Compare original and distilled prompts to verify lossless distillation.
npx skills add https://github.com/charly-vibes/wai --skill verify-prompt
Please help me install this Agent Skill. Skill: verify-prompt Source: https://github.com/charly-vibes/wai/tree/main/.agents/skills/verify-prompt Command: npx skills add https://github.com/charly-vibes/wai --skill verify-prompt
This Skill ensures that concise prompts used for LLMs accurately and completely reflect the original, more verbose prompts intended for developers, preventing loss of critical instructions or meaning.
Use the verify-prompt skill to compare the original and distilled versions of the summarization prompt.
High-intent search queries and answers about installing and using this skill.
To verify prompt distillation accuracy, compare the original verbose prompt against the distilled concise version to ensure all essential executable instructions, steps, and constraints are preserved without altering meaning.
Prompt distillation is refining a complex developer prompt into a concise version. You check it to prevent the loss of critical instructions or meaning when preparing prompts for LLMs.
To check for lost constraints, analyze the completeness, accuracy, and conciseness of the distilled prompt against the original to confirm no essential instructions were accidentally removed.
No specific frameworks are required. You can compare original and distilled prompts directly without dependencies, analyzing the refined version's faithful and lossless representation of the original text.
The best way to ensure a refined AI prompt remains faithful is to automatically verify the distillation process preserved all essential rules and executable instructions while maintaining appropriate conciseness.
charly-vibesCondense verbose developer-facing prompts into concise token-efficient LLM instructions.
Imad-OuteConvert complex documents into concise summaries for LLM processing.
ejolietDesign prompts, evaluate LLM outputs, and build agentic workflows.
eng-vmessiahAutomate regression tests validating API response shapes and state integrity.
