Skip to content
SkillScript-led2,505 tokens in use

MT5 Robot Tester

A Python pipeline that drives the MetaTrader 5 Strategy Tester headless through three rounds, moving Expert Advisors between folders and writing a leaderboard of finalists.

7,428 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/mt5-robot-tester

Skill label

measured from its files

What installing MT5 Robot Tester costs

111tokens idle
2,505tokens in use
4,913tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/dashboard.py, scripts/mt5_batch_tester.py, scripts/mt5_common.py, scripts/mt5_learnings.py, scripts/parse_mt5_optimization.py, scripts/parse_mt5_report.py.

Touches

shelldetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples15/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Good
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 91
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/dashboard.py, line 219
  • Hidden characters−20

    characters that render as nothing or reorder the text

    scripts/mt5_common.py, line 206

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community68
  • Maturity36
  • Momentum40

MT5 Robot Tester screens a folder of MetaTrader 5 Expert Advisors that have not been backtested yet. A Python script builds tester configuration files, launches terminal64.exe from the command line, parses the reports, and moves each robot between candidates, in-testing and finalists folders.

Round one backtests the robot on every configured symbol, round two backtests the best symbol, and round three optimizes the inputs one at a time. Runs are checkpointed and can be resumed. It needs Windows and MetaTrader 5 at run time, and it reports test statistics without advising anyone to trade.

What You Get

  • A leaderboard in JSON and Markdown with verdict, best symbol, profit, drawdown and LR correlation per robot
  • Finalist robots copied to a finalists folder together with their optimized .set files
  • A resumable run with state.json and run.log checkpoints after every step
  • A learnings file that records which parameters and symbols paid off so later loops reorder their work
  • An optional localhost HTML control panel showing each robot’s phase and verdict

Common Use Cases

  • Batch testing a folder of untested Expert Advisors across a Market Watch symbol list
  • Optimizing the inputs of a robot one parameter at a time and comparing against its baseline
  • Resuming an interrupted multi-day test run without repeating finished rounds
  • Dry-running the generated tester INI files before committing to a long real-tick run

What Makes It Unique

It treats the Strategy Tester as a pipeline with gates and a memory. Robots move between folders as they advance, runs resume only when the config, binary and .set fingerprints still match, and incomplete or unparsable reports never reject or promote a candidate. A learnings store reorders later optimization toward the parameters that helped before. The terminal path is never auto-discovered unless you opt in, which protects a live broker terminal on the same machine.

Under The Hood

The skill runs Python scripts that write INI files, start terminal64.exe on Windows with the tester settings, wait for it, and read the HTML or XML reports it produces. It moves and copies Expert Advisor files between the candidates, in-testing and finalists folders and writes reports, state, logs and learnings under an output folder. The optional dashboard script starts a small web server on localhost only, protected by a per-server token. Closing the terminal at the end of each run is part of the setup, so use a portable tester-only install. It uses only the Python standard library and calls no external API.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers