Sox Testing logo

Sox Testing

OrganizationPopular
anthropics
sox-testing

Generate SOX sample selections, testing workpapers, and control assessments. Use when planning quarterly or annual SOX 404 testing, pulling a sample for a control (revenue, P2P, ITGC, close), building a testing workpaper template, or evaluating and classifying a control deficiency.

Overview

Publisheranthropics
Repositoryknowledge-work-plugins
Skill namesox-testing
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 Sox Testing 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/sox-testing .claude/skills/sox-testing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sox Testing 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 Sox Testing 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 Sox Testing 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.

SOX Compliance Testing

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Important: This command assists with SOX compliance workflows but does not provide audit or legal advice. All testing workpapers and assessments should be reviewed by qualified financial professionals before use in audit documentation.

Generate sample selections, create testing workpapers, document control assessments, and provide testing templates for SOX 404 internal controls over financial reporting.

Usage

/sox <control-area> <period>

Arguments

  • control-area — The control area to test:
    • revenue-recognition — Revenue cycle controls (order-to-cash)
    • procure-to-pay or p2p — Procurement and AP controls (purchase-to-pay)
    • payroll — Payroll processing and compensation controls
    • financial-close — Period-end close and reporting controls
    • treasury — Cash management and treasury controls
    • fixed-assets — Capital asset lifecycle controls
    • inventory — Inventory valuation and management controls
    • itgc — IT general controls (access, change management, operations)
    • entity-level — Entity-level and monitoring controls
    • journal-entries — Journal entry processing controls
    • Any specific control ID or name
  • period — The testing period (e.g., 2024-Q4, 2024, 2024-H2)

Workflow

1. Identify Controls to Test

Based on the control area, identify the key controls. Present the control matrix:

Control #Control DescriptionTypeFrequencyKey/Non-KeyRiskAssertion
[ID][Description]Manual/Automated/IT-DependentDaily/Weekly/Monthly/Quarterly/AnnualKeyHigh/Medium/Low[CEAVOP]

Control types:

  • Automated: System-enforced controls with no manual intervention
  • Manual: Controls performed by personnel with judgment
  • IT-dependent manual: Manual controls that rely on system-generated data

Assertions (CEAVOP):

  • Completeness — All transactions are recorded
  • Existence/Occurrence — Transactions actually occurred
  • Accuracy — Amounts are correctly recorded
  • Valuation — Assets/liabilities are properly valued
  • Obligations/Rights — Entity has rights to assets, obligations for liabilities
  • Presentation/Disclosure — Properly classified and disclosed

2. Determine Sample Size

Calculate sample sizes based on control frequency and risk:

Control FrequencyPopulation Size (approx.)Recommended Sample
Annual11 (test the instance)
Quarterly42
Monthly122-4 (based on risk)
Weekly525-15 (based on risk)
Daily~25020-40 (based on risk)
Per-transactionVaries25-60 (based on risk and volume)

Adjust for:

  • Risk level: Higher risk controls require larger samples
  • Prior year results: Controls with prior deficiencies need larger samples
  • Reliance: Controls relied upon by external auditors may need larger samples

3. Generate Sample Selection

Select samples from the population using the appropriate method:

Random selection (default for transaction-level controls):

  • Generate random numbers to select specific items from the population
  • Ensure coverage across the full period

Systematic selection (for periodic controls):

  • Select items at fixed intervals with a random start point
  • Ensure representation across all sub-periods

Targeted selection (supplement to random, for risk-based testing):

  • Select items with specific risk characteristics (high dollar, unusual, period-end)
  • Document rationale for targeted selections

Present the sample:

SAMPLE SELECTION
Control: [Control ID] — [Description]
Period: [Testing period]
Population: [Count] items, $[Total value]
Sample size: [N] items
Selection method: [Random/Systematic/Targeted]

| Sample # | Transaction Date | Reference/ID | Amount | Selection Basis |
|----------|-----------------|--------------|--------|-----------------|
| 1        | [Date]          | [Ref]        | $X,XXX | Random          |
| 2        | [Date]          | [Ref]        | $X,XXX | Random          |
| ...      | ...             | ...          | ...    | ...             |

4. Create Testing Workpaper

Generate a testing template for each control:

SOX CONTROL TESTING WORKPAPER
==============================
Control #: [ID]
Control Description: [Full description of the control activity]
Control Owner: [Role/title — to be filled by tester]
Control Type: [Manual/Automated/IT-Dependent Manual]
Frequency: [How often the control operates]
Key Control: [Yes/No]
Relevant Assertion(s): [CEAVOP]
Testing Period: [Period]

TEST OBJECTIVE:
To determine whether [control description] operated effectively throughout the testing period.

TEST PROCEDURES:
1. [Step 1 — What to inspect, examine, or re-perform]
2. [Step 2 — What evidence to obtain]
3. [Step 3 — What to compare or verify]
4. [Step 4 — How to evaluate completeness of performance]
5. [Step 5 — How to assess timeliness of performance]

EXPECTED EVIDENCE:
- [Document type 1 — e.g., signed approval form]
- [Document type 2 — e.g., system screenshot showing review]
- [Document type 3 — e.g., reconciliation with preparer sign-off]

TEST RESULTS:

| Sample # | Ref | Procedure 1 | Procedure 2 | Procedure 3 | Result | Exception? | Notes |
|----------|-----|-------------|-------------|-------------|--------|------------|-------|
| 1        |     | Pass/Fail   | Pass/Fail   | Pass/Fail   | Pass/Fail | Y/N    |       |
| 2        |     | Pass/Fail   | Pass/Fail   | Pass/Fail   | Pass/Fail | Y/N    |       |

EXCEPTIONS NOTED:
| Sample # | Exception Description | Root Cause | Compensating Control | Impact |
|----------|----------------------|------------|---------------------|--------|
|          |                      |            |                     |        |

CONCLUSION:
[ ] Effective — Control operated effectively with no exceptions
[ ] Effective with exceptions — Control operated effectively; exceptions are isolated
[ ] Deficiency — Control did not operate effectively
[ ] Significant Deficiency — Deficiency is more than inconsequential
[ ] Material Weakness — Reasonable possibility of material misstatement not prevented/detected

Tested by: ________________  Date: ________
Reviewed by: _______________  Date: ________

5. Provide Common Control Templates

Based on the control area, provide pre-built test step templates:

Revenue Recognition:

  • Verify sales order approval and authorization
  • Confirm delivery/performance evidence
  • Test revenue recognition timing against contract terms
  • Verify pricing accuracy to contract/price list
  • Test credit memo approval and validity

Procure to Pay:

  • Verify purchase order approval and authorization limits
  • Confirm three-way match (PO, receipt, invoice)
  • Test vendor master data change controls
  • Verify payment approval and segregation of duties
  • Test duplicate payment prevention controls

Financial Close:

  • Verify account reconciliation completeness and timeliness
  • Test journal entry approval and segregation of duties
  • Verify management review of financial statements
  • Test consolidation and elimination entries
  • Verify disclosure checklist completion

ITGC:

  • Test user access provisioning and de-provisioning
  • Verify privileged access reviews
  • Test change management approval and testing
  • Verify batch job monitoring and exception handling
  • Test backup and recovery procedures

6. Document Control Assessment

Classify any identified deficiencies:

Deficiency: A control does not allow management or employees to prevent or detect misstatements on a timely basis. Consider:

  • Likelihood of misstatement
  • Magnitude of potential misstatement
  • Whether compensating controls exist

Significant Deficiency: A deficiency (or combination) that is less severe than a material weakness but important enough to merit attention by those responsible for oversight.

Material Weakness: A deficiency (or combination) such that there is a reasonable possibility that a material misstatement will not be prevented or detected on a timely basis.

7. Output

Provide:

  1. Control matrix for the selected area
  2. Sample selections with methodology documentation
  3. Testing workpaper templates with pre-populated test steps
  4. Results documentation template
  5. Deficiency evaluation framework (if exceptions are identified)
  6. Suggested remediation actions for any noted deficiencies

Frequently asked questions

What does the Sox Testing AI skill do?

Generate SOX sample selections, testing workpapers, and control assessments. Use when planning quarterly or annual SOX 404 testing, pulling a sample for a control (revenue, P2P, ITGC, close), building a testing workpaper template, or evaluating and classifying a control deficiency.

Why use Sox Testing on TypingMind?

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

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

Which AI models can use Sox Testing?

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 Sox Testing?

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

Is the Sox Testing 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 👇