Regulatory Change Monitor logo

Regulatory Change Monitor

Organization
Amazon-Quick
regulatory-change-monitor

Monitors regulatory feeds (SEC, GDPR enforcement, EU AI Act, NIST, FDA, FTC) for changes relevant to the user's industry and compliance scope. Deduplicates findings, classifies by impact level and urgency, and produces plain-language alerts with compliance action recommendations. Use when asked to 'check for regulatory changes', 'what's new in GDPR', 'regulatory update', 'compliance news', 'any new SEC rules', or 'monitor regulations for us'.

Overview

PublisherAmazon-Quick
RepositoryAmazon-Quick-official-catalog
Skill nameregulatory-change-monitor
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 Regulatory Change Monitor 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/legal/regulatory-change-monitor
  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/legal/regulatory-change-monitor .claude/skills/regulatory-change-monitor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Regulatory Change Monitor 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 Regulatory Change Monitor 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 Regulatory Change Monitor 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

Scans official regulatory sources for new or updated rules, guidance, and enforcement actions relevant to the user's compliance scope. Produces a deduplicated, impact-classified digest with plain-language summaries and recommended next steps.

Workflow

<Definition - Regulatory Impact Levels> Each finding is classified into one of three impact levels:

  • Informational: Guidance documents, advisory opinions, or notices that do not impose new obligations. No immediate action required, but awareness is recommended.
  • Action Required: Final rules, amendments, or enforcement actions that create new obligations or modify existing ones. The user's compliance team should review and plan implementation before the effective date.
  • Urgent: Rules with imminent effective dates (within 30 days), enforcement actions against entities in the user's industry, or emergency orders. Immediate review is necessary. </Definition - Regulatory Impact Levels>

<Definition - Rule Lifecycle> Regulatory rules move through distinct stages:

  • Proposed: Published for public comment. Not yet binding. May change substantially before finalization.
  • Final: Comment period closed. Rule text is fixed. Compliance obligations begin on the stated effective date.
  • Effective: The rule is now in force. Regulated entities must comply.
  • Enforced: The regulator has taken action (fines, consent orders, cease-and-desist) against entities for non-compliance. </Definition - Rule Lifecycle>

<Definition - Common Regulatory Bodies> Key sources by jurisdiction and scope:

  • US Financial: SEC (Securities and Exchange Commission), CFTC, FINRA, OCC, CFPB
  • US Healthcare: FDA, HHS, CMS
  • US Data/Cyber: FTC, CISA, NIST (frameworks, not binding rules)
  • US General: Federal Register (primary publication vehicle for all federal agencies)
  • EU: European Commission, European Data Protection Board (EDPB), EU Official Journal
  • UK: FCA, ICO, MHRA, UK Statutory Instruments
  • AI Governance: NIST AI RMF, EU AI Act (via Official Journal), state-level AI bills (US)
  • Environmental: EPA, EU ETS, UK Environment Agency </Definition - Common Regulatory Bodies>

<Workflow - Regulatory Change Scan description="End-to-end regulatory change monitoring and digest generation." tools=[web_search, url_fetch, file_write, run_python, open_in_session_tab] triggers=["check for regulatory changes", "what's new in GDPR", "regulatory update", "compliance news", "any new SEC rules", "monitor regulations for us"]

  1. [Ask user] Gather any missing inputs: scope, jurisdiction, industry, and lookback period. If the user's request implies specific values (e.g., "what's new in GDPR" implies scope=data_privacy, jurisdiction=eu), confirm the inferred selection rather than presenting the full menu. If fails: if a required input (scope, jurisdiction, or industry) is still missing after asking, re-ask for that specific input and do not start the scan until it is provided.

  2. [Agent] Build a search plan based on the confirmed inputs. Map each scope-jurisdiction pair to the relevant regulatory bodies (per the Common Regulatory Bodies definition). For each body, construct targeted search queries combining the body name, the industry context, and a date range matching the lookback period. Example queries: "SEC final rule financial services site:sec.gov", "EDPB enforcement decision 2026", "Federal Register AI governance". If fails: if a scope-jurisdiction pair maps to no known regulatory body, note the gap to the user and continue with the pairs that do map.

  3. [Agent] Execute web searches for each regulatory body in the plan. For each search, collect the title, URL, publication date, and snippet. Run searches in batches grouped by jurisdiction to maintain organization. Store raw results in a working list. If fails: if a search returns no results or errors, record that body as 'no results' and continue with the remaining searches rather than stopping.

  4. [Agent] For each result that appears relevant based on title and snippet, fetch the source page to confirm: (a) it is an official publication from the regulatory body, not a third-party summary, (b) it falls within the lookback period, (c) it relates to the user's scope and industry. Discard results that fail any of these checks. Trace third-party mentions back to the official source URL when possible. If fails: if a source page cannot be fetched, discard that result and note the unverified item rather than including an unconfirmed finding.

  5. [Think] Deduplicate the confirmed findings. Group by underlying regulatory action (same rule number, docket, or enforcement case). Merge entries that reference the same action from different sources into a single finding, preserving all source URLs. Classify each finding by lifecycle stage (Proposed, Final, Effective, Enforced) and impact level (Informational, Action Required, Urgent). Calculate days remaining until effective dates or comment deadlines. Flag jurisdiction overlaps per Rule 8.

  6. [Agent] Using run_python, sort findings by impact level (Urgent first), then by effective date proximity. Format the digest using the Regulatory Alert Digest template. Include all required fields for each finding. If fails: if sorting or formatting errors, fall back to presenting the findings unsorted and report the formatting error to the user.

  7. [Agent] Write the formatted digest to a file and open it in the session tab for the user to review. File name format: regulatory_digest_YYYY-MM-DD.md. If fails: report the specific write or open error and present the digest inline instead.

  8. [Ask user] Present a summary count (e.g., "Found 3 Urgent, 5 Action Required, and 8 Informational changes"). Ask if the user wants to drill into any specific finding, adjust the scope for future scans, or export the digest in a different format. If fails: if the user does not respond, leave the saved digest available and end without further changes.

</Workflow - Regulatory Change Scan>

<Template - Regulatory Alert Digest>

markdown
# Regulatory Change Digest

**Scope:** {{scope}}
**Jurisdictions:** {{jurisdiction}}
**Industry:** {{industry}}
**Period:** {{lookback_start}} to {{lookback_end}}
**Generated:** {{current_date}}

---

## Urgent

### [Finding Title]
- **Source:** [Regulatory Body Name](official_url)
- **Lifecycle Stage:** [Proposed | Final | Effective | Enforced]
- **Publication Date:** YYYY-MM-DD
- **Effective Date:** YYYY-MM-DD (X days remaining)
- **Comment Deadline:** YYYY-MM-DD (if applicable, X days remaining)
- **Jurisdiction:** [US | EU | UK | Multiple]
- **Overlap Flag:** [Note if conflicting requirements exist in another jurisdiction]

**Summary:** Plain-language description of what changed or was published. Two to four sentences covering the substance of the rule or action.

**Who is affected:** Description of which entities, products, or activities fall under this rule based on the published scope.

**Recommended action:** What the compliance team should evaluate, review, or prepare. Not legal advice. Framed as "Review with legal counsel whether..." or "Evaluate whether your organization's current practices align with..."

---

## Action Required

(Same structure as Urgent, repeated for each finding)

---

## Informational

(Same structure, repeated for each finding)

---

## Notes

- Findings are sourced exclusively from official regulatory body publications.
- This digest does not constitute legal advice. Consult qualified legal counsel for interpretation and applicability determinations.
- "Proposed" rules are not yet binding and may change before finalization.

</Template - Regulatory Alert Digest>

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 Regulatory Change Monitor AI skill do?

Monitors regulatory feeds (SEC, GDPR enforcement, EU AI Act, NIST, FDA, FTC) for changes relevant to the user's industry and compliance scope. Deduplicates findings, classifies by impact level and urgency, and produces plain-language alerts with compliance action recommendations. Use when asked to 'check for regulatory changes', 'what's new in GDPR', 'regulatory update', 'compliance news', 'any new SEC rules', or 'monitor regulations for us'.

Why use Regulatory Change Monitor on TypingMind?

Because you install it once and use it with any model. Regulatory Change Monitor 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 Regulatory Change Monitor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/legal/regulatory-change-monitor. 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 Regulatory Change Monitor?

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 Regulatory Change Monitor?

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

Is the Regulatory Change Monitor 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 👇