Decision Algorithm
v2.0.0EKB Decision Algorithm: Input any life decision and get structured analysis using Expected Value, Kelly Criterion, and Bayesian updating. Covers career, inve...
⭐ 1· 49·0 current·0 all-time
byLJ Li@truenorth-lj
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (EKB decision analysis) match the concrete behavior: a local Python calculator for EV/Kelly plus instructions to research fact-dependent cases. Requiring python3 and allowing WebSearch/WebFetch is appropriate for the stated purpose.
Instruction Scope
SKILL.md requires 'do your homework' and instructs the agent to use WebSearch/WebFetch for fact-dependent decisions (expected). It does not tell the agent to read arbitrary user files or access secrets. However, the declared allowed-tools list includes Read, Write, and Bash — more powerful capabilities than the core workflow strictly needs; this could enable filesystem or shell access if the agent is granted those tools, so consider whether you want to allow them.
Install Mechanism
No install spec (instruction-only) and a single local CLI tool (tools/decision_calculator.py). The Python script is self-contained, has no network calls, and is safe-looking; nothing is downloaded from external URLs.
Credentials
The skill requests no environment variables, credentials, or config paths. The operations described (web research + local calculations) do not require secrets, so the lack of credential requests is appropriate.
Persistence & Privilege
always:false (default) and the skill does not request system-wide configuration changes. It does not ask to modify other skills or agent settings.
Assessment
This skill appears coherent and low-risk: it uses a local Python calculator and asks the agent to fetch public data when needed. Before installing, review whether you want the agent to have filesystem or shell access — SKILL.md allows Read/Write/Bash which would let the agent run commands or write files; if you prefer tighter limits, disable Bash/Write for this skill. You should also avoid entering sensitive secrets or private credentials when asking the agent to research people/companies. If you want extra assurance, quickly inspect tools/decision_calculator.py (it's short and contains no networking or hidden behavior).Like a lobster shell, security has layers — review code before you run it.
latestvk97b1gvf1tbn0sher1s7nkyqg584sgh5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
Binspython3