data-reconciliation-and-financial-controls

Name: data-reconciliation-and-financial-controls
Author: vaquarkhan

19stars4forks

How to install data-reconciliation-and-financial-controls?

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

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

Installs into the current project.

Summary

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.

Files · 1

View on GitHub

SKILL.md

1	# Data Reconciliation And Financial Controls
2
3	## Overview
4
5	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.
6
7	## When to Use
8
9	- finance, billing, or revenue pipelines
10	- audit-sensitive operational datasets
11	- month-end or close-process data products
12	- source-to-target control validations
13	- exception-based review flows
14
15	Do not rely on a few spot queries when the business requires reconciled numbers.
16
17	## Workflow
18
19	1. Define the control objective.
20	Clarify:
21	- what must reconcile
22	- acceptable variance
23	- reconciliation frequency
24	- owner of exceptions
25
26	2. Choose the reconciliation pattern.
27	Common patterns:
28	- row-count reconciliation
29	- control totals
30	- aggregate balance checks
31	- record-level exception matching
32
33	3. Make timing and cutoff rules explicit.
34	Reconciliation often depends on accounting windows or source close timing.
35
36	4. Capture and route exceptions.
37
38	5. Preserve evidence.
39	Control systems need reviewable records, not only ephemeral job output.
40
41	## Common Rationalizations
42
43	\| Rationalization \| Reality \|
44	\| --- \| --- \|
45	\| "The transformation logic is simple enough to trust." \| Critical numbers still need independent validation evidence. \|
46	\| "A small variance is probably fine." \| Acceptable variance must be defined, not guessed after a miss. \|
47	\| "The warehouse total matches once, so we are done." \| Control reliability requires repeatable evidence over time. \|
48
49	## Red Flags
50
51	- no explicit acceptable variance exists
52	- cutoff timing is undocumented
53	- exceptions are noticed manually and inconsistently
54	- control evidence cannot be reproduced later
55
56	## Verification
57
58	- [ ] Control objectives and acceptable variance are defined
59	- [ ] Reconciliation logic is explicit and reviewable
60	- [ ] Exceptions have an owner and workflow
61	- [ ] Control evidence is retained for audit or review

People who liked this also viewed

6 picks

Type

data-reconciliation-and-financial-controls

19stars4forks

View on GitHub

How to install data-reconciliation-and-financial-controls?

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

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Data Reconciliation And Financial Controls
2
3	## Overview
4
5	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.
6
7	## When to Use
8
9	- finance, billing, or revenue pipelines
10	- audit-sensitive operational datasets
11	- month-end or close-process data products
12	- source-to-target control validations
13	- exception-based review flows
14
15	Do not rely on a few spot queries when the business requires reconciled numbers.
16
17	## Workflow
18
19	1. Define the control objective.
20	Clarify:
21	- what must reconcile
22	- acceptable variance
23	- reconciliation frequency
24	- owner of exceptions
25
26	2. Choose the reconciliation pattern.
27	Common patterns:
28	- row-count reconciliation
29	- control totals
30	- aggregate balance checks
31	- record-level exception matching
32
33	3. Make timing and cutoff rules explicit.
34	Reconciliation often depends on accounting windows or source close timing.
35
36	4. Capture and route exceptions.
37
38	5. Preserve evidence.
39	Control systems need reviewable records, not only ephemeral job output.
40
41	## Common Rationalizations
42
43	\| Rationalization \| Reality \|
44	\| --- \| --- \|
45	\| "The transformation logic is simple enough to trust." \| Critical numbers still need independent validation evidence. \|
46	\| "A small variance is probably fine." \| Acceptable variance must be defined, not guessed after a miss. \|
47	\| "The warehouse total matches once, so we are done." \| Control reliability requires repeatable evidence over time. \|
48
49	## Red Flags
50
51	- no explicit acceptable variance exists
52	- cutoff timing is undocumented
53	- exceptions are noticed manually and inconsistently
54	- control evidence cannot be reproduced later
55
56	## Verification
57
58	- [ ] Control objectives and acceptable variance are defined
59	- [ ] Reconciliation logic is explicit and reviewable
60	- [ ] Exceptions have an owner and workflow
61	- [ ] Control evidence is retained for audit or review

People who liked this also viewed

6 picks

Type