ab

SKILLWorkflowcommunity
v0.0.0CodeShuXMITUpdated 3mo agoSource →

Run an A/B test of the same task at multiple model tiers (Haiku, Sonnet, optionally Opus). Captures outputs, computes structural and semantic diffs, scores quality, writes a markdown comparison report. Use when the user wants to validate "is Haiku good enough for this task class?" or runs /tokenwise

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

Run an A/B test of the same task at multiple model tiers (Haiku, Sonnet, optionally Opus). Captures outputs, computes structural and semantic diffs, scores quality, writes a markdown comparison report. Use when the user wants to validate "is Haiku good enough for this task class?" or runs /tokenwise:ab "<task description>".

Keywords
skillclaude