agentsclimarketplace

Daily pnl reviewer

Skill rahulcommercial/claude-code-for-indian-traders/skills/daily-pnl-reviewer

Claude Code skills for Indian retail traders — Zerodha Kite, NSE option chains, paper trading, and EOD review.

Install
npx -y skills add rahulcommercial/claude-code-for-indian-traders --skill daily-pnl-reviewer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

End-of-day review skill for Indian intraday traders — analyses today's trades, computes win rate / expectancy / max DD, flags behavioural patterns (revenge trading, oversizing, time-of-day skew), and writes a journal entry. Trigger after market close, when reviewing trade logs, or when user says "review my day".

SKILL.md

2.4 KB, as published. Nobody here has run it

Daily P&L Reviewer

The trade is only half the work. The review is where edge gets built.

When to use

  • After 15:30 IST when market is closed.
  • User uploads / points to today's trade log (JSON / CSV / SQLite).
  • User asks "how did I do today" or "review my trades".

Inputs expected

A list of trades with at minimum:

  • entry_time, exit_time
  • instrument, side, qty
  • entry_price, exit_price
  • pnl (₹)
  • rationale / setup tag (optional but valuable)

Metrics to compute

Performance

  • Net P&L (after estimated STT + brokerage + GST)
  • Win rate = wins / total
  • Avg win, avg loss, expectancy = (win_rate × avg_win) − (loss_rate × avg_loss)
  • Profit factor = total wins ₹ / total losses ₹

Risk

  • Max intraday drawdown
  • Largest single loss as % of starting capital
  • Did daily loss cap trigger?

Behavioural flags (these matter more than P&L)

FlagHow to detect
Revenge tradingNew entry within 5 min of a losing exit, larger size than baseline
OversizingPosition size > 2× median for the day
Late-day chasingNew entries after 14:45 IST that aren't part of a closing-bell setup
Setup driftTrades without a tagged setup, or "vibe" entries
Holding losersAvg time-in-loss > 1.5× avg time-in-win

Output: the journal entry

Write to ~/projects/zerodha-signal-app/journal/YYYY-MM-DD.md (or user-specified path):

# 2026-06-06 — Trading Journal

## Numbers
- Net P&L: ₹+2,340 (2.3% on ₹1L)
- Trades: 6 (4W / 2L), win rate 67%
- Expectancy: ₹+390 / trade
- Max DD: ₹-1,100 at 11:42 IST

## What worked
- 09:30 ORB on BankNifty — clean, on-plan, sized right.

## What didn't
- 13:15 CE buy on Nifty — entered without OI confirmation, exited for -₹600.

## Behavioural flags
- ⚠ Revenge entry at 13:25 (within 5 min of loss). Recovered, but pattern noted.

## Tomorrow's focus
- Don't enter inside 12:30–13:30 chop unless setup is A+.

Tone

Honest, blunt, no pep talk. Treat the user as an adult building a process.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.