Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    TM Scenario Test Designer

    1

    Turn a TM rule or public typology into a portable test pack: rule contract, CSV fixtures, JSON expectations and a review report, with optional live research.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    TM Scenario Test Designer

    TM Scenario Test Designer

    Example session with this skill installed

    Design tests for a POST-ALERT fan-in rule: at least 3 distinct counterparties and
    at least 10,000 integer minor units, in a rolling interval (T-1h, T], posted inbound
    payments only, grouped separately by account/currency. Show exact boundary cases,
    synthetic fixtures and expected outputs. List any missing contract decisions.

    • Read your context and instructions
    • Compiled the tm scenario test

    DESIGNED, not executed against your system:

    • Exact amount/count thresholds: 3,000 + 3,000 + 4,000 from three distinct parties
      in one qualifying account/currency group => one alert, total 10,000, count 3.
    • Reduce last payment to 3,999 => no alert, total below threshold.
    • Replace the third party with the second => no alert, only two distinct parties.
    • Move a required payment to exactly T-1h => no alert, lower endpoint excluded.
    • Missing deduplication or suppression policy => affected expectations conditional.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Design reviewable tests for rule-based transaction monitoring before mistaking a passing example for a tested rule. This skill helps an AI agent extract the rule contract, expose unspecified behavior and build small cases that distinguish intended logic from plausible implementation bugs.

    Use it for fan-in/fan-out, rolling amounts and counts, pass-through matching, structuring-like scenarios and stateful alert behavior. It separates intended requirements from observed code and conditional assumptions. It covers threshold boundaries, time-window endpoints, currency/entity isolation, distinct parties, duplicates, reversals, information availability and legitimate look-alikes.

    Included:

    • Agent instructions and reusable rule-contract and test-matrix templates.
    • Rule-family test patterns and evaluation/leakage guidance.
    • One worked, fictional fan-in contract with 30 synthetic test cases and exact expected alerts or validation errors.
    • An optional Python standard-library demo checker that detects four deliberately introduced logic mutations. This checks the bundled example, not your system.

    Design-only use needs a text-capable AI agent and supplied rule evidence. Optional demo execution needs shell/local file access and Python 3.11+. No API keys, special external services or Python packages are required. The skill is delivered through Agensi's agent connection, with supporting files loaded as needed.

    Version 1.1.0 is an early release. Synthetic demo checks are available; external customer pilots and measured productivity gains are not established. Generated cases require owner review. This is not a production detector, calibration service, customer-system adapter, legal opinion or regulatory approval.

    Use approved material in your organization's permitted AI environment. No employer/customer documents are bundled. AI/model usage costs are separate.

    Version 1.1.0 — now live

    Version 1.1.0 is approved and live. This update adds:

    • Portable test packs: Markdown contract/review, CSV test matrix and synthetic transactions, JSON expectations, hashes and optional ZIP.
    • A dependency-free local Python builder that checks structure and references, without claiming to execute your detector.
    • Optional public-source typology research through Agensi Exa. Source facts remain separate from proposed detector mechanics. Supplied-rule mode skips research.
    • A second fictional pass-through example with 20 cases and five deliberately faulty variants detected.

    File/ZIP generation was verified in a Codex local workflow with Python 3.14 and 3.15. Other clients are unverified; text-only clients receive named file contents. Optional research tool charges are separate from the USD 12 skill price, quoted before use, and need an Agensi balance but no provider API keys. PACK_VALID is a structural check; customer execution stays NOT_RUN until actually performed. External customer pilots and measured time savings are not established.

    For a free documentation example, try BEAR Model Doc Writer.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Finance & Accounting.

    Early release. Synthetic examples check one fictional contract only; no customer-system adapter, production effectiveness, legal approval or measured productivity claim. Owner review required.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed today

    Nothing to install. It runs in your AI agent.

    Optional
    Python 3.11+

    Design-only mode needs no install. Files/ZIP need local shell, file access and Python 3.11+ (tested 3.14/3.15). Optional research is charged separately from the skill, quoted before use, and uses only public inputs.

    Permissions

    Terminal / Shell
    Listedtoday

    What's inside

    Frequently Asked Questions

    Turn a TM rule or public typology into a portable test pack: rule contract, CSV fixtures, JSON expectations and a review report, with optional live research.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use TM Scenario Test Designer on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in Finance & Accounting