research-loop

SKILLWorkflowcommunity
v0.0.0EmlembowMITUpdated 3d agoSource →

Run autonomous, metric-driven experiments on a version-controlled implementation against a fixed evaluation harness. Use when the user asks to improve eval pass rate, benchmark score, prompt or policy quality, performance, cost, or another measurable outcome through repeated hypothesis, change, eval

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
2Repo stars
1Clients
1Formats
3d agoLast update
Skill
AuthorEmlembow
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

Run autonomous, metric-driven experiments on a version-controlled implementation against a fixed evaluation harness. Use when the user asks to improve eval pass rate, benchmark score, prompt or policy quality, performance, cost, or another measurable outcome through repeated hypothesis, change, evaluate, keep-or-discard cycles. Protect generalization with holdout gates and reject hardcoded cases,

Keywords
skillclaude