Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Internal Controls Walkthrough

ASecurity

Walk through one process and describe the control as it is actually performed, including where it can fail. Use when the user mentions control walkthrough, internal controls, SOX walkthrough, process control review, or asks for a control walkthrough note. Accounting skill by Yasir Jilani.

2 stars
0 votes
0 copies
0 views
Added 9/30/2026
ai-agentspythongoawsgitapi

Works with

cliapi

Security Analysis

A100/100

Scanned 9/30/2026

$npx -y skills add SYasJ/claude-business-skills --skill internal-controls-walkthrough --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Internal Controls Walkthrough?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Internal Controls Walkthrough
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/syasj-internal-controls-walkthrough/badge)](https://www.skillsdirectory.com/skills/syasj-internal-controls-walkthrough)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: internal-controls-walkthrough
description: "Walk through one process and describe the control as it is actually performed, including where it can fail. Use when the user mentions control walkthrough, internal controls, SOX walkthrough, process control review, or asks for a control walkthrough note. Accounting skill by Yasir Jilani."
license: MIT
compatibility: Agent Skills standard. No network access, extra packages, or credentials required.
metadata:
  author: Yasir Jilani
  version: "1.0.0"
  domain: accounting
---

<!-- GENERATED FILE - edits here are overwritten by scripts/generate.py.
     Edit the 'internal-controls-walkthrough' entry in source/, then run:
       python3 scripts/generate.py && python3 scripts/validate.py
     See CONTRIBUTING.md. -->

# Internal Controls Walkthrough

Walk through one process and describe the control as it is actually performed, including where it can fail.

## When to use this skill

Use this skill when the user:

- control walkthrough
- internal controls
- SOX walkthrough
- process control review

## When not to use this skill

- The user wants a different domain's specialist skill.
- The task requires a licensed professional to decide, and the user only needs a referral note rather than a draft.
- The request asks you to deceive, evade a control, or hide material facts.

## Professional boundary

This is not an audit opinion, compilation, or tax advice. Do not invent accounting standards. Use the policy, framework, and chart of accounts the organization actually follows.

## Operating boundaries

- Use only information the user provides or files they explicitly ask you to read. Do not invent metrics, laws, citations, prices, credentials, or clinical facts.
- Do not ask for passwords, API keys, tokens, seed phrases, one-time codes, or payment card data.
- Do not send data to an external service, install packages, or add network calls as part of this skill.
- Separate facts, assumptions, and recommendations. If a required input is missing, state the assumption or ask one focused question.
- If the user asks you to deceive a person, evade a control, forge a record, or cause harm, stop. Offer a legitimate alternative.
- Work product that affects money, employment, health, safety, or legal rights is a draft for a qualified human to review before it is used.

## Inputs to collect

- The process
- The risk they care about
- Who performs the control
- Evidence the control produces

## Workflow


### 1. Name the risk

What could go wrong in money, compliance, or reporting terms. A control with no risk is a habit.
### 2. Describe the as-is

Who does what, how often, and what evidence exists. Use the user's description. Do not draw a fantasy flowchart of best practice and call it their process.
### 3. Find gaps

Missing evidence, self-review, or a control that happens after the transaction is already irreversible.
### 4. Distinguish design and operation

You can comment on design from an interview. You cannot say the control operated all year unless they give you samples.
### 5. Recommend one fix

Evidence, a second reviewer, or a system check. A list of twenty improvements will not land.
### 6. No false assurance

This note is not a controls opinion and not a certification.

## Output

Deliver a **control walkthrough note**.

- Purpose of this control walkthrough note, in two sentences.
- Facts the user supplied, listed separately from assumptions.
- The work itself, in the structure the workflow names.
- Open questions, risks, and the single next action with an owner.
- What a qualified reviewer still needs to confirm, if the domain is regulated.

## Quality bar

- Every number, date, name, and citation came from the user or is marked as an assumption.
- The artifact can be used without reading this skill again.
- Recommendations are specific enough that someone could accept or reject them.
- Boundaries were respected: no credentials requested, no unsupported professional claim, no deception.

## Example

### Scenario

Priya Shah, controller at Northline Studio in Calgary, needs a control walkthrough note by 30 September 2026. The team says vendor payments are 'reviewed' but cannot show what the reviewer looks at.

### Example data

```text
From: Priya Shah, controller
Organization: Northline Studio, Calgary
Date: 14 September 2026
Needed by: 30 September 2026

The team says vendor payments are 'reviewed' but cannot show what the reviewer looks at.

The process: email to Priya Shah. No written steps after 1 Sep 2026
The risk they care about: Operating cash is open. No score in the file
Who performs the control: Priya Shah, controller
Evidence the control produces: one PDF, 2 pages, dated 14 September 2026
```

### Example outcome

**Control walkthrough note**
To: Priya Shah, controller, Northline Studio
Date: 14 September 2026 · Needed by: 30 September 2026

**Decision**
States the risk, describes the review as undocumented, and recommends one evidence fix without claiming certification.

**What the file supports**

| Input | Value | Status |
| --- | --- | --- |
| The process | email to Priya Shah. No written steps after 1 Sep 2026 | Needs confirmation |
| The risk they care about | Operating cash is open. No score in the file | Carried into the draft |
| Who performs the control | Priya Shah, controller | Carried into the draft |
| Evidence the control produces | one PDF, 2 pages, dated 14 September 2026 | Needs confirmation |

**How this draft was built**

**1. Name the risk**  
What could go wrong in money, compliance, or reporting terms. A control with no risk is a habit.

**2. Describe the as-is**  
Who does what, how often, and what evidence exists. Use the user's description. Do not draw a fantasy flowchart of best practice and call it their process.

**3. Find gaps**  
Missing evidence, self-review, or a control that happens after the transaction is already irreversible.

**4. Distinguish design and operation**  
You can comment on design from an interview. You cannot say the control operated all year unless they give you samples.

**5. Recommend one fix**  
Evidence, a second reviewer, or a system check. A list of twenty improvements will not land.

**Deliberately not done**
- A best-practice narrative presented as their process.
- Claiming the control operated all year from one interview.
- A certification no one issued.

**Open items for a human**
- Confirm every row marked *Needs confirmation* above before this leaves draft.
- Anything absent from the file stayed absent. No figure, date, or name was supplied from outside it.

Next: Priya Shah by 30 September 2026. This is a draft, not a sign-off.

## Anti-patterns

- A best-practice narrative presented as their process.
- Claiming the control operated all year from one interview.
- A certification no one issued.

## Related skills

- `control-design`
- `accounts-payable-control`
- `sox-walkthrough`

Attribution

SYasJSYasJ
View sourceSee grades on GitHubMore from SYasJ →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →