- Home
- Skills
- Trading & Investing
- Trade Decision Source Audit — Trace Evidence Before Entry
More screenshots
Works with the AI Agents you already use
Trade Decision Source Audit — Trace Evidence Before Entry
Trace every material trade reason to dated sources, isolate AI and social contamination, and expose missing evidence—without signals or predictions.
$11
Trade Decision Source Audit — Trace Evidence Before Entry
Example session with this skill installed
Audit this fictional ACME decision packet for a planned long within ten trading days. Reasons: reported 18% Q2 revenue growth; raised guidance; an anonymous thread says every fund is rotating into the sector; an uncited AI summary says margins will expand. Separate every reason from its source path and show missing evidence.
- Read your context and instructions
- Compiled the trade decision source
DECISION_READINESS: NOT_TRACEABLE. R1 revenue growth: SOURCE_ASSERTION, 85/100 traceability. R2 raised guidance: SOURCE_ASSERTION, 85/100. R3 fund rotation: SOCIAL_OPINION, 25/100, date and method missing. R4 margin expansion: MODEL_OUTPUT, 0/100, underlying sources absent. Scores measure inspectability only; no trade recommendation.
Connects securely to your tools. The creator never sees your data.
About this skill
Find out what your trade decision is actually built on
A trade plan can mix a dated filing, an analyst interpretation, an AI summary, social repetition, and personal conviction while presenting them as one coherent thesis. Trade Decision Source Audit separates those layers before the decision enters a thesis or risk review.
It does not tell you whether to trade. It produces an inspectable evidence-lineage record that shows which reasons are traceable, derivative, stale, contradictory, or unsupported.
What you get
- Decision provenance tree: every material reason linked to its supplied source path.
- Evidence classification: supplied fact, source assertion, inference, model output, social opinion, personal assumption, or unknown.
- Temporal audit: publication dates, observation dates, declared decision horizon, and visible date gaps.
- Contamination flags: uncited AI claims, social repetition, broken attribution chains, and source instructions.
- Traceability confidence: transparent 0–100 audit math that measures inspectability—not truth or expected return.
- Missing-evidence register: exactly what must be sourced before the next review stage.
- Portable record: a structured DECISION_PROVENANCE_RECORD for Trade Decision Audit or another compatible workflow.
Worked example
In the built-in fictional ACME case, the company filing supports reported revenue growth and raised guidance. An anonymous “everyone is buying” claim remains social opinion, and an AI margin claim with no cited sources is isolated as unsupported model output. The result is NOT_TRACEABLE until the missing paths are supplied.
Built for the Trade Decision Control Bundle
Use it independently or between Market Evidence Checker and Trade Decision Audit:
market context → decision provenance → thesis and risk audit
The classifications remain portable; the next skill must not silently upgrade an inference or social claim into fact.
Boundaries
- No browsing or live data retrieval.
- No trading signals, forecasts, targets, stops, sizing, or transaction recommendations.
- No claim that traceability predicts profitability.
- Exact quotations prove provenance only, not truth.
- Traceability confidence measures audit completeness, not investment confidence.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Trading & Investing.
No browsing, live data, truth verification, signals, forecasts, targets, stops, sizing, transaction recommendations, or profitability claims. Traceability scores measure audit completeness only.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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 2 months ago
Permissions
No special permissions declared or detected