eval-clarity
Original：🇺🇸 English
Translated
Score assistant responses for clarity on a strict 1-5 scale, then return strict JSON only with score, rationale, and improvement suggestions. Use when the user asks to evaluate clarity, grade clarity, or critique clarity quality.
16installs
Added on
NPX Install
npx skill4agent add whitespectre/ai-assistant-evals eval-clarityTags
Translated version includes tags in frontmatterSKILL.md Content
View Translation Comparison →Eval Clarity
Use this skill to evaluate how clear and understandable an assistant response is.
Inputs
Require:
- The assistant response text to evaluate.
Internal Rubric (1–5)
5 = Structured, unambiguous, direct answer, minimal fluff
4 = Mostly clear, minor ambiguity or verbosity
3 = Understandable but lacks structure or precision
2 = Vague, missing key steps, hard to follow
1 = Confusing, contradictory, or unclear
4 = Mostly clear, minor ambiguity or verbosity
3 = Understandable but lacks structure or precision
2 = Vague, missing key steps, hard to follow
1 = Confusing, contradictory, or unclear
Workflow
- Assess structure, precision, and readability.
- Score clarity on a 1-5 integer scale using the rubric only.
- Write concise rationale tied directly to rubric criteria.
- Produce actionable suggestions that improve clarity.
Output Contract
Return JSON only. Do not include markdown, backticks, prose, or extra keys.
Use exactly this schema:
{
"dimension": "clarity",
"score": 1,
"rationale": "...",
"improvement_suggestions": [
"..."
]
}
Hard Rules
- must always equal
dimension."clarity" - must be an integer from 1 to 5.
score - must be concise (max 3 sentences).
rationale - Do not include step-by-step reasoning.
- must be a non-empty array of concrete edits.
improvement_suggestions - Never output text outside the JSON object.