agentleFS
Sign inStart free
cecewu3cecewu3/agent-trading-skills/skills/trade-report/SKILL.md

trade-report

Skill0 starsChanged 14 days agoMITView on GitHub

Generate a human-readable session or daily report from positions and trade logs (fills, PnL, open risk, skips). Use when the user asks for a daily summary, PnL report, what happened today, or implementing report.py. Trigger phrases: "trading report", "daily PnL", "summarize trades", "what did the bot do".

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read bot state (paths.positions_file, paths.trades_log) and produce a markdown or JSON report for a date (default: today in …

    line 15
  2. Distinctive:

    After a manual cycle

    line 20
  3. Very specific:

    Write under paths.report_dir and print a short summary.

    line 33
  4. Distinctive:

    Never include API keys, secrets, or full account balances beyond bot-tracked positions unless the user asks.

    line 34
  5. Distinctive:

    Do not give investment advice in the report footer beyond restating that past cycle results are not predictive

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Trade report

Overview

Read bot state (paths.positions_file, paths.trades_log) and produce a markdown or JSON report for a date (default: today in schedule.timezone). No API keys required for log-only reports; optional live marks via public ticker.

When to use

  • End of day / session
  • After a manual cycle
  • Auditing behavior before going live

Instructions

  1. Parse data/trades.log (or configured path) for the target date.
  2. Load open positions; mark with last price if available.
  3. Summarize:
    • Buys / sells count and quote volume
    • Realized PnL (fees if logged)
    • Unrealized PnL for open positions
    • Skips / ASK_USER counts if logged
    • Cap utilization vs risk.max_total_cost_quote (show config key, not a hardcoded number)
  4. Write under paths.report_dir and print a short summary.
  5. Never include API keys, secrets, or full account balances beyond bot-tracked positions unless the user asks.

Suggested CLI

python report.py                  # today in schedule.timezone
python report.py YYYY-MM-DD
python report.py --json

Failure handling

  • Missing log file → empty report with warning
  • Corrupt line → skip line, count errors

Guidelines

  • Reports are for the operator; keep tone factual
  • Do not give investment advice in the report footer beyond restating that past cycle results are not predictive

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free