Regulatory Reporting logo

Regulatory Reporting

Community
agiprolabs
regulatory-reporting

[STUB] Regulatory report generation including IRS Form 8949, Schedule D, FinCEN FBAR, and state-specific crypto reporting requirements

Overview

Publisheragiprolabs
Repositoryclaude-trading-skills
Skill nameregulatory-reporting
Stars
434
Forks
85
Bundled files
2
LicenseMIT
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.

  • 2 bundled files

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

  • Open source

    Published by agiprolabs on GitHub. Read the source before you install it.

Installation

Install the Regulatory Reporting 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/agiprolabs/claude-trading-skills/tree/main/skills/regulatory-reporting
  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/agiprolabs/claude-trading-skills.git /tmp/claude-trading-skills
mkdir -p .claude/skills
cp -r /tmp/claude-trading-skills/skills/regulatory-reporting .claude/skills/regulatory-reporting
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Regulatory Reporting 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 Reporting 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 Reporting 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.

Regulatory Reporting

STATUS: STUB — This skill outlines planned capabilities for crypto tax and regulatory reporting. All generated output must be reviewed by a qualified tax professional before filing. Nothing in this skill constitutes tax or legal advice.

Overview

Track and generate required regulatory reports for cryptocurrency trading activity. Covers U.S. federal forms (IRS Form 8949, Schedule D), FinCEN foreign account reporting (FBAR), state-specific crypto obligations, large-transaction flagging, and deadline tracking.

Crypto tax reporting is complex and evolving. Rules change frequently, cost-basis methods vary by jurisdiction, and DeFi activities (swaps, LP positions, airdrops, staking rewards) have ambiguous treatment under current guidance. This skill provides a structured framework for organizing trade data into the formats regulators expect — but a tax professional must validate every filing.

Disclaimer

WARNING: This skill is for informational and educational purposes only. It does NOT constitute tax, legal, or financial advice. Cryptocurrency tax law is complex, jurisdiction-specific, and rapidly evolving. You MUST consult a qualified tax professional (CPA, EA, or tax attorney with crypto expertise) before relying on any output from this skill for actual tax filings. Errors in tax reporting can result in penalties, interest, and legal consequences. The authors accept no liability for any use of this material.

Current Status

This is a STUB skill. The code and references provided are starting points that demonstrate data structures and basic calculations. They have NOT been validated against current IRS guidance or any state tax authority requirements.

What Exists Now

  • Basic Form 8949 line-item generation from trade data (see scripts/form_8949_generator.py)
  • Regulatory requirements overview (see references/planned_features.md)
  • Demo mode with sample trade data

What Is Planned

  • Complete IRS Form 8949 and Schedule D PDF generation
  • FinCEN FBAR generation when foreign exchange accounts exceed $10,000
  • State-specific reporting requirement detection and templates
  • Reporting threshold tracking and deadline calendar
  • Large transaction flagging ($10,000+ cash-equivalent transactions)
  • Foreign account reporting requirements (FATCA Form 8938)
  • Wash sale detection and adjustment (where applicable)
  • Cost-basis method selection (FIFO, LIFO, Specific ID, HIFO)
  • DeFi-specific event classification (swaps, LP entry/exit, staking, airdrops)
  • Actual IRS-compatible CSV/PDF form data output

Prerequisites

bash
# No external dependencies for the demo script
python scripts/form_8949_generator.py --demo

For a production implementation, the following would be needed:

bash
uv pip install pandas reportlab  # PDF generation

Key Concepts

IRS Form 8949 — Sales and Dispositions of Capital Assets

Form 8949 reports each individual sale or disposition of a capital asset. For crypto, every trade, swap, or spending event is a taxable disposition. Key fields:

ColumnDescription
(a)Description of property (e.g., "2.5 BTC")
(b)Date acquired
(c)Date sold or disposed of
(d)Proceeds (sale price in USD)
(e)Cost or other basis
(f)Adjustment code (e.g., W for wash sale)
(g)Adjustment amount
(h)Gain or loss (d minus e, adjusted by g)

Transactions are split into Part I (short-term, held one year or less) and Part II (long-term, held more than one year).

Schedule D — Capital Gains and Losses

Schedule D aggregates the totals from Form 8949:

  • Line 1b/8b: Totals from Form 8949 Part I / Part II (basis reported to IRS)
  • Line 1c/8c: Totals where basis was NOT reported to IRS
  • Line 7/15: Net short-term / long-term capital gain or loss
  • Line 16: Combined net gain or loss

FinCEN FBAR (FinCEN Form 114)

Required when the aggregate value of foreign financial accounts exceeds $10,000 at any point during the calendar year. Crypto held on foreign exchanges (e.g., Binance for non-U.S. entities) may trigger this requirement — though IRS guidance on whether crypto accounts are "foreign financial accounts" remains evolving.

  • Filing deadline: April 15 (automatic extension to October 15)
  • Penalty for non-filing: Up to $12,500 per non-willful violation; up to $100,000 or 50% of account balance for willful violations

Large Transaction Reporting

Businesses receiving $10,000+ in cash (which may include crypto under recent guidance) must file IRS Form 8300 within 15 days. Individual traders generally do not file Form 8300, but exchanges may report large transactions.

Quick Start

python
"""Generate Form 8949 line items from trade history."""
from dataclasses import dataclass
from datetime import date
from decimal import Decimal

@dataclass
class Trade:
    asset: str
    quantity: Decimal
    date_acquired: date
    date_sold: date
    proceeds_usd: Decimal
    cost_basis_usd: Decimal

def classify_holding_period(trade: Trade) -> str:
    """Return 'short-term' or 'long-term' based on holding period."""
    holding_days = (trade.date_sold - trade.date_acquired).days
    return "short-term" if holding_days <= 365 else "long-term"

def compute_gain_loss(trade: Trade) -> Decimal:
    """Compute capital gain or loss for a single trade."""
    return trade.proceeds_usd - trade.cost_basis_usd

# Example
trade = Trade(
    asset="SOL",
    quantity=Decimal("10"),
    date_acquired=date(2025, 1, 15),
    date_sold=date(2025, 8, 20),
    proceeds_usd=Decimal("2500.00"),
    cost_basis_usd=Decimal("1800.00"),
)
gain = compute_gain_loss(trade)
period = classify_holding_period(trade)
print(f"{trade.asset}: {period} gain of ${gain}")
# SOL: short-term gain of $700.00

Use Cases

  1. End-of-year tax preparation — Export trade history from exchanges, generate Form 8949 line items, calculate Schedule D totals, and hand the organized data to your tax professional.

  2. Quarterly estimated tax tracking — Monitor cumulative realized gains throughout the year to estimate quarterly tax payments (IRS Form 1040-ES).

  3. FBAR threshold monitoring — Track aggregate balances across foreign exchange accounts to determine whether FBAR filing is required.

  4. Audit preparation — Maintain organized records of all dispositions with cost-basis documentation in case of an IRS inquiry.

  5. Multi-state filing — Identify state-specific crypto reporting obligations when trading from states with additional requirements.

Files

References

  • references/planned_features.md — Regulatory requirements overview, Form 8949/Schedule D field descriptions, FBAR thresholds, state requirements summary, and reporting deadlines

Scripts

  • scripts/form_8949_generator.py — Basic Form 8949 line-item generator from trade data with --demo mode; no external dependencies

Limitations

  • Not legal or tax advice. This is a software tool, not a tax professional.
  • U.S.-focused. International tax obligations are not covered.
  • Evolving rules. Crypto tax guidance changes frequently; this skill may not reflect the latest IRS notices or rulings.
  • No DeFi classification yet. Complex DeFi events (LP positions, yield farming, rebasing tokens) are not yet handled.
  • No wash sale certainty. Whether wash sale rules apply to crypto is unsettled; the skill flags potential wash sales but cannot make definitive determinations.
  • Cost-basis methods limited. Only FIFO is implemented in the demo; LIFO, HIFO, and Specific ID are planned.

Reporting Deadlines (U.S. Federal)

FormDeadlineExtension
Form 8949 / Schedule DApril 15October 15 (with Form 4868)
FinCEN FBAR (Form 114)April 15October 15 (automatic)
Form 830015 days after transactionNone
FATCA Form 8938With tax returnWith tax return extension
1040-ES (quarterly)Apr 15, Jun 15, Sep 15, Jan 15None

Contributing

This is a stub skill with significant room for expansion. Contributions welcome in these areas:

  • Additional cost-basis methods (LIFO, HIFO, Specific ID)
  • DeFi event classification (LP entry/exit, staking, airdrops, bridging)
  • State-specific requirement databases
  • Wash sale detection algorithms
  • PDF form generation (IRS-compatible output)
  • International tax jurisdiction support
  • Integration with exchange API export formats

All contributions must include appropriate disclaimers and must not provide specific tax advice. See the project CLAUDE.md for contribution guidelines.

Related Skills

  • portfolio-analytics — Portfolio performance tracking that feeds into tax reporting
  • trade-journal — Trade logging that can serve as source data for Form 8949

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 Reporting AI skill do?

[STUB] Regulatory report generation including IRS Form 8949, Schedule D, FinCEN FBAR, and state-specific crypto reporting requirements

Why use Regulatory Reporting on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agiprolabs/claude-trading-skills/tree/main/skills/regulatory-reporting. 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 Reporting?

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 Reporting?

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

Is the Regulatory Reporting AI skill free?

Yes. It is published on GitHub by agiprolabs under the MIT 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 👇