- Home
- Skills
- Trading & Investing
- Alpha Reality Check — Strategy Results Auditor
Alpha Reality Check — Strategy Results Auditor
Audits closed-trade CSVs and returns a deterministic CONTINUE / WATCH / PAUSE / REJECT verdict with evidence: expectancy decay, concentration, backtest-to-live gaps and a bootstrap PnL check.
$1
Works with the AI Agents you already use
Alpha Reality Check — Strategy Results Auditor
Example session with this skill installed
Audit my closed-trades CSV (trades.csv, 214 closed trades, backtest and live) and tell me whether I should keep trading this strategy.
- Read your context and instructions
- Compiled the alpha reality check
- Generated the data export
Verdict: WATCH
Alpha Reality Check audited 214 closed trades from trades.csv (backtest and live). The strategy is not rejected, but it is not cleared to continue unchanged either — recent performance has weakened and results depend on a small number of winners.
Evidence
- Expectancy decay: recent expectancy is materially lower than the full-history expectancy. The most recent 50 trades contribute far less per trade than the earlier history, so the edge is fading rather than stable.
- Winner concentration: a small share of trades accounts for most of the total profit. Removing the top few winners would materially change the result, so the outcome is fragile.
- Symbol concentration: profit is concentrated in a small number of symbols. The strategy has not demonstrated the same edge broadly across the symbols it trades.
- Backtest-to-live gap: live expectancy is below backtest expectancy. The degradation is consistent with a strategy that looked stronger in backtest than it performs live.
- Bootstrap check: the bootstrap estimate for mean trade PnL is positive, but the lower bound is close to zero, so the positive edge is not strong.
What to do next
Keep trading at reduced size, monitor the next 50 trades, and re-audit before increasing size. If expectancy decay continues or the bootstrap lower bound turns negative, move to PAUSE. This is an audit of past results, not investment advice, and it generates no signals and executes no trades.
trades.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Alpha Reality Check audits the trading results you already have. Feed it a CSV of closed trades (backtest, paper, or live) and it returns a deterministic CONTINUE / WATCH / PAUSE / REJECT verdict with the evidence behind it: expectancy decay (recent vs history), winner and symbol concentration, backtest-to-live degradation gaps, and a bootstrap estimate that mean trade PnL is positive. It is not a backtester: it generates no signals, fetches no market data, connects to no exchange, and executes no trades. Runs fully locally inside your agent; your trade data never leaves your machine. The reference policy is transparent and tunable via YAML. Not investment advice.
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.
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 today
- Software
Python