Skill of Skills
📚 resourceStalePromisingcritical

AI-Scientist-v2

by SakanaAI

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Stars

6.6k

Skill Type

📖 Library & API Reference

Quality Score

94/200

License

Not specified

Forks

897

Last Updated

Jul 25, 2026

Discovered

Apr 5, 2026

Validation

Passed

github.com/SakanaAI/AI-Scientist-v2

Quality Breakdown

94/ 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

critical

Manual security review required. Use with extreme caution.

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

  • Executes LLM-generated code autonomously without human approval gates - README explicitly warns about this capability
  • Contains agent_manager.py and parallel_agent.py indicating multi-agent spawning and orchestration
  • Interpreter module (treesearch/interpreter.py) suggests arbitrary code execution capabilities
  • Autonomous experiment execution without human oversight - system runs full scientific workflows independently
  • LLM backends (Anthropic, OpenAI) integrated with code execution pipelines
  • System generates and executes Python scripts as part of scientific discovery process