agentsclimarketplace

Data reconciliation and financial controls

Skill vaquarkhan/data-engineering-agent-skills/skills/data-reconciliation-and-financial-controls

Production-grade Agent Skills for data engineering AI agents: 73 workflows, platform presets, safe backfill/replay, Kafka & Spark reliability, MCP observability, and VS Code/JetBrains installers.

Install
npx -y skills add vaquarkhan/data-engineering-agent-skills --skill data-reconciliation-and-financial-controls

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 21 stars21 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Guides agents through reconciliation and control design for business-critical data. Use when validating financial, operational, or audit-sensitive metrics with source-to-target totals, control balances, exception tracking, or close-process dependencies.

SKILL.md

2.3 KB, as published. Nobody here has run it

Data Reconciliation And Financial Controls

Overview

Use this skill when correctness must be proven with control evidence, not only tests. It helps agents design reconciliations, control totals, exception workflows, and audit-friendly validation for high-trust datasets.

When to Use

  • finance, billing, or revenue pipelines
  • audit-sensitive operational datasets
  • month-end or close-process data products
  • source-to-target control validations
  • exception-based review flows

Do not rely on a few spot queries when the business requires reconciled numbers.

Workflow

  1. Define the control objective. Clarify:

    • what must reconcile
    • acceptable variance
    • reconciliation frequency
    • owner of exceptions

  2. Choose the reconciliation pattern. Common patterns:

    • row-count reconciliation
    • control totals
    • aggregate balance checks
    • record-level exception matching

  3. Make timing and cutoff rules explicit. Reconciliation often depends on accounting windows or source close timing.

  4. Capture and route exceptions.

  5. Preserve evidence. Control systems need reviewable records, not only ephemeral job output.

Common Rationalizations

RationalizationReality
"The transformation logic is simple enough to trust."Critical numbers still need independent validation evidence.
"A small variance is probably fine."Acceptable variance must be defined, not guessed after a miss.
"The warehouse total matches once, so we are done."Control reliability requires repeatable evidence over time.

Red Flags

  • no explicit acceptable variance exists
  • cutoff timing is undocumented
  • exceptions are noticed manually and inconsistently
  • control evidence cannot be reproduced later

Verification

  • Control objectives and acceptable variance are defined
  • Reconciliation logic is explicit and reviewable
  • Exceptions have an owner and workflow
  • Control evidence is retained for audit or review

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.