BF nautilus-trader
How to use the NautilusTrader algorithmic trading platform for data conversion, strategy development, backtesting, paper trading (sandbox), and live trading. Use this skill whenever the user wants to build or run a quantitative trading strategy with nautilus_trader, convert market data for backtesting, set up a backtest engine, run a sandbox/paper-trading session, connect to a live exchange or broker, or generate performance reports and tearsheets. Also use it when the user mentions NautilusTrader, trading strategies, backtesting frameworks, or connecting to exchanges like Binance, Bybit, Interactive Brokers, etc.
As a process F 51/100 · Will not run — References files that are not bundled: examples/backtest/fx_ema_cross_audusd_ticks.py, examples/backtest/fx_ema_cross_bracket_gbpusd_bars_external.py, examples/sandbox/binance_futures_testnet_sandbox.py
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 3
✓ No critical or high findings
Medium and low: 3
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:56Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl https://sh.rustup.rs -sSf | sh -s -- -y
security skill -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:60Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl https://sh.rustup.rs -sSf | sh -s -- -y
security skill -
low Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:70Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)curl -LsSf https://astral.sh/uv/install.sh | sh
security skill
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: examples/backtest/fx_ema_cross_audusd_ticks.py - warning
missing-refreference to a missing file: examples/backtest/fx_ema_cross_bracket_gbpusd_bars_external.py - warning
missing-refreference to a missing file: examples/sandbox/binance_futures_testnet_sandbox.py - warning
missing-refreference to a missing file: examples/live/binance/binance_spot_ema_cross_bracket_algo.py - warning
missing-refreference to a missing file: examples/data_conversion/if_data_converter.py
Process rating: all ten parameters 51/100
- 0Tools and files. 5 referenced file(s) missing: examples/backtest/fx_ema_cross_audusd_ticks.py, examples/backtest/fx_ema_cross_bracket_gbpusd_bars_external.py, examples/sandbox/binance_futures_testnet_sandbox.py
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (nautilus-trader) differs from the folder (nautilus-trader-pro)
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 27 steps
- 100Execution cost. Instruction body is 2695 tokens
- 100Running it twice. Mutating operations check current state
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 621: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.