Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+20 more

    trading decision evidence manifest

    1

    Generate hash-linked evidence manifests for trading decisions, model versions, and audit trails.

    $15

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    0 installsSecurity scanned
    trading decision evidence manifest

    trading decision evidence manifest

    Example session with this skill installed

    Generate a decision manifest for the last three EUR/USD scalp trades. Include model v2.1.4, the market data hashes, and the manual risk override on the second trade.

    • Read your context and instructions
    • Compiled the trading decision evidence
    • Generated the document

    I have processed the trade logs and generated a linked decision manifest. The chain starts with a null previous hash and anchors the three events using SHA-256 canonicalization.

    Trading Decision Replay Manifest

    Event IDTimestamp (UTC)Model VersionDecision TypeHash StatusReviewer
    TX-99012023-10-27 09:15:02strat-scalp-v2.1.4Auto-ExecuteVALIDSystem
    TX-99022023-10-27 09:16:45strat-scalp-v2.1.4Manual OverrideVALIDj.doe_risk
    TX-99032023-10-27 09:18:10strat-scalp-v2.1.4Auto-ExecuteVALIDSystem
    {
  "manifest_version": "1.0.2",
  "chain_head": "8f3b2a...e41c",
  "records": [
    {
      "record_id": "TX-9901",
      "previous_hash": null,
      "source_refs": ["md_eurusd_915.csv"],
      "model_metadata": { "version": "2.1.4", "checksum": "a1b2c3" },
      "record_hash": "3d4e5f...6g7h"
    },
    {
      "record_id": "TX-9902",
      "previous_hash": "3d4e5f...6g7h",
      "source_refs": ["md_eurusd_916.csv"],
      "override_note": "Risk limit adjustment - volatility spike",
      "record_hash": "2a9b8c...d7e6"
    },
    {
      "record_id": "TX-9903",
      "previous_hash": "2a9b8c...d7e6",
      "source_refs": ["md_eurusd_918.csv"],
      "record_hash": "8f3b2a...e41c"
    }
  ]
}

    Next steps

    1. Export this JSON manifest to your access-controlled audit storage.
    2. Verify the source_refs files exist in your local data lake to ensure replay capability.
    3. Anchor the chain_head hash in your firm's immutable log service.

    trading-decision-evidence-manifest.pdf

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    What you get

    Create verifiable audit trails for regulatory compliance reporting.Link specific model versions to execution outcomes for performance analysis.Document manual risk overrides with cryptographic pointers to market state.Generate replay manifests to debug algorithmic trading errors.

    About this skill

    The problem

    Trading desks struggle to prove the integrity of algorithmic decisions during audits. It is difficult to reconstruct the exact model version, data inputs, and human overrides that led to a specific execution.

    What it does

    • Generates linked decision-record hashes to create a verifiable chronology of trading actions.
    • Maps model versions, strategy metadata, and reviewer actions to specific execution events.
    • Identifies gaps in evidence by checking source file availability and hash consistency.
    • Produces a replay manifest for reconstructing trade logic in isolated environments.
    • Redacts sensitive metadata while maintaining the integrity of the decision chain.

    Why this beats prompting it yourself

    General-purpose LLMs lack the strict schema enforcement required for cryptographic chaining and audit readiness. This skill ensures canonicalization of trading metadata, preventing "hallucinated" event sequences that would fail a compliance review.

    Use cases

    • Generating audit-ready evidence for regulatory inquiries.
    • Post-mortem analysis of algorithmic slippage or unexpected strategy behavior.
    • Establishing a secure chain of custody for human-in-the-loop trade approvals.

    Known limitations

    Local hash-linked metadata only. No native digital signatures, immutable storage anchoring, or automatic PII redaction. Requires manual mapping of external data exports.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 13 days ago

    • Passed all security checks, Safe to install

    Listed13 days ago

    What's inside

    Frequently Asked Questions