one system with no corresponding entry in the other
  • Classification errors: Correctly recorded but in the wrong account

Action: Prepare adjusting journal entry to correct the GL or subledger.

Category 3: Requires Investigation

Items that cannot be immediately explained:

  • Unidentified differences: Variances with no obvious cause
  • Disputed items: Amounts contested between parties
  • Aged outstanding items: Items that have not cleared within expected timeframes
  • Recurring unexplained differences: Same type of difference appearing each period

Action: Investigate root cause, document findings, escalate if unresolved.

Aging Analysis for Outstanding Items

Track the age of reconciling items to identify stale items requiring escalation:

Age BucketStatusAction
0-30 daysCurrentMonitor — within normal processing cycle
31-60 daysAgingInvestigate — follow up on why item has not cleared
61-90 daysOverdueEscalate — notify supervisor, document investigation
90+ daysStaleEscalate to management — potential write-off or adjustment needed

Aging Report Format

Item #DescriptionAmountDate OriginatedAge (Days)CategoryStatusOwner
1[Detail]$X,XXX[Date]XX[Type][Status][Name]

Trending

Track reconciling item totals over time to identify growing balances:

  • Compare total outstanding items to prior period
  • Flag if total reconciling items exceed materiality threshold
  • Flag if number of items is growing period over period
  • Identify recurring items that appear every period (may indicate process issue)

Escalation Thresholds

Define escalation triggers based on your organization's risk tolerance:

TriggerThreshold (Example)Escalation
Individual item amount> $10,000Supervisor review
Individual item amount> $50,000Controller review
Total reconciling items> $100,000Controller review
Item age> 60 daysSupervisor follow-up
Item age> 90 daysController / management review
Unreconciled differenceAny amountCannot close — must resolve or document
Growing trend3+ consecutive periodsProcess improvement investigation

Note: Set thresholds based on your organization's materiality level and risk appetite. The examples above are illustrative.

Reconciliation Best Practices

  1. Timeliness: Complete reconciliations within the close calendar deadline (typically T+3 to T+5 business days after period end)
  2. Completeness: Reconcile all balance sheet accounts on a defined frequency (monthly for material accounts, quarterly for immaterial)
  3. Documentation: Every reconciliation should include preparer, reviewer, date, and clear explanation of all reconciling items
  4. Segregation: The person who reconciles should not be the same person who processes transactions in that account
  5. Follow-through: Track open items to resolution — do not just carry items forward indefinitely
  6. Root cause analysis: For recurring reconciling items, investigate and fix the underlying process issue
  7. Standardization: Use consistent templates and procedures across all accounts
  8. Retention: Maintain reconciliations and supporting detail per your organization's document retention policy

Frequently asked questions

What does the Reconciliation AI skill do?

Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.

Why use Reconciliation on TypingMind?

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

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

Which AI models can use 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 Reconciliation?

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

Is the Reconciliation AI skill free?

Yes. It is published on GitHub by anthropics 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 👇