Automated summary
Automates bank reconciliation by matching book and bank transactions, detecting discrepancies, and generating reports.
Strengths
- Supports transaction import via CSV or Plaid
- Exact and fuzzy matching with date and amount tolerance
- Detects discrepancies and tracks outstanding items
- Generates structured reconciliation reports
Limitations
- Requires initial account and rule setup
- Fuzzy matches may require manual review
- Does not handle complex multi-currency scenarios
Use for monthly bank account reconciliation or when balance discrepancies are detected.
Avoid for real-time transaction processing or when bank data is unreliable.
Security analysis
SafeThe skill is a procedural guide for bank reconciliation. It instructs querying a database and generating reports, with no execution of destructive commands. It explicitly requires manual approval for adjustments and logging of actions, posing no security risk.
No concerns found
How this analysis is madeExamples
Reconcile bank account 1234 for January 2026 using the imported bank CSV file. Generate a report and flag any discrepancies.Show me all unmatched transactions from the January reconciliation for account 1234. Identify potential fuzzy matches.Verify the book balance for account 1234 equals the cleared bank balance plus outstanding items as of January 31, 2026.name: bank-reconciliation description: "Match bank transactions to book transactions, detect discrepancies, and resolve mismatches. Use when reconciling bank accounts, investigating unmatched transactions, or generating reconciliation reports. Handles multiple accounts and currencies."
Bank Reconciliation Skill
Purpose
Automates the bank reconciliation process by matching book transactions to bank statement transactions, detecting discrepancies, and facilitating resolution.
Triggers
- End of month reconciliation scheduled
- User initiates manual reconciliation
- Discrepancy detected in account balance
- Bank feed imported via Plaid
Capabilities
- Transaction Import - Import bank transactions via Plaid or CSV
- Transaction Matching - Match book to bank transactions
- Discrepancy Detection - Identify unmatched transactions
- Fuzzy Matching - Match similar amounts and dates
- Outstanding Items - Track checks and deposits in transit
- Balance Verification - Verify book balance = cleared bank balance + outstanding items
Instructions
Step 1: Import Bank Transactions
Options:
- Plaid Integration - Fetch via data-sync skill
- CSV Upload - Parse CSV file with columns: date, description, amount
- Manual Entry - User inputs transactions
Step 2: Load Book Transactions
Query database for unreconciled transactions in date range:
SELECT * FROM transactions
WHERE account_id = $1
AND date BETWEEN $2 AND $3
AND reconciled = FALSE
Step 3: Exact Matching
Match transactions where:
- Date matches exactly
- Amount matches exactly (cents)
- Payee name matches (after normalization)
Mark as reconciled = TRUE when matched.
Step 4: Fuzzy Matching
For unmatched transactions, try fuzzy match:
- Date proximity - Within ±3 days
- Amount match - Exact amount
- Payee similarity - Levenshtein distance < 3 or substring match
Present fuzzy matches for manual review.
Step 5: Discrepancy Detection
Identify discrepancies:
- Missing from Bank - In books but not in bank statement (check in transit?)
- Missing from Books - In bank but not in books (unrecorded transaction?)
- Amount Mismatch - Same transaction, different amounts (data entry error?)
- Date Mismatch - Same transaction, different dates (timing difference?)
Step 6: Outstanding Items
Track outstanding items:
- Checks Written - In books, not yet cleared bank
- Deposits Made - In books, not yet posted by bank
Calculate outstanding balance:
Book Balance - Outstanding Checks + Outstanding Deposits = Bank Balance
Step 7: Generate Report
Create reconciliation report:
{
"account_id": "uuid",
"period_start": "2026-01-01",
"period_end": "2026-01-31",
"book_balance": 5000000, // cents
"bank_balance": 4950000, // cents
"matched_count": 45,
"unmatched_book_count": 2,
"unmatched_bank_count": 1,
"outstanding_checks": [
{"id": "...", "amount": -25000, "payee": "..."}
],
"outstanding_deposits": [
{"id": "...", "amount": 75000}
],
"discrepancies": [
{
"type": "missing_from_bank",
"transaction_id": "...",
"description": "...",
"amount": -5000
}
],
"status": "balanced", // or "discrepancy"
"requires_investigation": false
}
Decision Logic
Auto-Reconcile
- Exact match (date, amount, payee)
- Previously reconciled (if re-running)
Manual Review Required
- Fuzzy match (present options to user)
- Significant discrepancy (> $100)
- Unusual pattern (e.g., duplicate amounts)
Escalate
- Unresolved after 3 reconciliation attempts
- Balance off by > $1000
- Fraud indicators detected
Integration Points
- data-sync (via Integration Lead) - For Plaid import
- transaction-matcher (Reconciliation worker) - For matching logic
- discrepancy-investigator (Reconciliation worker) - For investigation
- audit-trail - Log all reconciliation actions
Models
- Matching: Deterministic algorithm (no LLM)
- Payee Normalization: Claude Sonnet 4 or Gemini Flash
- Discrepancy Investigation: Claude Sonnet 4
Security
- Never modify historical transactions automatically
- Require manual approval for adjustments
- Log all reconciliation actions to audit_log
- Preserve original bank data
Invoke this skill at month-end or when investigating account discrepancies.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/bank-reconciliation-mm78noir/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/bank-reconciliation-mm78noir' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/bank-reconciliation-mm78noir/download' --output '.skill-downloads/bank-reconciliation-mm78noir/SKILL.md.part' && mv '.skill-downloads/bank-reconciliation-mm78noir/SKILL.md.part' '.skill-downloads/bank-reconciliation-mm78noir/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/bank-reconciliation-mm78noir/SKILL.md' && test -s '.skill-downloads/bank-reconciliation-mm78noir/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/bank-reconciliation' && cp -R '.skill-downloads/bank-reconciliation-mm78noir' '.claude/skills/bank-reconciliation'Cursor
test -f '.skill-downloads/bank-reconciliation-mm78noir/SKILL.md' && test -s '.skill-downloads/bank-reconciliation-mm78noir/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/bank-reconciliation' && cp -R '.skill-downloads/bank-reconciliation-mm78noir' '.cursor/skills/bank-reconciliation'Codex
test -f '.skill-downloads/bank-reconciliation-mm78noir/SKILL.md' && test -s '.skill-downloads/bank-reconciliation-mm78noir/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/bank-reconciliation' && cp -R '.skill-downloads/bank-reconciliation-mm78noir' '.agents/skills/bank-reconciliation'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/bank-reconciliation-mm78noir'openskills read 'bank-reconciliation-mm78noir'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/bank-reconciliation-mm78noir/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Create Interactive Maps with kepler.gl
Data & AI
Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.
Agent-Driven Parameter Optimization
Data & AI
Guide for optimizing configurable systems with a measurable objective, using bounded trials and evidence-based recommendations.
ICP Visitor Outreach
Data & AI
Identify signed-up users matching the ideal customer profile but stalled, and draft personalized outreach to re-engage them.