Backtest Expert - Strategy Validation
v0.1.0Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies...
⭐ 0· 90·0 current·0 all-time
byRunByDaVinci@clawdiri-ai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (systematic backtesting guidance) matches the contents: methodology docs, checklists, and a local evaluation script. Nothing in the files requires unrelated credentials, binaries, or external services.
Instruction Scope
SKILL.md is a methodology guide and stays on-topic. It references a separate programmatic engine (einstein-research-backtest-engine) which is expected. Be aware that the repository includes a Python evaluator script and tests; importing that script (as the test fixture does) will execute its top-level code — in this package that code defines functions only, but you should still treat bundled scripts as executable code and review them before running.
Install Mechanism
No install spec and no downloads are present (instruction-only plus local scripts). This minimizes supply-chain risk; nothing is being fetched from remote URLs or installed automatically.
Credentials
The skill declares no required environment variables, no credentials, and no config paths. The files also do not attempt to read secrets or environment variables. This matches the stated non-networked, methodology nature of the skill.
Persistence & Privilege
Skill does not request always:true or any elevated persistence. It does not modify other skills or global config. Normal autonomous invocation is allowed but not excessive given the content.
Assessment
This skill appears coherent and non-malicious: it provides methodology docs and a local backtest-evaluation script. Before using it, do the following: (1) Review and run the unit tests in an isolated/sandboxed environment — the tests import and execute the Python file, so run them in a controlled environment. (2) Inspect/fix the small implementation bug in scripts/evaluate_backtest.py (the returned dict references calc_profit_fact but the function is named calc_profit_factor), which will cause runtime errors. (3) Confirm you provide your own historical data (the package states it does not include or fetch data). (4) If you plan to use or link the separate einstein-research-backtest-engine referenced in SKILL.md, verify that engine's provenance before connecting it. (5) As with any third-party code, avoid running it on sensitive systems or with production credentials; run preliminary checks in a throwaway VM or container.Like a lobster shell, security has layers — review code before you run it.
latestvk97d83y75b6dzhgah7h2tvw4md83dtz0
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
