Quant Full Stack
v1.0.0Complete A-share quantitative stock trading workflow covering data collection, factor analysis, strategy development, backtesting, simulated trading, and ris...
⭐ 0· 151·2 current·2 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description (quant full-stack workflow) align with the provided files: SKILL.md documents tasks and runner.py launches local task scripts. No unrelated credentials, binaries, or external services are requested.
Instruction Scope
SKILL.md limits work to the six quant modules and points at runner.py. The runner executes Python scripts located under ~/quant_trading using the project's virtualenv and returns their stdout/stderr. This is expected for a local project runner, but it means whatever scripts exist in ~/quant_trading will be executed and their output returned.
Install Mechanism
No install spec is provided (instruction-only with a small helper script). Nothing is downloaded or written by the skill itself.
Credentials
The skill declares no required env vars or credentials. It does read the current user's home to locate ~/quant_trading and its virtualenv, which is proportional to its purpose.
Persistence & Privilege
always is false and the skill doesn't modify other skills or system settings. It can be invoked autonomously (platform default) but requests no extra privileges.
Assessment
This skill is a wrapper that runs Python scripts from ~/quant_trading using ~/quant_trading/venv/bin/python3. Before using it, inspect the scripts in that directory and the virtualenv to ensure they are trustworthy (they will be executed and their stdout/stderr returned). The runner times out after 2 minutes per invocation. If you don't have the project path or virtualenv set up, the runner will fail. Although the skill requests no credentials, be cautious: outputs from executed scripts could include sensitive data, so audit the project for secrets or unintended network calls before running.Like a lobster shell, security has layers — review code before you run it.
latestvk97cb3apxtvxpdyvz99vttxkzd835hty
License
MIT-0
Free to use, modify, and redistribute. No attribution required.