Skip to content
SkillScript-led1,462 tokens in use

manifoldbt Backtester

Runs a declarative strategy spec over OHLCV bars with the manifoldbt engine and produces the eight measured inputs the backtest-expert skill scores.

7,427 stars on the repository MIT Licensetradermonty/claude-trading-skills · skills/manifoldbt-backtester

Skill label

measured from its files

What installing manifoldbt Backtester costs

93tokens idle
1,462tokens in use
3,583tokens, 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/bridge.py, scripts/round_trips.py, scripts/run_backtest.py, scripts/spec.py.

Touches

shelldetectednetworkdetectedwrites 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 →
Good
  • Frontmatter12/15
  • Structure14/25
  • Examples9/15
  • Output10/15
  • Size13/15
  • Resources12/15

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 68
  • Reaches the network−10

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

    scripts/run_backtest.py, line 124
  • Writes files−8

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

    scripts/run_backtest.py, line 210

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

manifoldbt Backtester executes a simple strategy rule over bars from a CSV or Parquet file, using SMA, EMA or RSI indicators, one entry condition, optional stop-loss and take-profit, and fees and slippage in basis points.

It pairs the engine’s fills into round trips and reports win rate, average win, average loss, maximum drawdown and parameter count, with warnings for small samples or missing costs. It then prints a command to hand the figures to backtest-expert. It measures a rule on past data and gives no investment advice.

What You Get

  • A validated strategy spec with its parameter count
  • Win rate, average win, average loss, maximum drawdown and trade count from real bars
  • Warnings for fewer than 30 trades, a span under a year, no friction or mismatched win rates
  • An optional JSON result file
  • A ready-to-paste command for the backtest-expert evaluator

Common Use Cases

  • Measuring a one-sentence moving-average or RSI rule on your own price data
  • Getting real numbers before asking backtest-expert for a score
  • Checking how fees and slippage change a short-holding-period edge
  • Finding out how many parameters a strategy spec carries

What Makes It Unique

The skill documents four conversions that fail without an error: fills versus round trips, buy and sell alternation, costs on small trades and the sign of drawdown. It stops the handoff when there are no completed round trips, when drawdown is missing or when scratch trades are present, and it refuses shapes it cannot handle, such as shorting or multi-condition entries.

Under The Hood

Claude writes the spec file and runs Python scripts from the skill folder through the shell: run_backtest.py reads your data file and spec, validates the spec first and calls the manifoldbt engine, which you install with pip. It makes no network calls of its own and needs no API key. It can write a JSON result file and prints the evaluator command. Helper modules for validation, round trips and the metric bridge have no dependencies, and two reference files describe the spec fields and the conversions.

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