recipe-eval-prompt

SKILLWorkflowcommunity
v0.0.0shinprMITUpdated 1mo agoSource →

Compares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
17Repo stars
1Clients
1Formats
1mo agoLast update
Skill
Authorshinpr
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor—
Copilot—
ChatGPT—
Gemini—
About

Compares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.

Keywords
skillclaude

No dependency coverage

This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.