autoresearch
Run bounded automated experiment iterations by recording baselines, applying hypothesis patches, comparing metrics, protecting regression guards, and deciding keep, discard, rollback, or block. Use when $autoresearch is named or a repo/skill needs evidence-backed research, metric tracking, or safe optimisation loops.
69
Quality
85%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Securityby
Passed
No known issues
Loading evals
- Repository
- jscraik/Agent-Skills
- Commit
8e7e19d
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.