Prompt Evaluator

Evaluate LLM prompts on a 100-point scale based on research findings from Thorgeirsson et al. (2026), which demonstrated that writing quality—specifically coherence, instructional clarity, and information content—significantly predicts LLM-assisted programming performance.

Key Research Insights

• Information content > vocabulary: Adding missing information improves results; rewording without adding information rarely helps (Lucchetti et al.)
• Structure matters: Unorganized, vague prompts lead to failure cycles
• Declarative > interrogative: Declarative statements outperform questions (Chen et al.)
• Ambiguity kills: Unclear pronouns, implicit assumptions, and missing constraints are top failure causes

Evaluation Workflow

1. Receive the user's prompt
2. Read references/evaluation-rubric.md for detailed scoring criteria
3. Score each of the 5 axes (4 sub-items × 5pt = 20pt per axis, 100pt total)
4. For common issues, consult references/improvement-patterns.md for Before/After examples
5. Output the evaluation result using the template below
6. Provide a revised prompt