- Home
- Skills
- Trading & Investing
- Trade Decision Audit — Check Thesis, Risk & Discipline
More screenshots
Works with the AI Agents you already use
Trade Decision Audit — Check Thesis, Risk & Discipline
Audit trade logic, position sizing, completed trades, and weekly discipline—without buy/sell signals or price predictions.
$7
Trade Decision Audit — Check Thesis, Risk & Discipline
Example session with this skill installed
Audit this pre-trade plan without recommending whether to buy: NVDA, long, entry 128.40, stop 121.80, target 145.00, intended size 150 shares, account 42,000 USD, max risk 1.5%. Thesis: earnings beat last week, price is above the 20-day moving average, sector momentum is strong, and traders are loading up before a conference. Invalidation: if it starts looking weak I'll get out.
- Read your context and instructions
- Compiled the trade decision audit
MODE: PRE-TRADE
EVIDENCE LIMIT: Thesis assertions are not corroborated by raw market data.
MISSING DATA: Slippage and objective time-exit assumptions are absent.
RISK MATH: R:R 2.515; implied breakeven win rate 28.45%; maximum size 95.45 shares. Intended size risks 990 USD, or 2.357% of the account, breaching the stated 1.5% rule.
VERDICT: 41/100 - material process gaps. A low score does not predict a loss.
ONE RULE UPDATE: Before entry, record one objective invalidation condition that can be evaluated without interpretation.
PORTABLE RECORD: PRE_TRADE_DECISION with supplied values, score, rule update, and blocked calculations.
BOUNDARY: Process and risk-structure audit only; no buy, sell, or hold recommendation.
Connects securely to your tools. The creator never sees your data.
About this skill
Audit the decision before the market grades the outcome
Trade Decision Audit helps traders test whether a planned trade is logically and mathematically ready, then review completed trades without confusing profit with good process.
It does not tell you what to buy or sell. It turns the information you provide into a structured decision record with explicit evidence gaps, deterministic risk math, and one concrete process improvement.
What you get
- Pre-trade audit: thesis evidence, invalidation clarity, hidden assumptions, failure paths, risk-to-reward, and maximum position size.
- Post-trade audit: decision quality separated from P&L, rule divergence, realized R, and execution lessons.
- Portfolio review: concentration math plus clearly labeled qualitative factor-overlap analysis.
- Weekly review: repeated process patterns condensed into exactly one observable rule experiment.
- Portable records: structured outputs that can feed the next review instead of disappearing into chat history.
Why this is different
- Risk, sizing, realized-R, expectancy, HHI, and drawdown calculations use the bundled deterministic Python script.
- Missing prices, volatility, correlations, or regime data remain visible gaps; the skill does not invent them.
- A profitable rule breach can still receive a poor process verdict.
- The final output distinguishes supplied facts, calculations, inference, and unresolved uncertainty.
- No broker connection, credentials, live market feed, or order execution is required.
Worked example
A plan risks 2.36% of a $10,000 account when the stated rule permits 1.5%. The audit calculates a maximum size of 95.45 shares, preserves the unsupported crowd claim as an evidence gap, and converts a vague stop idea into one objective invalidation rule. The result is an auditable decision record—not a prediction.
Built for a trading workflow
Use it independently or as the decision-quality layer in the future Trader Operating System bundle. Market-context claims belong in Market Evidence Checker; claim-to-source lineage belongs in the planned Trade Decision Provenance Auditor.
Boundaries
- No buy, sell, or hold recommendations.
- No signals, forecasts, live prices, or automated orders.
- No broker or exchange connection.
- Portfolio shock values require a user-supplied scenario assumption.
- Portable records are returned as text and are not stored automatically.
- Local Python is required for deterministic arithmetic.
Does not provide buy, sell, or hold recommendations; signals, forecasts, live prices, automated orders, or broker/exchange connections. Qualitative factor clusters remain inference unless supported by user-supplied data. Numeric portfolio shocks require a user-supplied scenario assumption. Portable records are returned as text and are not stored automatically. Requires local Python execution for deterministic arithmetic.
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 any payment.
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 3 months ago
Permissions
Terminal / Shell is used only to run the bundled scripts/risk_math.py for deterministic calculations. No browser, network, external file read/write, or environment-variable access.