Compliance Automation logo

Compliance Automation

Organization
Amazon-Quick
compliance-automation

Generates draft compliance policies for SOC 2 Type I/II, ISO 27001, and HIPAA frameworks. Produces evidence collection checklists, control mapping matrices, and gap analysis reports from existing documentation. Use when asked to 'prepare for SOC 2 audit', 'generate compliance policies', 'map controls to framework', 'audit prep', 'compliance gap analysis', or 'ISO 27001 readiness'.

Overview

PublisherAmazon-Quick
RepositoryAmazon-Quick-official-catalog
Skill namecompliance-automation
Stars
50
Forks
4
Bundled files
1
LicenseMIT-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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Amazon-Quick on GitHub. Read the source before you install it.

Installation

Install the Compliance Automation 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.
    https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/security-compliance/compliance-automation
  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/Amazon-Quick/Amazon-Quick-official-catalog.git /tmp/Amazon-Quick-official-catalog
mkdir -p .claude/skills
cp -r /tmp/Amazon-Quick-official-catalog/skills/security-compliance/compliance-automation .claude/skills/compliance-automation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Compliance Automation 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 Compliance Automation 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 Compliance Automation 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.

Overview

Generates draft compliance documentation, control mapping matrices, evidence collection checklists, and gap analysis reports for major regulatory and audit frameworks. Ingests existing organizational documentation to identify what controls are already addressed and where gaps remain. All outputs are drafts requiring qualified legal and compliance review before use.

Workflow

<Definition - Trust Service Criteria> The five categories defined by the AICPA for SOC 2 engagements: Security (CC), Availability (A), Processing Integrity (PI), Confidentiality (C), and Privacy (P). Security is always in scope. The others are selected based on the service and its commitments. Each category contains numbered criteria (e.g., CC6.1) that map to specific control objectives. </Definition - Trust Service Criteria>

<Definition - Control Objectives> Statements describing what a control is designed to achieve. A single control objective may be satisfied by one or more implemented controls. In ISO 27001, these appear in Annex A. In SOC 2, they align to Trust Service Criteria points of focus. In HIPAA, they correspond to Administrative, Physical, and Technical Safeguard standards. </Definition - Control Objectives>

<Definition - Evidence Types> Documentation or artifacts that demonstrate a control is designed and operating effectively. Common categories:

  • Policy documents: Approved written statements of intent and requirements
  • Configuration screenshots: Point-in-time captures of system settings
  • Logs and reports: Automated output showing control execution over a period
  • Attestations: Signed statements from responsible personnel
  • Tickets and records: Change management, incident response, access review records </Definition - Evidence Types>

<Definition - Gap Classification> Rating applied to each control during gap analysis:

  • Fully Addressed: Control is documented, implemented, and evidence exists
  • Partially Addressed: Control exists but lacks documentation, evidence, or consistent execution
  • Not Addressed: No evidence of design or implementation
  • Not Applicable: Control is outside the defined scope with documented justification </Definition - Gap Classification>

<Definition - Framework Versions> The specific edition of each standard referenced during generation:

  • SOC 2: 2017 Trust Service Criteria (current as of this skill's creation date)
  • ISO 27001: ISO/IEC 27001:2022 with Annex A controls
  • HIPAA: 45 CFR Parts 160 and 164 (Security Rule, Privacy Rule, Breach Notification Rule) Always state the version in generated artifacts. If the user references a different version, confirm before proceeding. </Definition - Framework Versions>

<Workflow - Compliance Artifact Generation description="End-to-end compliance documentation generation flow." tools=[file_write, file_read, file_read_pdf, file_rag_search, open_in_session_tab] triggers=["prepare for SOC 2 audit", "generate compliance policies", "map controls to framework", "audit prep", "compliance gap analysis", "ISO 27001 readiness", "HIPAA compliance check"]

  1. [Ask user] Confirm the target framework, scope, and whether existing documentation is available. If framework is "custom", request the control catalog or reference document. If framework is "hipaa", ask whether the organization is a covered entity or business associate per Rule 9. If fails: If the framework or scope is missing, re-ask the user for the missing input and do not proceed until both are provided.

  2. [Agent] Determine the framework version per the Framework Versions definition. Load the relevant control catalog:

    • SOC 2 Type I/II: Trust Service Criteria with points of focus
    • ISO 27001: Annex A control set (2022 edition, 93 controls across 4 themes)
    • HIPAA: Security Rule standards and implementation specifications If the user specified a version that differs from the default, confirm before proceeding. If fails: If the control catalog cannot be loaded, report which framework failed and ask the user to confirm the version or supply the catalog.
  3. [Decide] If existing_docs path is provided, proceed to Step 4. If not, skip to Step 5 and generate templates with placeholder content only.

  4. [Agent] Ingest existing documentation using file_read, file_read_pdf, or file_rag_search. Extract:

    • Policy statements and their stated objectives
    • Referenced controls and security measures
    • Mentioned tools, platforms, and processes
    • Any existing compliance mappings or audit reports Organize findings by control domain. Do not modify source documents per Rule 12. If fails: If a source document cannot be read, report the specific file and continue with the documents that parsed, noting the unread source in the gap report.
  5. [Think] Map extracted findings (or empty placeholders if no docs provided) against the target framework's control catalog. For each control objective, classify coverage using the Gap Classification definition. Note overlapping controls across frameworks per Rule 7.

  6. [Agent] Generate the Control Mapping Matrix using the Control Mapping Matrix template. Save to the workspace using file_write. Include:

    • Every control objective in the target framework
    • Current coverage status (Fully Addressed, Partially Addressed, Not Addressed, Not Applicable)
    • Source reference from existing documentation (if applicable)
    • Cross-framework overlaps where relevant If fails: If the matrix cannot be written, report the write error, retry once, and present the matrix inline if the retry fails.
  7. [Agent] Generate the Gap Analysis Report using the Gap Analysis Report template. Save to workspace. Include:

    • Executive summary with counts by gap classification
    • Detailed findings per control domain
    • Prioritized remediation recommendations (Critical, High, Medium, Low)
    • Estimated effort indicators (hours/days, not calendar dates) If fails: If the report cannot be saved, report the write error, retry once, and present the report inline if the retry fails.
  8. [Ask user] Present the gap analysis summary: total controls assessed, breakdown by classification, and top-priority gaps. Confirm the user wants to proceed with policy generation and evidence checklist creation. Allow them to adjust scope or priorities. If fails: If the user does not confirm priorities, re-present the summary and ask which gaps to prioritize before continuing.

  9. [Agent] Generate draft policy documents for each control domain where gaps were identified (or for all domains if no existing docs). Each policy follows a consistent structure: Purpose, Scope, Roles and Responsibilities, Policy Statements, Related Controls, Review Cadence. Mark as DRAFT per Rule 3. If fails: If a policy document cannot be generated or saved, report which control domain failed and continue with the remaining domains.

  10. [Agent] Generate the Evidence Collection Checklist using the Evidence Collection Checklist template. For each control, specify:

    • Required evidence type (per Evidence Types definition)
    • Collection frequency (annual, quarterly, continuous, per-event)
    • Responsible role
    • Retention period per framework requirements
    • Storage location placeholder If fails: If the checklist cannot be written, report the write error, retry once, and present the checklist inline if the retry fails.
  11. [Agent] Compile all artifacts into a summary document listing what was generated, where each file is saved, and recommended next steps. Open the summary in the session tab using open_in_session_tab for user review. If fails: If the summary cannot be opened in the session tab, report the error and provide the file path so the user can open it manually.

</Workflow - Compliance Artifact Generation>

<Template - Control Mapping Matrix>

markdown
# Control Mapping Matrix
## DRAFT - Requires review by qualified compliance/legal professionals before use.

**Framework:** {{framework}} ({{version}})
**Scope:** {{scope}}
**Generated:** {{date}}

| Control ID | Control Objective | Status | Existing Evidence | Source Document | Cross-Framework Mapping | Notes |
|---|---|---|---|---|---|---|
| {{control_id}} | {{objective_text}} | {{Fully Addressed / Partially Addressed / Not Addressed / Not Applicable}} | {{evidence_reference}} | {{doc_name, section}} | {{overlapping_framework_control_ids}} | {{notes}} |

Repeat for all controls in the target framework catalog.

</Template - Control Mapping Matrix>

<Template - Gap Analysis Report>

markdown
# Gap Analysis Report
## DRAFT - Requires review by qualified compliance/legal professionals before use.

**Framework:** {{framework}} ({{version}})
**Scope:** {{scope}}
**Assessment Date:** {{date}}
**Limitation:** This analysis reflects documented controls only. Undocumented controls that exist in practice will appear as gaps.

### Executive Summary

| Classification | Count | Percentage |
|---|---|---|
| Fully Addressed | {{count}} | {{pct}}% |
| Partially Addressed | {{count}} | {{pct}}% |
| Not Addressed | {{count}} | {{pct}}% |
| Not Applicable | {{count}} | {{pct}}% |

### Priority Findings

#### Critical (Remediation recommended before audit engagement)
- **{{control_id}} - {{control_name}}:** {{finding_description}}. Remediation: {{recommendation}}. Estimated effort: {{effort}}.

#### High
...

#### Medium
...

#### Low
...

### Domain-by-Domain Analysis

#### {{Domain Name}} ({{framework_section_reference}})
| Control ID | Objective | Status | Finding | Recommendation |
|---|---|---|---|---|
| {{control_id}} | {{objective}} | {{status}} | {{finding}} | {{recommendation}} |

### Recommended Next Steps
1. {{step}}
2. {{step}}
...

</Template - Gap Analysis Report>

<Template - Evidence Collection Checklist>

markdown
# Evidence Collection Checklist
## DRAFT - Requires review by qualified compliance/legal professionals before use.

**Framework:** {{framework}} ({{version}})
**Scope:** {{scope}}
**Generated:** {{date}}

| Control ID | Control Objective | Evidence Required | Evidence Type | Collection Frequency | Responsible Role | Retention Period | Storage Location |
|---|---|---|---|---|---|---|---|
| {{control_id}} | {{objective}} | {{specific_artifact_description}} | {{Policy / Configuration / Log / Attestation / Record}} | {{Annual / Quarterly / Monthly / Continuous / Per-event}} | {{role}} | {{period}} | {{location_placeholder}} |

### Collection Notes
- Evidence must be timestamped and attributable to the review period.
- Screenshots must include visible date/time and system identification.
- Logs must cover the complete review period without gaps.
- Attestations must be signed by personnel with appropriate authority.

</Template - Evidence Collection Checklist>

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Compliance Automation AI skill do?

Generates draft compliance policies for SOC 2 Type I/II, ISO 27001, and HIPAA frameworks. Produces evidence collection checklists, control mapping matrices, and gap analysis reports from existing documentation. Use when asked to 'prepare for SOC 2 audit', 'generate compliance policies', 'map controls to framework', 'audit prep', 'compliance gap analysis', or 'ISO 27001 readiness'.

Why use Compliance Automation on TypingMind?

Because you install it once and use it with any model. Compliance Automation 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 Compliance Automation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/security-compliance/compliance-automation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Compliance Automation?

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 Compliance Automation?

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

Is the Compliance Automation AI skill free?

Yes. It is published on GitHub by Amazon-Quick under the MIT-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 👇