📚 resourceStalePromisingmedium

example-scripts

by numerai

A collection of scripts and notebooks to help you get started quickly.

Stars

1.1k

Skill Type

🏗️ Code Scaffolding & Templates

Quality Score

87/200

License

MIT

Forks

307

Last Updated

Jul 24, 2026

Discovered

Mar 27, 2026

Validation

Passed

github.com/numerai/example-scripts

Quality Breakdown

87/ 200

Content Signals

Gotchas/Edge Cases+40
Progressive Disclosure+30
Trigger Description+20
Verification/Safety+20
Code Examples+15
Composability+15

Repo Health

Recent Activity+15
Scripts/Automation+10
Real Usage (Issues)+10
Single Responsibility+10
Config/Persistence+10
Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Stale

No commits in 90-365 days and no tagged releases.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • README contains instruction to execute remote shell script via curl: 'curl -sL http://numer.ai/install-mcp.sh | bash' - this downloads and executes untrusted code
  • Repository includes agent skills framework (numerai/agents/skills/) that could enable autonomous multi-agent orchestration
  • AGENTS.md and agent skill definitions suggest potential for spawning sub-agents without explicit human approval gates
  • CLI utilities and model factory patterns present that could enable dynamic code execution
  • Agent framework appears designed for autonomous operation ('AI scientist') with example showing '--yolo' flag suggesting reduced safety guardrails