hrdtbs/prompt-evaluator
skills/prompt-evaluator/SKILL.md
Evaluate and score user-written LLM prompts on a 100-point scale across 5 axes (Clarity, Structure, Information Content, Specificity, Context), providing specific improvement suggestions and a revised prompt. Make sure to use this skill whenever the user asks to evaluate, review, score, or improve a prompt, or when they say things like 'このプロンプトどう？', 'プロンプトを評価して', 'rate my prompt', 'review this prompt', or 'is this prompt good enough?'. This skill focuses on scoring existing prompts, not writing new ones from scratch.
development
Updated May 14, 2026
$ install --global
skillsauthnpx skillsauth add hrdtbs/agent-skills prompt-evaluatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 14, 2026, 2:36 AM208.2s3 files scanned
SKILL.md
- name:
- prompt-evaluator
- description:
- Evaluate and score user-written LLM prompts on a 100-point scale across 5 axes (Clarity, Structure, Information Content, Specificity, Context), providing specific improvement suggestions and a revised prompt. Make sure to use this skill whenever the user asks to evaluate, review, score, or improve a prompt, or when they say things like 'このプロンプトどう？', 'プロンプトを評価して', 'rate my prompt', 'review this prompt', or 'is this prompt good enough?'. This skill focuses on scoring existing prompts, not writing new ones from scratch.
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
- Receive the user's prompt
- Read references/evaluation-rubric.md for detailed scoring criteria
- Score each of the 5 axes (4 sub-items × 5pt = 20pt per axis, 100pt total)
- For common issues, consult references/improvement-patterns.md for Before/After examples
- Output the evaluation result using the template below
- Provide a revised prompt
5 Evaluation Axes
| # | Axis | Points | Focus | |---|------|--------|-------| | 1 | Clarity (明確性) | 20 | Unambiguous intent, no unclear references | | 2 | Structure (構造) | 20 | Logical organization, appropriate segmentation | | 3 | Information Content (情報量) | 20 | Sufficient detail for task completion | | 4 | Specificity (特定性) | 20 | Concrete requirements, constraints, formats | | 5 | Context (文脈提供) | 20 | Background, audience, purpose clearly stated |
Output Template
Use this exact template because a consistent format helps the user easily compare evaluations and understand the scoring breakdown:
## プロンプト評価結果 / Prompt Evaluation
### 対象プロンプト
> [quote the evaluated prompt here]
### スコア
| 軸 / Axis | スコア | 主な所見 |
|-----------|--------|----------|
| 明確性 (Clarity) | __/20 | ... |
| 構造 (Structure) | __/20 | ... |
| 情報量 (Info Content) | __/20 | ... |
| 特定性 (Specificity) | __/20 | ... |
| 文脈提供 (Context) | __/20 | ... |
| **合計 / Total** | **__/100** | |
### 評価の概要
[1-2 paragraph summary of strengths and weaknesses]
### 改善提案
1. [specific, actionable suggestion]
2. [specific, actionable suggestion]
...
### 改善版プロンプト
[the improved prompt in a code block]
Scoring Guidelines
- 0pt: Sub-item is completely absent or counterproductive
- 1pt: Minimal attempt, mostly insufficient
- 2-3pt: Partially addressed, room for improvement
- 4pt: Well addressed with minor gaps
- 5pt: Excellent, no meaningful improvement needed
Language Handling
- Evaluate prompts in any language (Japanese, English, etc.)
- Output the evaluation in the same language as the user's prompt
- Scoring criteria apply universally regardless of language
Related Skills
hrdtbs/skill-judge
testing
VerifiedTrustedCommunity
Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement suggestions.
SKILL.mdUpdated May 14, 2026
hrdtbs/skill-creator
testing
VerifiedTrustedCommunity
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
SKILL.mdUpdated May 14, 2026
hrdtbs/prompt-engineering-expert
testing
VerifiedTrustedCommunity
Apply prompt engineering best practices to write, refine, and optimize system prompts, user prompts, and agent instructions. Use this skill whenever the user wants to write a prompt, optimize an existing prompt for better results, fix a prompt that is hallucinating or underperforming, or structure prompts for Large Language Models (LLMs). Even if the user just says "help me write instructions for my agent", trigger this skill.
SKILL.mdUpdated May 14, 2026
hrdtbs/plan-self-review
testing
VerifiedTrustedCommunity
Self-evaluate a plan on a 100-point scale after it is created or updated. Make sure to use this skill immediately whenever you create a plan or update a plan, even if the user does not explicitly ask for a review. This skill ensures that the plan is clear, comprehensive, feasible, and consistent before execution.
SKILL.mdUpdated May 14, 2026